Physical AI Brief

3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference. We address this bottleneck and show that the animation of pretrained avatar models can be closely approximated by a linear combination of identity-independent blendshapes. Building on this finding, we introduce GALA (Gaussian Animation via Linear Approximation), a distillation method that replaces per-frame heavy neural decoding with a shallow coefficient predictor and a linear blend. To improve fidelity and reduce memory requirements, we propose to construct the basis using block-local PCA under a rendering-aware metric and a memory budget. Our method learns a shallow MLP network to predict blendshape coefficients and applies to various animation architectures without retraining original models. We validate GALA by accelerating the inference of three distinct avatar models for 3D animation of facial expressions and full-bodies with clothing dynamics. Across these models, our distillation generalizes to held-out identities and reduces CPU animation cost by up to three orders of magnitude while preserving most of the rendering quality. Excellent results of our method confirm the shared linear structure of learned avatar representations and enable highly efficient and accurate animation at frame rates reaching up to 60fps on mobile devices. Project page: https://ramazan793.github.io/gala/

LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks, and do not directly measure LLMs' ability to generate executable commands for real-world cybersecurity tools. This gap is critical because cybersecurity operations rely on strict command-line interfaces (CLIs), where minor syntax errors, incorrect flag--value bindings, or argument misordering can invalidate execution. We introduce KaliBench, a fine-grained benchmark and dataset for natural-language--to--CLI translation on Kali Linux, comprising 8,504 query--command pairs spanning 1,642 tools across 23 capability dimensions and 5 security phases. KaliBench is constructed via a manuscript-grounded pipeline with deterministic canonicalization and alias-aware evaluation, enabling precise and reproducible assessment of tool selection and argument construction. To ensure both semantic correctness and practical executability, we develop a multi-stage verification pipeline that combines LLM-based validation, sandboxed terminal execution, and human-in-the-loop refinement. Building on these fine-grained, deterministic signals, KaliBench further enables runtime-free verifiable rewards for training. Across three evaluation modes and 24 configurations of general-purpose and security-focused open-weight models, no open-weight model exceeds 42% exact-command accuracy in the unrestricted setting, highlighting the difficulty of accurate CLI-based cybersecurity tool use without explicit tool hints. We further show that supervised fine-tuning and reinforcement learning with verifiable rewards derived from KaliBench significantly improve an 8B model and achieve performance comparable to a 685B MoE model.

Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-generation game engines. However, their visual adherence to explicit rules and interactions remains insufficiently evaluated. Existing benchmarks assess visual quality, controllability, and instruction or physical adherence, but rarely test fidelity to fine-grained, program-specified world events. We introduce PROWBench, comprising 170 programmatically constructed episodes and 600 proxy videos covering diverse scenes and interactions. PROWBench logs entity states and timestamped events, including those outside the camera's field of view, as replayable world records, from which it renders synchronized views and proxy representations. This enables generated videos to be checked against the observable consequences of program execution. An extensible framework constructs scenes, controls behaviors, and can render each camera view in different representations, such as coarse 3D, and bounding boxes. The benchmark covers first- and third-person perspectives, with synchronized multi-view observations available for a subset of episodes. Grounded in these records, PROWBench evaluates entity control, long-horizon memory, and, with two VLM-based metrics, Logic-Render Alignment and Interaction Success Rate, adherence to the prescribed timeline and the visual realization of timestamped engine-recorded events.

Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model weights. RPG identifies manipulation capabilities in an offline dataset and constructs related practice tasks in simulation. During practice, RPG uses execution feedback, privileged simulator state, and available dataset videos to diagnose failures. It develops new reusable symbolic skills, refines existing skills, and revises the system prompt based on these diagnoses. Cross-task evaluation tests individual candidate changes and merged revisions before they are retained for reuse. At test time, a multimodal LLM uses the resulting system prompt and skill library to coordinate perception and robot control. On held-out initializations of 22 manipulation tasks, RPG improves task success from 28.6% after the first practice round to 95.0% after 15 rounds, outperforming all evaluated baselines, including ASPIRE (75.5%) and CaP-Agent0 powered by GPT-6 Astra Pro (60.0%). After a common calibration and hardware-adaptation procedure, the frozen system succeeds in all 30 physical trials, with ten trials on each of three tasks. Project Website: https://rpg-robot.github.io/

What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs. To study this skill, we draw on researchers who know firsthand which earlier work advanced their completed projects, with papers serving as pointers to the ideas within. Using our automated pipeline that makes author annotation scalable, we build ScholarCatalyst by having 184 lead authors of 207 recent computer science papers label which candidates did or could have advanced their project, each with a detailed rationale. We introduce a retrieval task with author-provided judgments: given an initial research question, retrieve these papers from only the literature available when the project began. Agentic search does no better than embedding retrieval (0.42 vs. 0.48 Recall@20) despite calling that same retriever as a tool. Even an agent built on Claude Fable 5.1, which may have seen the completed papers during training, reaches only 0.51 R@20. These results highlight the need for new training recipes that equip models with expert intuition for searching broad corpora. We envision ScholarCatalyst as a step toward scientific agents that can take a half-formed idea and point to the prior research it needs.

High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes. We introduce SILSA, a topology-aware 3D generation framework that represents shapes with compact sliding-window slice latents. Instead of generating expensive voxel tokens, SILSA uses a fixed set of overlapping slices along the three canonical axes, where each token summarizes a local depth window to preserve cross-sectional continuity and support single-stage rectified-flow generation. A Slice VAE encodes oriented surface samples into multi-axis slice latents and reconstructs them with a sparse volumetric decoder, while a Volumetric Anchor Lattice coordinates directional slice streams through a shared 3D workspace. To preserve structural correctness, we introduce slice-level topology supervision that matches persistence diagrams and aligns Betti transitions across neighboring slices. Experiments show that SILSA improves structural fidelity while substantially reducing generation cost. SILSA improves PSNR by $8.7\%$, coverage by $5.96$ absolute points, and Betti error by $9.2\%$ over the strongest baseline, while using $70.0\%$ fewer tokens than the next-most compact baseline and over $98\%$ fewer tokens than sparse or hierarchical tokenizers, effectively reducing training memory by $40.4\%$ and inference time by $58.5\%$. Qualitative results further show improved preservation of thin structures, repeated components, and long-range connectivity.

We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a general-purpose multimodal model long-horizon vision. VISTA allows the model to directly perceive the environment through visual observations and maintains a lossless visual memory that preserves past observations in their original form. The model can actively retrieve these observations and reorganize its visual input as it reasons. On ARC-AGI-3, VISTA improves Claude Opus 5.0's Relative Human Action Efficiency score from 40.68 to a perfect 100.00, with the model completing all 25 public games using 57.4% fewer actions than first-time human participants. VISTA's simple design also allows it to extend naturally to diverse visual environments with minimal adaptation. Across three additional benchmarks covering a diverse range of visual games and puzzles, it substantially outperforms baselines using the same underlying model with minimal harnesses. Our results highlight VISTA's potential as a general-purpose visual harness for advancing multimodal agents in complex visual environments.

Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory overhead, limiting the model sizes that fit on modern GPUs. Existing approaches either compress optimizer state, abandon first-order gradients, or change the update geometry while retaining dense state. The recently introduced Muon optimizer reduces optimizer memory through matrix-valued updates. Still, its geometry differs from AdamW and can lead to performance degradation when fine-tuning AdamW-pretrained models. To reduce optimizer memory without sacrificing accuracy or computational efficiency in LLM fine-tuning, we propose Ternary Absolute-max Column-wise One-sparse optimizer, or TACO, which follows Muon's operator-norm steepest-descent view but takes the geometric route further. TACO computes the exact steepest-descent direction under a dimension-normalized $1\to1$ operator norm by selecting the sign of the largest magnitude entry in each column of two-dimensional weight matrices. This retains first-order gradients while making optimizer state memory nearly negligible. Our practical TACO optimizer maintains only a small set of low precision gradient components per column, reducing persistent optimizer state by $174\times$ relative to AdamW8bit (from 27.7 GB to 0.16 GB) and peak training memory by $2.9\times$ (from 80.6 GB to 27.5 GB) on OPT-13B, while achieving comparable accuracy and runtime. TACO further enables full-parameter fine-tuning of 30-32B-parameter models on a single 80 GB H100 GPU across multiple model families and tasks.

Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically trained to predict returns, and accurate value predictions do not necessarily yield accurate action derivatives, potentially leading to unreliable policy updates. We propose Forward Entropy-Regularized Policy Optimization (FERPO), an on-policy maximum entropy reinforcement learning algorithm that performs policy improvement using critic values without differentiating the critic with respect to actions. FERPO derives an optimal target action distribution from a policy-improvement objective regularized by entropy and Kullback-Leibler (KL) divergence. We then fit the actor to this target by minimizing a forward-KL objective, estimated using self-normalized importance sampling (SNIS) with actions drawn from the rollout policy. By limiting the target distribution's deviation from the rollout policy, the KL regularization helps keep these importance weights well behaved. In contrast to reverse-KL objectives, which can favor a subset of the target distribution's modes, the forward-KL objective encourages coverage of multiple high-value modes and thereby promotes exploration. Experiments and ablations on MuJoCo Playground and ManiSkill show competitive performance and sample-efficiency gains. Computational benchmarks also demonstrate faster actor updates than Relative Entropy Pathwise Policy Optimization (REPPO).

Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this progress, they still fail to generate videos which adhere to laws of physics. The problem becomes even more apparent in realistic settings where multiple physical principles must work together within the same video; for example, "a balloon floating upward while steam rises from a pot" requires buoyancy and fluid dynamics to unfold coherently and simultaneously. Yet existing methods largely ignore multi-principle interactions, focusing on a single principle per video. We propose HiPhy (Hierarchical Physical Alignment), a reinforcement learning framework that grounds video generation in physical laws through a dual-level objective: locally enforcing the temporal dynamics of individual physical principles, and globally ensuring the physical and semantic coherence of the entire scene. To support multi-principle generation, we construct a 50K-prompt dataset and introduce a prompt benchmark MultiPhyBench, spanning a diverse range of co-occurring physical events. Our experiments show that HiPhy significantly outperforms prior methods and baselines, improving physical commonsense and semantic alignment significantly across various benchmarks, with the largest gains on scenes involving multiple concurrent physical principles where competing methods degrade most sharply.

We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attempts, and retaining what it learns, without retraining. Our key insight is that a broad controller already holds much of the competence a new task needs, and that this competence becomes accessible through an interface between planning and control that is expressive enough to specify contact-rich, multi-stage interactions, yet executable and measurable enough that execution feedback can guide planning from experience. InterEvolve realizes this interface with two components. First, we develop an object-aware forward-backward (FB) behavioral foundation model, whose object residuals on a frozen body prior turn a new reward about the body or objects into loco-manipulation behavior at test time. Second, we specify tasks as reward programs: staged rewards with completion conditions and tunable constants. A large language model (LLM) agent revises the program structure in context, drawing on execution feedback and a skill library of verified programs, while a numerical optimizer tunes its constants. With every candidate verified across parallel simulation scenarios, the program explores new ways to induce, repurpose, and compose the controller's existing motor competence for the task at hand, and thus improves over iterations. Experiments show that human-designed rewards leave much of the FB model's loco-manipulation competence untapped, whereas the programs InterEvolve evolves release it, sometimes through novel strategies. It further produces behaviors for diverse tasks, complex scenes, and long-horizon compositions in simulation, and evolved skills run autonomously on a physical Unitree G1 from egocentric onboard perception.

The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. It has been approached by learning the rates of a controlled continuous-time Markov chain, with a temporal-difference penalty that restores the cost. A state cost folds into the reference process as a Feynman-Kac tilt. The cost-augmented bridge is then a plain bridge against the tilted reference, and the penalty is unnecessary. The bridge is computed exactly by alternating two endpoint rescalings, each one sparse matrix-exponential application; nothing is discretized in time or learned. The alternation converges at a rate set by the endpoint coupling alone. For a quadratic congestion cost on time-averaged occupancies, damped best response around the exact bridge is gradient descent on a strongly convex function, and its residual bounds its error. On a protein-folding model, a free-energy cost lowers the expected barrier of the folding paths. On the learned approach's road network, roll-outs of the exact bridge match the target within sampling error, and on networks with millions of intersections its memory grows linearly.

While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions. In this paper, we take a first step toward systematically studying mathematical understanding in LLMs, from diagnosing its distinct capabilities to leveraging these findings to improve post-training. First, we introduce the notion of Mathematical Primitive to probe structural mathematical understanding and propose \hlei{}, a novel benchmark that evaluates mathematical reasoning along four distinct dimensions: Discovery, Generation, Digestion, and Execution. Second, our systematic diagnosis shows that solution accuracy masks distinct capability profiles, primitives unlock substantial latent execution capacity, and Discovery is the dominant bottleneck in mathematical reasoning. Our post-training analysis further shows that discovery-limited failures are particularly amenable to repair. Finally, building on these findings, we introduce \abs{}, a primitive-privileged self-distillation framework that selectively transfers primitive-guided reasoning into the student model. Extensive experiments demonstrate that \abs{} consistently improves mathematical reasoning over baselines across model scales and challenging benchmarks.

Intrinsically disordered protein regions (IDRs) play central roles in cellular processes such as transcriptional regulation, signal transduction, and subcellular localization, yet their functional design remains challenging. Structure-based design methods do not readily apply to IDRs, and existing protein language models are trained on full-length protein sequences, thus learning a prior that is biased towards folded domains. Here, we present IDiom, an autoregressive protein language model trained on IDiom-DB, a dataset of 54 million predicted IDRs curated from the AlphaFold Database. IDiom generates diverse sequences that recapitulate the composition, patterning, motifs, and predicted disorder of natural IDRs. To control function-associated sequence patterns, we also introduce reinforcement learning with sparse autoencoder features (RL-SAE), a post-training method that rewards the generation of sequences that activate specified feature sets. Across eight IDR design tasks, RL-SAE sequences activate, on average, 90% of 30 targeted features, compared to 24% for activation steering. We demonstrate that RL-SAE improves the predicted subcellular localization and transcriptional activity of generated IDRs compared to steering and supervised fine-tuning, and enables features associated with distinct biological functions to be combined within individual sequences. Thus, IDiom and RL-SAE enable interpretable and composable IDR design through explicit control of function-associated sequence features. More broadly, RL-SAE could extend to other protein design settings where interpretable features provide useful design targets. Code is available at https://github.com/rotskoff-group/idiom.

Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving distribution at extra memory and computation cost. We introduce DMAD, Distribution Matching as Adversarial Distillation, which recasts distribution matching as classification and learns the required log-density ratios directly. Two discriminator heads on a shared backbone distinguish real data and teacher samples from the student's, and linear losses on their logits train the student without auxiliary score fitting. We prove that at the discriminator optimum these losses recover the distribution-matching gradient underlying DMD, through the classical identity linking discriminator logits to log-density ratios. We further introduce gap-based reweighting, which adapts teacher supervision across noise levels from the real-data head's empirical logit gap between real and teacher samples. DMAD reaches a Fréchet Inception Distance (FID) of 1.04 with one-step generation on ImageNet-64x64, 14.47 with four-step SDXL on COCO-10K, and a VBench total score of 85.15 with four-step Wan2.1-T2V-14B, the best values among the compared few-step methods and the multi-step teachers. On MiniMax-H3-33B, our four-step student achieves overall human preference rates of 79.1% over DMD2 and 84.6% over rCM for joint audio-video generation, excluding ties. Our code, models and demos are available at https://yzmblog.github.io/projects/DMAD.

Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitly encode higher-order topology, such as ring systems and recurring motifs. Existing higher-order representations can capture these structures directly, but they are often computationally demanding and difficult to decode into valid molecules. Here, we introduce Higher-order Grammar Representation (HGR), a principled, topology-aware framework that lifts molecules to combinatorial complexes and parses each complex into a compact sequence of production rules under a context-free higher-order grammar. By serialising higher-order topology into rule sequences, HGR makes these structures directly compatible with standard sequence models, avoiding the computational overhead of explicit higher-order encodings while preserving topological expressiveness. To reduce benchmark bias towards simple ring systems, we construct RingDiv, a ring-enriched benchmark containing 1.18 million molecules, including the curated RingDiv300k subset, and introduce the ring diversity index (RDI) to quantify ring-system coverage. In molecular generation, HGR-based models uniquely combine 100% validity by construction with leading distributional alignment, ranking first in FCD on all five generation benchmarks. In representation learning, HGR-FM achieves the highest mean AUC across seven MoleculeNet benchmarks under both transfer protocols, improving on the strongest baseline by 8.3 and 3.3 AUC points under probing and full fine-tuning, respectively. Collectively, these results establish HGR as an efficient higher-order representation for molecular generation and transferable representation learning.

We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native tool use. Rather than passively processing an entire audio-visual sequence in a single forward pass, OmniSeek makes evidence acquisition part of the reasoning process: it dynamically decides whether to look or listen, and over which temporal window, to retrieve sparse but critical evidence across different modalities within long contexts. Through an iterative multi-turn protocol, the retrieved raw audio or visual segments are appended back into the context to support subsequent reasoning. To cold-start this capability, we build a data engine that synthesizes OmniTraj-170K, a corpus of multi-hop Chain-of-Thought trajectories with interleaved audio and visual evidence. We first supervise the model on these trajectories to instill multi-turn tool-use behavior, and then further optimize the policy via a two-stage reinforcement learning with verifiable rewards. Moreover, we introduce an Audio-Visual Necessity objective that explicitly rewards successful trajectories whose reasoning depends on both modalities, discouraging single-modality shortcuts. Extensive experiments across a wide range of benchmarks demonstrate that OmniSeek learns adaptive cross-modal evidence seeking and consistently improves audio-visual reasoning performance.

Robots operating in the physical world will increasingly need to coordinate with other robots, particularly in manipulation tasks where an object may be too large or heavy for a single robot to carry alone. Physical limitations caused by hardware degradation or actuator faults can restrict the actions a robot can reliably execute, yet these limitations may be unknown to its partner. We study whether a helper can infer a robot partner's physical constraints from observing it coordinate with another robot, then use the inferred capability to coordinate with the same partner on a new task. This is difficult because a demonstration shows what the constrained robot did, but not what it could have done. In physically coupled tasks, the other robot may also compensate for its limitations, making those limitations difficult to identify from the constrained robot's behavior alone. Our key insight is that these constraints shape the joint behavior of the team, making the actions of both robots informative about the constrained partner's capability. We introduce Watch, Infer, Coordinate, a benchmark spanning three physically coupled manipulation settings, together with an inference approach that scores candidate constraints using observed joint behavior. Across all three settings, our method substantially improves constraint inference and zero-shot coordination, approaching an oracle with access to the true constraints.

Coding agents solve repository-level software engineering tasks through long trajectories of code inspection, search, editing, and testing. As a task progresses, earlier exploration becomes stale, so managing context is more than avoiding overflow: an agent must decide when to compact, what working state to preserve, and how to continue from it. We introduce AutoCompact, which trains a coding agent to make these decisions as part of its policy. To collect training data, we run the base agent on coding tasks and use a judge to review its compaction decisions, summaries, and actions after compaction. Flawed outputs are replaced with corrected ones before being executed in the environment, so each trajectory continues from the corrected decisions. We use these trajectories for supervised fine-tuning, then jointly optimize coding and compaction through reinforcement learning with task-success rewards. Experiments on SWE-bench Verified and SWE-PolyBench Verified show that AutoCompact improves pass rates over the base model by an absolute 9.2\% and 5.0\%, respectively. The improvements hold across all evaluated inference budgets, with a 256K context window that never overflows and with a 16K window whose overflow triggers fallback compaction.

How can a world model continuously observe regions beyond the actor's current view? Video world models simulate how an environment evolves from an agent's actions, yet remain actor-centric. Once an object leaves the actor's view, they lose direct evidence of its evolution, often failing to preserve its state and dynamics upon re-entry. To address this, we introduce World Observer, which decouples observing from acting by jointly generating a perspective actor for the agent-centric view with one or more panoramic observers that watch selected world regions. This allows objects that leave the actor's view to remain visually evolving in an observer, so their updated states are reflected when they re-enter. We ground the actor and observers by warping from a shared panoramic source for explicit geometric correspondence, and introduce an Observer Sink of high-resolution perspective references to restore fine appearance upon re-entry. Since the observers are decoupled from the actor, they can be placed freely across the scene, extended to multiple locations for broader coverage, and driven by control signals to steer out-of-view evolution. To evaluate out-of-view evolution, we further introduce world-space metrics and a benchmark spanning real and synthetic scenes. World Observer substantially improves out-of-view dynamics while remaining competitive in visual fidelity, camera control, and 3D adherence.

Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progress has focused on single-robot settings. Extending these capabilities to multi-robot systems remains challenging because robots must coordinate long-horizon behaviors while maintaining reliable, fine-grained execution. We introduce DuoMind, a distributed hierarchical framework for multi-robot coordination through semantic communication. Each robot uses a VLA-based action model for low-level execution and a VLM-based orchestrator for high-level reasoning and inter-agent coordination. At each planning step, the orchestrator at each robot reasons over the task instruction, local observations, and messages received from other robots. It then generates low-level instructions for the action model and semantic messages for peer robots. This architecture exploits the complementary strengths of pretrained models by combining the semantic reasoning capabilities of VLMs with the precise action-generation capabilities of VLAs. To address the scarcity of benchmarks for multi-robot coordination, we further develop RoboPoly, a benchmark comprising long-horizon manipulation tasks that require coordinated, closed-loop execution under distributed control. Experiments on RoboPoly and RoboTwin demonstrate that DuoMind improves multi-robot task performance, while ablation studies confirm the contributions of hierarchical orchestration and semantic communication. More details are available on our project page.

Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through image-plane cues that are ambiguous in depth and rotation or through 3D tracks and blobs that lack complete geometry and lose consistency across viewpoint changes. We introduce 4Director, a video world model conditioned on an explicit 4D scene representation: each object is reconstructed once from the input image as a canonical mesh and moved by one prescribed rigid transformation per frame. This representation provides an intuitive 3D control interface and prevents unobserved geometry from being regenerated independently in every frame. We render the controlled scene as a depth video and introduce a Motion Adapter that transforms this geometric scaffold into video while synthesizing view-consistent appearance, illumination, and non-rigid dynamics. For training, we construct RealCOD-Rigid, a new dataset of 20,774 clips annotated with rigid 3D scenes by our automatic pipeline. We further introduce Identity-Gated IoU (IG-IoU), which jointly evaluates adherence to prescribed object motion and preservation of object identity. Experiments demonstrate that 4Director consistently outperforms prior methods in visual quality and in camera and object control.

Long-horizon autoregressive video generation is limited by a finite context window. When an object or scene falls out of context, its fine-grained visual details may be lost and difficult to recover upon reappearance. To retain access to such visual details, we introduce MosaiChunk, a spatio-temporal memory mechanism that composes a mosaic of selected historical key-value (KV) entries across space and time. Our approach is motivated by the observation that a frozen video generator can directly consume such non-contiguous historical KV and recover the corresponding visual content. We therefore keep the generator fixed and learn only a lightweight router that determines which historical sections to include in the mosaic under a fixed active-memory budget. We further introduce RememBench, a benchmark of long-horizon revisits with prompt-driven text-to-video (T2V) and camera-driven image-to-video (I2V) splits. Our experiments show that MosaiChunk consistently improves revisit consistency over both sliding-window inference and whole-chunk retrieval under matched memory budgets, across both T2V and I2V settings.

Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods improve how source content is accessed and organized, while agent-memory systems preserve reusable knowledge from prior interactions, but repeated use of the same source is still largely treated as repeated access rather than an opportunity to progressively improve understanding of that source. We study source learning: developing reusable source-specific competence over a persistent authoritative source. We represent this competence with a persistent source model that captures reusable understanding of the source, including how its knowledge is structured, interpreted, and applied. To construct and progressively refine such models, we propose SourceLearn, which combines two complementary learning mechanisms. Self-Directed Source Learning identifies what remains incompletely understood and adaptively revisits the source, while Task-Guided Source Learning uses downstream experience to reveal local representational gaps and recurring needs in how source knowledge should be organized. In both cases, learning signals determine what should be reconsidered, while persistent updates are reconstructed from the authoritative source. Across five benchmarks and three LLM backends, SourceLearn achieves the best performance in 13 of 15 settings, with gains of up to 22.6 points over Hybrid RAG and substantial overall improvements over static source representations and experience-based memory baselines.

We introduce Faynt, a family of 10M- and 75M-parameter Transformer policies for Super Smash Bros. Melee, each controlling all 26 characters with a single checkpoint. After reinforcement learning (RL), the 10M wins 240 of 244 same-character games (98.4%) against fourteen specialist and multi-character releases on their supported rosters, with a winning record against every release. These opponents retain 21- or 24-frame action delays; Faynt uses no added delay, and we have not isolated the effect of this difference. In a separate evaluation against a privately supplied zero-delay Slippi-AI model, the 10M wins all 68 games across two conditioning settings. We study architecture, optimization, scaling, and hyperparameter transfer to guide pretraining on approximately 840,000 human replays. Post-training combines rank- and outcome-based curricula, 75M-to-10M distillation, and RL restricted to Fox mirror matches. On the initial 152-game benchmark, the supervised 10M wins 69.7% of games, compared with 45.4% for the pretrained 75M, despite higher overall held-out controller-prediction loss. The weighted validation loss used for supervised checkpoint selection agrees with the win-rate ordering of all four pretrained and supervised policies. After supervised post-training, both models take less damage per minute, build larger early leads, and win more often after losing the first life. Optimized inference on recorded game states averages 5.2 ms per decision for the 10M and 8.7 ms for the 75M on an NVIDIA T4, excluding emulator execution and communication. We open-source the weights, both benchmark suites, and a platform for automated model tournaments.

Keyword-matching benchmarks can credit small models for tool use they never perform. We document such a false positive in a matched-architecture pair of Spanish security language models and propose a ladder of strict, cheap diagnostics. A 661.6M parameter model (approx. 65% code/technical text; no dedicated SFT) and a 1,109M model (web-heavy multi-phase curriculum; 6B-token tool-SFT) share decoder, tokenizer, and special tokens, scoring almost identically on lenient tool-use metrics (B4: 0.660 vs. 0.650). Verbatim-reproduction checks on training examples separate them completely: the 600M emits valid tool calls with generalized arguments on 6/6 examples; the 1B does so on 0/6 across checkpoints. A first-token probe localizes the 1B's failure to a missing prior (prob. $10^{-4}$--$10^{-5}$ on <|tool_call|>), which was erased by its web-heavy training phase. A targeted SFT recipe (diverse corpus, 5x higher learning rate, 2,202 steps, ~3.3 GPU-hours) repairs the 1B using three orders of magnitude fewer tokens than the failed phase. On all 269 corpus rows, valid emission rises from 0.100 to 0.959 (600M: 0.926). On 238 unseen prompts, the repaired 1B passes 0.536 vs. the 600M's 0.428 ($p = 0.004$). Embedding-drift checks show the repair did not move the trigger token's tied embedding (97.7% of the bf16 table remains bit-identical), meaning changes live in the surrounding network. Both models over-trigger, rarely answering negative prompts without a call (0.09 for 600M, 0.17 for repaired 1B). Factorial analyses confirm all repair configurations install the format, though suppression benefits from a diverse corpus remain a hypothesis due to seed sensitivity. This cheap diagnostic ladder costs minutes of CPU time and should gate tool-use claims on small models.

Unsupervised anomaly detection (UAD) methods for brain MRI are ranked by a single score, yet that score rests on choices that are rarely reported: how each anomaly map is aligned with the reference, how and on which data the threshold is set, and which false-positive budget, metric, aggregation and lesion definition are used. We present MIRTO, an evaluation protocol that makes these choices explicit and measures their effect. It gates the geometry of every comparison with a registration check and label-free diagnostics of known power, sets thresholds on validation data alone and reports the false-positive volume actually realised on test, repeats each comparison over 15,552 defensible evaluation pipelines, and attaches paired subject-bootstrap intervals with multiplicity control. Applied to four UAD methods trained on the same healthy data and tested on 312 BraTS 2020 subjects, MIRTO showed that an axis-order mismatch between stored maps and the reference lowered a diffusion model's voxel AUROC from 0.873 to 0.583 whilst barely moving its slice-level AUROC. Within each metric, the method explained at least 0.95 of the variance in voxel AUROC and AUPRC and 0.77 in Dice, but only 0.14 in lesion sensitivity, where the lesion definition and hit criterion dominated. A Dice advantage that was significant at validation thresholds vanished at equal realised false-positive burden, and an exact identity attributes it to threshold transfer. A training-free change to REFLECT's latent aggregation raised Dice at equal burden by 0.052. Nine hypotheses were tested against explicit criteria; because the same cohort served to develop the protocol, all inference is exploratory.

Many applications in statistics, economics, and physics require sampling from high-dimensional categorical distributions with local dependence structures. Examples include finite memory language models, Ising and Potts systems in statistical physics and protein folding, etc. In modern machine learning, discrete diffusions have emerged as a flexible approach for sampling such data, with strong empirical performance. Motivated by this, we develop learning methods with end-to-end sample complexity bounds for discrete diffusion with uniform noising under local dependence, which we model through low order Markov random fields (MRFs). Our main technical insight is a new \emph{pinning decomposition} of the discrete score. It shows that unlike in continuous diffusions, the score decomposes into components where the dependence on time separates multiplicatively from the dependence on the target. Building on this decomposition, we propose a \emph{weight-sharing neural score learner} and combine it with $τ$-leaping to obtain an end-to-end sampling procedure. Rather than treating score-learning error as a black-box input, as is common in existing sampling analyses, we study the score learning error from finite data and derive optimal sampling guarantees with explicit dependence on the vocabulary size, the interaction order of the MRF, and the sample size. Moreover, our strategy trains a single score network across uniform noise levels while leaving the sampling discretization to be chosen at inference-time. This allows the same trained model to trade accuracy for computational cost as inference-time budgets vary. Numerical experiments on Potts, Ising, and tree-structured models show that weight-sharing score networks outperform fully connected ones for sampling long sequences.

We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of each weight matrix, we uncover a natural retention objective under which updates produced by gradient-based optimizers are suboptimal. Following this observation, we propose Local Support Learning (LSL), a general-purpose framework that augments gradient-based training for retention of prior capabilities without access to prior data. During a new learning phase, LSL pairs two components with distinct roles: a standard weight adapter, trained as usual to minimize the loss, and a gating function that enables the adapter only on input activations from its own training distribution, making the update local to that distribution. The key challenge is that this gate must route data from all learning phases while training only on data from the current one. We address this with a gate based on a Gaussian Mixture Model (GMM), whose likelihood decays rapidly away from its training data, giving it a natural tendency to stay closed on data from prior phases. We show that this post-training approach can resolve forgetting in LLMs of up to 7 billion parameters, retaining both pretrained and finetuned capabilities across multiple training phases, while being efficient in memory and compute, robust to hyperparameter choice, and showing scaling potential.

Real-world enterprise data science and analytics workflows require reasoning across dozens of tables, performing statistical analyses, and acting on the results. Established text-to-SQL benchmarks evaluate query generation alone, and audits have found their answer keys frequently wrong. Because real enterprise warehouses are too sensitive to release, these benchmarks are built on public datasets where a business event fits in a single table. We introduce Argo-Bench, an evaluation framework comprising 210 data science and analytics tasks. Drawing on public data, peer-reviewed industry literature, and regulatory filings, we simulate a food delivery platform in New York City at true scale, with 81 million orders in 2024, grounded economics, fraud patterns, and marketplace incentives. We export this world to an ERP warehouse of 235 tables and 7.5 billion rows, modeled on the Oracle E-Business Suite schema. The simulator's ground-truth state is withheld from the warehouse the agent sees, so tasks require reconstructing facts by navigating the warehouse before acting on them. Argo-Bench goes beyond text-to-SQL: the agent files actions such as banning fraudulent accounts, allocating courier incentive budgets, or issuing back pay, and the grader scores each by its consequences in the simulator. Every task has an executable reference solution that demonstrates solvability using only the warehouse. The strongest of 14 frontier and open-weight models scores 95 or higher on only 34.8% of tasks and averages 59.5 points. We hope Argo-Bench drives progress toward agents that understand, navigate, and act within real data environments.

World action models (WAMs) combine robot action generation with future state prediction. Existing WAMs typically predict videos or learned visual latents, which represent interaction geometry only implicitly and may retain appearance information unrelated to control. We introduce SkeleWAM, a compact WAM that represents a manipulation scene as a sparse 3D skeleton composed of robot joints, object centers, and interaction points. Constructed online from current RGB-D observations and robot proprioception, the skeleton provides a unified geometric state for action generation and future skeleton prediction. Future skeleton prediction provides additional geometric supervision for action learning without requiring visual reconstruction. At inference, SkeleWAM generates actions directly from the current skeleton and language instruction, while Medoid Action Consensus (MAC) serves as an auxiliary consensus strategy for stochastic action samples. On LIBERO-Plus, SkeleWAM achieves an overall success rate of 85.9% with 57.1M parameters, outperforming Cosmos-Policy by 3.7 percentage points. These results demonstrate that sparse 3D robot--object structure provides an effective state space for robust and parameter-efficient world action learning. The project is available at https://skelewam-project.github.io/.

On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of themselves that receives privileged information. Its application to multimodal large language models (MLLMs), however, remains largely unexplored. Recent approaches use privileged visual information, such as image crops corresponding to a question, to improve fine-grained perception, but their gains are confined to tasks that benefit from such visual zooming and require either human-annotated grounding data or external teacher models. We introduce a different form of on-policy self-distillation for MLLMs that provides the teacher with textual, spatially grounded guidance identifying the visual elements relevant to a query. We use procedurally generated scenes with automatically available object identities and spatial coordinates, enabling scalable and annotation-free post-training. The teacher uses this spatial guidance to locate and integrate evidence from multiple relevant image regions, while the student learns to reproduce the resulting behavior from the image and question alone. Our approach consistently improves performance on counting, document and chart understanding benchmarks across multiple models. Importantly, although post-training uses only synthetic scenes, the resulting improvements transfer to real-world perception benchmarks, yielding a 3.23-point gain in average performance across CVBench, V*, ZoomBench, BLINK, HR-Bench, and MME-RealWorld. These results show that spatially grounded privileged information can induce broader perceptual capabilities through on-policy self-distillation, enabling substantial synthetic-to-real transfer beyond the task and data distribution used for post-training. Project page: https://github.com/sirkosophia/Where-OPD

As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use requires selecting a suitable tool and coordinating manipulation and, when needed, locomotion to complete the task. Existing benchmarks do not jointly evaluate these capabilities on a humanoid. We introduce HumanoidToolBench, an 18-task benchmark spanning three scenarios, three execution levels, and two tool-set modes, together with ToolBook, a dataset of 3.1k demonstrations collected in simulation and on a real Unitree G1. Evaluation of seven policies in simulation and three on the real robot reveals substantial gaps between selecting a suitable tool and completing the task. Focused GR00T N1.7 probes show reduced selection accuracy on unseen tools and continued task execution under unrelated instructions. Code and data are available at https://snu-pi.github.io/HumanoidToolBench/.

Epitaxial quantum dots (QDs) are widely recognised as one of the best quantum light sources, given their good stability, brightness, quantum efficiency and coherence. To reach such properties, QDs are protected from potentially detrimental surface states by a relatively thick capping layer, typically exceeding 50nm. This prevents the implementation of near-field effects, like plasmonic-based ones, that can dramatically increase the light-matter interaction, since the control of the spontaneous emission dynamics and directionality of the emission can only occur if the emitter is in close proximity (typically tens of nanometers or less) from the metallic structures. In this work, we report the growth and optical characterisation of InAs/GaAs QDs with GaAs capping layer thickness of 10nm, 20nm, and a more standard 95nm. Remarkably, we observe emission linewidths up to 5 times smaller than previously reported, with unperturbed excitonic lifetimes. These results demonstrate that the epitaxial QD's high optical quality can be maintained even when the emitters are at reduced distances from the surface, opening the path for the exploration of near-field light-matter interactions with coherent and stable emitters, suitable for quantum technology applications.

Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomorphic Encryption (FHE) offers a compelling solution for secure computation, preserving data confidentiality of cloud computations. However, applying FHE to reinforcement learning (RL) requires replacing non-linear operations with polynomial approximations, which diverge catastrophically due to a unique recursive error phenomenon known as the Bellman drift. This article introduces the Homomorphic Advantage Operator (HAO), a stabilization framework designed to prevent polynomial approximation divergence in FHE-based deep RL. HAO adapts the zero-mean centering projection from advantage-based value estimation directly to temporal-difference (TD) targets. This linear projection annihilates the uniform state-value baseline that drives the Bellman drift, maintaining per-state action rankings while requiring zero additional non-linear multiplicative depth and avoiding expensive ciphertext bootstrapping. The proposed HAO framework was evaluated using a three-tier experimental methodology, including a tabular Markov Decision Process (MDP), an encrypted CartPole environment using real CKKS cryptographic operations, and a 20-node logistics routing benchmark with dense continuous features. The results demonstrate that the proposed HAO strictly bounds network pre-activations within the safe polynomial approximation domain. The proposed HAO RL agents achieved 0% boundary breaches across all random seeds used, whereas regularization alone (L2 weight decay and gradient clipping) breached the bound on 3 of 5 seeds and the unstabilized baseline did so in 83.8% of episodes. Finally, HAO agents improve optimal policy accuracy by 18.0 percentage points in tabular domains and remain stable when DP-SGD-style Gaussian noise is added to the clipped gradients.

Memory-augmented large language models must decide which memories to retain, and recent systems do so by estimating each memory's effect on task performance. However, these estimates rely entirely on retrieved memories. When a memory is never retrieved, store-level interventions produce identical outcomes, leaving its utility unidentified. This is a retrieval-level positivity violation, invisible to diagnostics that examine only memory operations. We introduce Causal Memory Policy (CMP), a causal framework that restores identification by intervening on retrieval itself, reserving a fixed number of context slots for memories sampled with known propensities. CMP estimates memory utility by self-normalized inverse propensity weighting under a balanced assignment design. We prove the causal factorization of memory utility through retrieval, the unbiasedness and exact variance of the estimator, and the optimal decision rule under irreversible operations. Empirically, identification fails for 54% of required memories on LongMemEval and 67% on LoCoMo, and the failure persists in a deployed memory system. CMP improves discrimination between required and non-required memories from 0.54 to 0.66 AUC. Finally, we show that identified memory utility alone is insufficient for retention decisions: per-query utility reaches 0.78 AUC on the query for which it is estimated, yet no aggregation available to a retention policy predicts a memory's value on unseen queries. Code is available at: https://anonymous.4open.science/r/cmp-release-D0C3/.

How complex can the responses of a quantum device become as it runs longer with a fixed internal memory? We quantify this complexity through sequential response capacity: how many adaptive testing stages, each using a fresh run, can continue to separate possible processes by a prescribed gap in response probabilities. For fixed system and memory sizes, we establish a tight law relating this capacity to run length and probability resolution. At fixed resolution, the capacity grows on the order of $K\log K$, where $K$ is the number of time steps in each run. Our construction attains this growth using time-dependent phase rotations on a single visible qubit with no additional internal memory; its tests give response probabilities exactly zero or one. Under the same tests, classical stochastic processes that measure in a fixed basis at every step have only linear capacity at fixed sizes and resolution. For phase sequences selected by a stored classical label, we then quantify how known independent Pauli noise changes this logarithmic enhancement. With ideal controls and weak residual phase noise after correction, we prove matching capacity bounds at a fixed small probability gap. These bounds identify the inverse residual phase-flip probability as the coherence timescale that limits the extra logarithmic growth.

While Low-Rank Adaptation (LoRA) enables efficient task specialization, its learned updates can compromise capabilities beyond the target task. We identify \textbf{adaptation imbalance}: a few singular directions dominate the trained update, leaving its performance sensitive to how gains are allocated. We argue that \textbf{learning where to adapt does not ensure that adaptation gains are well balanced}. This motivates \textbf{LoRA-Norm}, a post-training normalization method that retains learned directions while rebalancing their gains. LoRA-Norm combines spectral rebalancing, a fixed nonlinear transformation of singular values, with nuclear-norm restoration, which preserves the original total spectral mass. It requires no calibration data or additional training and introduces no inference overhead. Across two backbones and three adaptation tasks, LoRA-Norm improves average specialization and capability retention, outperforming the evaluated post-hoc spectral pruning and gradient-guided editing configurations on both measures. Stronger functional equalization brings no consistent additional gains, revealing that balancing adapter gains and equalizing their responses are distinct objectives.

Despite the success of Time Series Foundation Models (TSFMs) on broad benchmarks, their ability to internalize basic temporal logic, especially in settings supported by exogenous covariates, remains under-examined. We introduce SimpleTimeBench, a diagnostic univariate and multivariate "unit test" suite for primitives such as monotonic trends, periodic signals and leading indicator covariates, scenarios where near-perfect forecasts should be trivial. Surprisingly, prominent multivariate TSFMs (Chronos-2, Moirai and Toto) frequently produce suboptimal zero-shot forecasts for these inputs. While fine-tuning Chronos-2 improves its behaviour on specific tasks, we show that this adaptation degrades performance on other fundamental patterns rather than enhancing its generalizable foundational capabilities. This reveals a gap between pre-training scale and basic temporal reasoning, suggesting that current TSFMs could potentially lack the inductive biases needed to capture simple predictable functions. We further demonstrate that these failures are not merely synthetic curiosities: they persist in real-world sensor forecasting, where TSFMs consistently underutilize leading indicators available in observed covariates. This inability to capture simple relationships limits the practical utility and reliability of current multivariate models.

Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in world dynamics. Conversely, world-action models inherit spatiotemporal priors from video generation models, yet remain limited in semantic understanding and reasoning under distribution shifts. We introduce UniWAM, a unified architecture that integrates a physical reasoner, a world generator, and an action predictor to jointly learn semantic understanding of the physical world, visual generation, and action prediction. To ensure the quality of the training data, we developed a rigorous data cleaning and annotation pipeline for both human egocentric data and robot data. To adapt the vision-language component to embodied tasks while preserving its inherited language capabilities, we represent low-level actions in natural language and introduce a pre-training recipe that assigns complementary supervision from visual question answering (VQA) data, human egocentric data, and robot demonstrations to the appropriate model components. During post-training, future visual noise augmentation reduces reliance on precise future predictions, while history-conditioned flow matching uses encoded action history to initialize action generation. Together, these designs significantly reduce denoising steps while maintaining performance. UniWAM achieves state-of-the-art (SOTA) performance across multiple evaluations, including in-distribution performance, robustness, generalization, instruction following, and long-horizon task execution. Furthermore, we uncover a log-linear scaling law of unified human-robot co-training, demonstrating the effectiveness of large-scale pre-training on a mixture of human and robot data.

Adverse weather image restoration aims to recover images degraded by rain, haze, snow, and other weather-induced artifacts, thereby improving the robustness of outdoor vision systems. Existing unified restoration models exhibit limited generalization to real-world scenes due to their reliance on synthetic supervision and insufficient semantic constraints. In this paper, we propose a novel student--teacher semi-supervised framework that addresses both challenges. Specifically, we introduce an unreliable database that preserves failed teacher predictions as informative negative samples for contrastive learning, while a reliable database stores high-quality teacher predictions as positive samples. By jointly exploiting reliable pseudo-ground truths and unreliable teacher outputs, the proposed framework learns to enhance desirable restoration characteristics while avoiding common failures. We further propose a phase spectrum-based semantic constraint that replaces computationally expensive text-based supervision with an efficient and naturally aligned semantic prior. An adaptive phase consistency loss is also designed to dynamically balance supervision between the degraded input and teacher pseudo-ground truths according to degradation severity. Extensive experiments on real-world benchmarks demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches in restoration quality and perceptual fidelity while exhibiting stronger generalization to real-world adverse weather conditions.

When a SCADA alarm is raised in a water distribution network, operators must decide quickly whether it reflects a cyberattack, a physical fault, a normal transient or a faulty sensor. Supervised classifiers need labelled incidents that utilities rarely have, and frontier large language models (LLMs) take tens of seconds per decision. We tested whether Jev, a training-free model that returns class probabilities in about one second, can serve as the first tier of this triage. On a four-class cause-attribution benchmark built on the C-Town network in EPANET, Jev was compared with a hand-written rule tree, a supervised classifier and seven cloud LLMs on identical evidence in four sealed, pre-registered rounds. With only a label-free prior correction, Jev matched the rule tree (macro-F1 0.62-0.64 against 0.56-0.61 in distribution) and exceeded the supervised classifier by 0.36-0.42 on event subtypes absent from its labels, in all four rounds, and it outperformed the classifier whenever fewer than about four labelled events per class were available. Jev also decided 20-40 times faster than frontier LLMs. Accepting only benign Jev verdicts confirmed by the rule tree spared an LLM reviewer 35-38% of windows on fresh sealed sets without loss of macro-F1. Transferred unchanged to two further networks, this gated cascade stayed within the non-inferiority margin of its reviewer on all four sets. A fast, training-free screen can therefore take over about a third of the review load in SCADA anomaly triage while preserving the accuracy of deliberate review.

Positive and negative space is a fundamental principle in visual composition, supporting visually coherent forms and layered semantic relationships. Generating such compositions is challenging because it requires coordinated control over two semantic concepts that share a common boundary. Although recent text-to-image models and multimodal large language models (MLLMs) have achieved strong performance in image generation and visual understanding, positive-negative space generation remains difficult, particularly under direct single-pass prompting. In this work, we present the \textbf{F}orm \textbf{a}nd \textbf{V}oid \textbf{A}gent (\textbf{FaV-A}), a multimodal agent designed for staged positive-negative space generation. FaV-A follows a progressive workflow: it first generates a base object, then analyzes its shape and spatial structure to identify candidate negative-space semantics, and finally produces compositional instructions for the final image generation stage. Experimental results and ablation analyses suggest that FaV-A provides a more effective framework than direct zero-shot MLLM baselines for producing visually coherent and semantically aligned positive-negative space compositions.

Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line of work has exploited these strong 3D priors for training-free stylization, transferring visual attributes from a reference image onto a generated 3D asset. However, existing methods enforce an all-or-nothing paradigm: color and texture are transferred jointly, with no mechanism to control them independently -- a limitation we formalize as Disentangled 3D Stylization(Disen3D). To address this, we propose DiDE, the first training-free framework for Disen3D. Key to our approach is the observation that the structured latent space of image-to-3D models is overcomplete with respect to texture: texture information occupies only a small subset of the style-significant channels, leaving a free subspace available for independent color encoding. DiDE exploits this via a channel partition mechanism that processes a content image, a texture reference, and a color reference through dedicated branches and composes both style signals interference-free at every self-attention layer, preserving content geometry throughout. Experiments on Disen3D-Bench, our newly collected multi-reference benchmark, show that DiDE consistently outperforms 2D and 3D stylization baselines in color fidelity, texture transfer, and content preservation.

Some properties of languages, e.g., subject-object-verb (SOV) word order, are more prevalent than others among the thousands of attested natural languages (NLs). Such typological commonality is often attributed to learning biases. Computational simulations, recently with language models (LMs), have facilitated the exploration of this theory. In this paper, we extend existing analyses of the relationship between LMs' learning biases and typological commonality on both data and model sides, focusing on: (i) cross-serial dependencies, the upper limit of attested syntactic complexity, and (ii) stack-based LMs (SLMs), potentially facilitating learning of hierarchical patterns. We first evaluate generalization of SLMs on cross-serial dependencies across diverse artificial languages and confirm that they struggle with such constructions. However, SLMs with limited working memory generalize better suggesting a possible basis for such inductive bias and thus the typological commonality of some word order configurations.

Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasoning and code generation. In practical systems, however, policy updates and differences between rollout and training engines can make sampled responses off-policy. Sequence-level masking addresses this mismatch by deciding whether an entire response should contribute to optimization. A common masking rule uses the length-normalized geometric mean of sampled token probability ratios. Its signed log-ratios can cancel across positions, concealing substantial bidirectional policy drift. We propose \emph{Cancellation-Aware Response Masking} (CARM), a sequence-level mask that takes the absolute value of each token log-ratio before averaging, preventing opposing probability changes from canceling. We prove that accepted responses satisfy a joint bound on the fraction of sampled-token ratios outside a prescribed band and their mean log-distance beyond its boundaries. Experiments on mathematical reasoning and code generation show that CARM improves mean@16 averaged over AIME 2024/2025/2026 and BeyondAIME by up to $3.13$ percentage points over geometric-mean masking, and increases average pass@1 across four code benchmarks by $2.88$ points over the strongest evaluated baseline. These findings support CARM as a theoretically grounded and effective method for response-level off-policy control in LLM reinforcement learning.

Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively immediate feedback and reset failures. Long-running physical control operates in a different regime: actions alter future states, errors compound across decisions, and an agent must improve from experience without being allowed to rewrite the physical rules that make execution safe. We study this regime through irrigation, where daily decisions interact with soil-water dynamics over entire growing seasons. We present Mimir, a physics-grounded LLM agent organized around two repair timescales. At the fast timescale, a structured physical interface and deterministic simulator turn an LLM output into a proposal that we numerically check, revise, and subject to bounded deterministic action selection before execution. At the slow timescale, recurrent failure patterns are consolidated into persistent contextual principles that condition future proposals, while the physical model, evaluator, and execution constraints remain immutable. Under a common retrospective evaluator across multiple sites, crops, and years, Mimir attains the lowest reported aggregate control cost among the evaluated references and uses about 51% less irrigation than the historical schedule replay. The ablation study show higher control cost when forward simulation, verified revision, or persistent context is removed; model-scale and model-family studies show no monotonic gain from increasing LLM size. The resulting lesson show that persistent physical agents can combine semantic reasoning with bounded, evidence-driven self-improvement while reserving physical truth and actuator authority for explicit numerical mechanisms.

AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared state, not merely of model intelligence. Our Observation-Aliasing Impossibility Theorem gives the exact boundary. A policy can guarantee a valid action exactly when all worlds producing the same observation share an admissible action. If k indistinguishable worlds require pairwise-disjoint actions, the best randomized worst-case success is 1/k; more reasoning, roles, messages, or samples cannot recover the missing distinction. A stronger model can reason better within its context, but it cannot see beyond it. We then give local-to-global runtime semantics X = (H, C, G, F; D): topology H records overlapping scopes; category C governs state-changing actions; groupoid G retains reversible translations; sheaf F tests whether local views glue into one world; and minimal history D keeps only distinctions that alter legal futures. Models propose; the harness owns shared state and governs commit. Nine studies test both the failure and its boundary. On a controlled revision benchmark, the same frontier model scores 40/40 when the deciding event is visible; when it is hidden, tested arms score 12--17/40, consistent with chance (1/3); restoring one authoritative fact returns 40/40. On TeamBench, ordinary teams exceed a shared budget in 5/5 runs, a visible live count leaves 4/5 violations, and commit enforcement leaves 0/5. In tau2-bench Telecom, current-state checks score 0.07 after silent reverts, while the harness scores 1.00. Where a conventional solver already owns the complete relevant state, it ties the harness as predicted. The counterintuitive conclusion is that local intelligence cannot substitute for missing global state.

While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making immersive authoring a repetitive and physically fatiguing process. We present SPHERE, an adaptive VR generation framework that transforms isolated synthesis into continuous human-AI co-creation. SPHERE extracts persistent spatial preferences from natural multimodal interactions (speech and controller edits). To ensure geometric resilience against spatial distortions, it abstracts these raw edits into hierarchical constraints modeling both local functional and global topological contexts. Furthermore, a human-in-the-loop reinforcement learning mechanism dynamically updates retrieval policies based on the user's final edited scenes. A mixed-design user study ($N=42$) and an offline ablation demonstrate that SPHERE significantly reduces corrective edits and physical demand, preventing bias toward shallow object-level traits to yield geometrically resilient, profile-aligned layouts. Ultimately, SPHERE demonstrates how capturing demonstrated spatial logic enables controlled spatial adaptation, establishing a reliable, governed human-AI collaboration framework for immersive authoring. Project page and source code will be available at: https://github.com/hyeonmin11/SPHERE

Automated ideation systems are often evaluated on the novelty of the ideas they produce, and that judgment is increasingly delegated to large language models. Such judges are typically built ad hoc and validated, if at all, on human-authored papers rather than on the generated ideas they are meant to score. So, how do novelty judges perform? Not well. We present a systematic controlled study of novelty evaluation design choices. We first build an evaluation set automatically, mining OpenReview for passages where reviewers explicitly affirm or dispute a paper's originality and keeping only submissions with unanimous agreement at the extremes of their research area; we pair these with ideas from a vanilla LLM generator. Across six judges, we find that small prompt design choices have large consequences; e.g., simply telling the judge that reviewers found one idea novel and the other not can change its verdict on more than half of the identical idea pairs it is shown, shifting pairwise accuracy by over 50 points and occasionally pushing it below chance. The same change helps one judge and hurts another. Retrieval and larger reasoning budgets help little, and two purpose-built novelty evaluators are outperformed by our cheapest prompted baseline. These results raise questions about reported novelty gains of automated ideation systems, and call for robust novelty evaluation methods.

Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by data scale, training diversity, and reasoning capacity. Instead of naively extending these models into 3D, we take a different approach: we enable powerful 2D VLMs to operate reliably in 3D by introducing 3D grounding and iterative feedback loops with two novel concepts: Canonical Coordinate Framing (CCF) and Task-Adaptive Feedback (TAF). CCF serves as a unified visual representation that anchors both inputs and outputs to a shared Euclidean coordinate system, solving common challenges in 3D grounding such as axis ambiguity, inconsistent metric scale, and floating references. Complementary to this structured framing of the 3D inputs, TAF closes the reasoning loop with task-adaptive dynamic feedback that enables 2D VLMs to perform varied open-vocabulary tasks within their native visual context. Building on this foundation, we introduce 3D-Prog, a 3D understanding, reasoning, and generation framework that jointly employs the capabilities of CCF and TAF together with powerful VLMs. Without requiring any retraining, 3D-Prog performs open-vocabulary 3D understanding, manipulation, and generation across both object-level and scene-level tasks. Our experiments show that the joint use of CCF and TAF transforms 2D VLMs into geometry-aware 3D programmers, achieving consistent, interpretable, and high-quality results across diverse 3D tasks.

Recent advances in LLM reasoning models---driven primarily by the paradigm of post-training via reinforcement learning with verifiable reward (RLVR)---have enabled them to accomplish impressively complex tasks. However, in parallel with their rising capabilities, LLMs have increasingly displayed signs of language drift in their chains of thought (CoTs): unusual, non-standard, and seemingly nonsensical language use. Although it is well-documented---and can potentially impair CoT monitorability---the causes of language drift are thus far poorly understood. In this paper, we identify the conditions under which language drift occurs: we prove theoretically that RLVR optimization pressure permits unbounded language drift, while supervised fine-tuning does not. We then show empirically that language drift specifically arises during RLVR on novel reasoning tasks---i.e. when the target behavior cannot be drawn out of the base model. Finally, we prove that it is not possible to constrain language drift without constraining expected reward, suggesting that CoT monitorability cannot be improved without harming performance during RLVR post-training at the frontier.

Equivariant machine learning interatomic potentials (MLIPs) have revolutionized atomistic modeling, but accurate treatment of complex materials and molecular systems demands expensive models. This limits simulation length- and time-scales, with tensor products a key computational bottleneck. The recent emergence of foundation-scale MLIPs further exacerbates this challenge. We present Branch Interatomic Potential (BranchIP), a single-model framework for learned adaptive tensor product computation, trained with a novel distillation loss. In our experiments on two systems of physical interest, a heterogeneous catalysis system and a proton-conducting solid acid electrolyte, BranchIP accelerates MLIPs across model sizes by up to $2.4\times$ while reducing memory usage by up to $2.6\times$. This is achieved while maintaining physical fidelity. Furthermore, the learned adaptive computation provides model interpretability by revealing which interactions demand deeper computation and showing how computational depth relates to chemical complexity and dynamics.

Reinforcement learning (RL) is a powerful paradigm for training agents, yet its success rests on domain expertise of human engineers who design informative reward signals for every new task. Unsupervised RL aims to reduce this engineering with intrinsic motivation (IM): reward signals that emerge from the agent environment interaction itself. Existing IM objectives, however, involve the selection of information variables, which re-introduces domain expertise the field has sought to eliminate. We introduce Forward CIP (F-CIP), an RL-native formulation of the Controllable Information Production (CIP) objective, which is defined by the system's dynamics alone and requires no such selection. We prove that F-CIP is compatible with RL and demonstrate its effectiveness with existing algorithms. Training agents with F-CIP results in unsupervised discovery of primitive behaviors such as balancing and maintaining controllability, which are essential for more complex robot behaviors. Paired with a simple forward-velocity reward, our method produces coordinated gaits such as hopping and running which otherwise require reward engineering to learn.

Invisible watermarking has become a central tool for tracing AI-generated images, but its robustness against adaptive removal attacks remains an open security question. We introduce Latent Frequency Masking, an attack that erases watermark evidence by replacing selected Fourier coefficients in the latent representation of a watermarked image. The replacement can be sampled from Gaussian noise for efficiency or derived from diffusion regeneration for improved image preservation. We provide a theoretical distortion bound relating the change between the reconstructed adversarial image and the masked latent-frequency perturbation. We evaluate the proposed attack against six diffusion watermarking methods on images generated from DiffusionDB and MS-COCO prompts. Latent Frequency Masking removes or substantially weakens several watermarks while preserving perceptual quality and achieving favorable runtime compared with existing attacks. These results identify latent-frequency manipulation as a practical attack surface and highlight the need to include such attacks in robustness evaluations of generative image watermarking.

A multi-LLM \emph{council} lets several large language models (LLMs) deliberate on a question and return an answer together with a confidence estimate. As these systems become increasingly used for reasoning, that confidence should represent a calibrated \emph{probability of being correct}, and the decision should remain robust when some agents are persistently unreliable. Existing \emph{council aggregation} methods fail on both fronts: their confidence estimates measure decisiveness rather than correctness, and they cannot identify or discount persistently unreliable agents. We introduce Bayesian Dialectical Argumentation (BDA), which treats the council's \emph{typed} moves---who proposed, challenged, or conceded which answer---as observations of a classical annotator model with \emph{per-agent} reliabilities. This formulation recasts multi-agent deliberation as a reliability estimation problem, using the deliberation trace to infer agent reliability under persistent adversarial behavior. By weighting evidence according to inferred agent reliability, BDA yields calibrated posterior probabilities over candidate answers while allowing persistently unreliable agents to be inverted rather than merely outvoted. Across binary and multi-class benchmarks, BDA achieves the best calibration among zero-cost council aggregation methods, requiring no additional LLM calls, and improves robustness under persistent adversarial coalitions while remaining competitive in clean settings.

Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arrives as a new document rather than an edit, answering a question requires knowing which version held at a given time. However, most memory systems compress the record at write time. By distilling each document into facts, notes or graph edges, these methods fix what can be answered before any question is asked. To address this, we propose Mem++, a non-destructive memory framework shifting from write-time distillation to read-time selection. Mem++ stores every document whole with its date and author, and it calls no generative model at write time. At read time, it retrieves only documents dated up to the time a question asks about and fuses lexical and semantic rankings. Unlike systems that overwrite older versions, Mem++ keeps them and leaves the choice to the answering model. Evaluations on the organizational benchmark OrgMemBench demonstrate that Mem++ surpasses the strongest memory system baseline by 8.0 to 13.1 points across two answering models. With gpt-4.1-mini, it also achieves the best overall score, 2.6 points above RAG. In addition, Mem++ achieves the best average LLM-judge score on LoCoMo and ranks second on LongMemEval-S, behind only its entity-graph variant. Code for benchmark evaluation is available at https://github.com/AIDAChip-Inc/mem-plus-plus.

Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows the context, self-correction diverges, tool demonstrations loop, and tasks are silently abandoned. We present evidence, from a controlled single-machine comparison and one third-party benchmark, that a substantial share of these failures is attributable to the harness rather than the model. We introduce Mingbird, a local-first agent harness for Windows and Ollama whose ten mechanisms compensate point-by-point for small-model failure forms, three of them representative: a byte-level net-zero prefill budget, a finish gate that re-reads the task before accepting completion, and signature-level loop detection. On LRAB, a controlled comparison holding machine, models, budgets, and scoring fixed (4 harnesses $\times$ 4 open models (2B-35B) $\times$ 18 real tasks, deterministic artifact scoring), Mingbird reaches 0.886 overall against 0.631 (goose), 0.479 (opencode), and 0.405 (agent-mini), with all 288 cells published; on $τ^2$-bench (278 tasks, three arms, one protocol) it totals 0.856 against 0.791 and 0.737; and a frontier-model probe on the same 18 tasks spans 0.997 to 0.478 across harnesses, with well-formed scaffolds staying within 0.072 of each other. A leave-one-mechanism-out ablation is reported as directional only: same-night replications of the same arm move its mean by up to 0.069, the size of every nominal single-trial delta, and the one batch-matched comparison (full mechanism stack versus text re-read alone) gives the executable completion guards a paired +0.10 across three replications. The evidence carries stated limits: a self-built benchmark, a single machine, and single-trial scoring.

Adverse conditions such as rain, snow, fog, and dust remain challenging for camera-based perception in autonomous driving. We study multi-class weather recognition from street-view images under domain shift, where most available training data come from non-street-view sources that differ markedly from real driving scenes. We propose Weather-Aware Adversarial Discriminative Domain Adaptation (WA-ADDA), which conditions the domain discriminator on predicted weather to promote features that are both domain-invariant and weather-sensitive. We also assemble a multi-dataset benchmark by unifying diverse non-street-view weather collections as sources and real street-view images as targets, and define a standardized evaluation protocol with macro accuracy as the primary metric. Across backbones (ResNet-50, EfficientNet, VGG, DenseNet), WA-ADDA consistently improves street-view performance and yields strong per-class recalls in challenging conditions while preserving clear-weather accuracy. These findings highlight the feasibility of domain-adapted weather recognition and the value of our benchmark for advancing robust, on-board perception.

Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities account for success or failure. Each task requires recovering spatial evidence, representing geometry, and reasoning over it. We disentangle these capabilities by comparing predicted and ground-truth spatial context under a shared schema and coordinate contract. This comparison reveals four recurring sources of error: inaccurate perception, missing information in the spatial context, selection of the wrong measurement, and errors in reference frames or in tracking position and orientation. Guided by this diagnosis, we develop CROSS, a training-free library of typed geometric operators and spatial skills that function over available evidence to support reliable video spatial reasoning. The resulting library supplies verified context to non-coding VLMs or callable skills to a SpatialClaw agent. We evaluate \methodname{} on five benchmarks. \methodname{} raises the average score from 55.9\% to 60.2\% on ReVSI and improves the SpatialClaw result from 62.8\% to 66.3\% on DSI-Bench. These gains demonstrate that explicit handling of spatial conventions can repair systematic reasoning failures without additional training.

Byte-level byte-pair encoding (BBPE) tokenizers are attractive for multilingual large language models (LLMs) because they cover all Unicode text. In UTF-8-based BBPE, however, many scripts start from a higher fallback cost than English: when no learned merges can be applied, a multibyte character requires multiple byte-derived symbols. We call this worst-case pre-merge cost the encoding floor. A higher floor can increase token counts and per-request cost and shrink usable context. Changing the text encoding can reduce this gap, but a single global encoding can make already-efficient English spans more expensive in mixed-script text. We propose Universal Byte-Level Encoding (UBE), a dual-alphabet tokenizer that keeps 1-2-byte UTF-8 characters on the UTF-8 path while routing 3-4-byte UTF-8 characters through UTF-16. This lowers the encoding floor for 3-byte Basic Multilingual Plane (BMP) characters in scripts with high token premiums (token counts relative to English) without raising it for already-efficient spans in mixed-script text. UBE changes only the byte representation presented to byte-pair encoding (BPE); the merge rule remains standard, and exact decoding is preserved. UBE also composes with alternative boundary policies and morphology-based representations. In a Unicode 17 audit, UBE exactly round-trips all Unicode scalar values and all inputs in the official normalization, grapheme-break, and emoji test suites. Across intrinsic evaluations, UBE lowers dispersion in English-normalized token-count ratios, reducing cross-lingual token-budget disparity. In multilingual language model (LM) experiments, UBE matches BBPE's LM quality. In the main multilingual settings, UBE reduces token counts most for high-premium scripts and slightly lowers English token counts, yielding more usable context under fixed token budgets and faster prompt processing in content-matched benchmarks.

Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-image diffusion model while preserving its ability to generate other content. Existing activation steering methods build an erasure direction mainly from the target concept and adjust model activations along it at inference time. However, target and retained concepts often overlap in the model's representation space, so this direction also contains shared components that retained concepts rely on. Steering directly along this direction can therefore suppress retained concepts and harm the generation of non-target content. To address this issue, we propose Retain-aware Activation Steering (RASteer), a training-free method. RASteer first builds a retain subspace from the concepts to preserve. Retain-Orthogonal Steering (ROS) then removes components aligned with this subspace from the erasure direction, making steering more specific to the target. Since fully removing the shared components can weaken erasure, we further introduce Overlap-Adaptive Calibration (OAC). At each layer and denoising step, OAC uses the overlap between the erasure direction and the retain subspace to control how much of each shared component is removed, balancing target erasure and concept preservation. Experiments on unsafe-content, instance, and artistic-style erasure across multiple backbones and benchmarks show that RASteer matches or outperforms the activation steering and weight editing baselines we evaluate, achieving a better balance between erasure and preservation.

Path finding and multi-robot motion planning require trajectories that are smooth, goal-directed, and collision-free in environments with complex geometric constraints. Recent diffusion-based planners have shown that trajectory generation can be cast as iterative denoising which has opened the doors to learning-based approaches that can handle multi-modal trajectory distributions and refine entire trajectories. However, a key limitation is that diffusion planners require training on large collections of feasible trajectories, rendering them map-specific, and difficult to deploy when high-quality demonstrations are unavailable. This paper introduces a training-free diffusion-based motion planner that replaces learned global trajectory scores with analytical local scores derived from obstacle, smoothness, velocity, and inter-agent feasibility terms. The proposed idea relies on a key observation: the score of a trajectory can be reconstructed by considering only local interactions between neighboring waypoints and nearby constraints. This structure exploitation yields a decomposed denoising procedure that retains the optimization structure of classical trajectory methods while inheriting the iterative refinement behavior of diffusion models. Experiments on a large collection of complex environments and large multi-agent planning tasks show that the proposed analytical score produces smooth and feasible trajectories within limited computational costs, for example in generating feasible paths for 300+ agents in environments containing 100+ obstacles in under 6 seconds on a GPU, outperforming strong learning-based and optimization baselines, while avoiding the data requirements of learned diffusion planners.

Outcome-based reinforcement learning can train language models to forecast real-world events, but prior forecasting work either freezes research context before training or deploys agentic research only at test time, so the skill of gathering evidence is never shaped by the reward. We introduce an agentic forecasting environment, dataset, and harness built from 2,100+ resolved Polymarket questions; the agent acquires its own context at rollout time (web search, page reading, and financial time series, all restricted by layered leak filtering to information published before each question's cutoff), and we train Qwen3.5-35B-A3B (3B active parameters) on it with single-epoch GRPO under a Brier-score reward. Training changes how the agent interacts with information: calibration improves 30-40%, and search attempts fall from 3.8 to 2.25 per rollout as evidence discipline is learned. Evaluated in an identical harness against four frontier models, the trained policy also finishes ahead of every frontier model tested at evidence-based forecasting, including Claude Opus 4.5 (soft-Brier 0.254 vs. 0.256, n=265), at about 5% of the inference cost, and its margin is widest on the hardest questions, the ones the crowd itself had not decided. We release the environment, dataset, and per-rollout records as a reusable harness for temporal forecasting agents.

Robotic simulation and virtual reality increasingly require object assets that capture not only visual geometry but also the physical cues underlying tactile and thermal interaction. Existing 3D datasets and reconstruction methods primarily represent object-scale geometry and visual appearance, overlooking microscale surface structure for high-fidelity haptic rendering and transient temperature dynamics for temperature-aware interaction. We present TouchTherm, a framework for constructing simulation-ready visuo-tactile-thermal object assets from real-world objects. For visual and tactile reconstruction, we combine structured-light scanning with multiview normal maps obtained from photometric stereo. The normal maps are registered to the scanned geometry and transformed into tangent space to recover local micro-height fields for optical tactile rendering, while the coarse mesh handles collision detection. For thermal reconstruction, we capture synchronized multiview infrared videos of natural cooling following controlled heating and reconstruct a physics-regularized dynamic thermal field. Experiments on 20 objects show that the reconstructed micro-height fields preserve dominant surface structures and recover higher-frequency details beyond the coarse geometry, while the thermal fields achieve held-out surface-temperature MAEs of 0.465 degrees C and 0.592 degrees C at 30 s and 45 s, respectively. The resulting tactile assets support synthetic-to-real object recognition from tactile observations, while a glove-based VR system demonstrates spatially and temporally varying thermal feedback. These results highlight the potential of TouchTherm for multimodal sensory simulation and temperature-aware virtual interaction.

Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VFMs) yields semantically rich representations that support diverse future scene understanding tasks. However, existing approaches rely on two-stage pipelines, where VFM features are first compressed using fixed dimensionality reduction (e.g., PCA) or independently trained autoencoders, and a separate predictor is trained on top of the resulting frozen latent space. This decoupling between representation learning and temporal prediction, as well as approaches that apply predictors directly on raw VFM features, provides no guarantee that the latent space is structured for predictable dynamics. In this work, we propose Latent-Foresight, an end-to-end framework that jointly learns a latent tokenizer and a flow-based generative dynamics model, explicitly shaping the representation to support temporal predictability. To enable stable joint optimization, we introduce several key design choices that prevent latent collapse and align reconstruction with generative objectives. Extensive experiments show that our approach learns more temporally coherent latent representations and consistently outperforms two-stage baselines across multiple future scene understanding tasks and prediction horizons, while eliminating separate training stages, including during high-resolution adaptation. We provide the implementation code and model weights at https://github.com/Sta8is/Latent-Foresight

Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observations incur substantial token overhead. We introduce PyRUA-Lean, an interactive code-execution framework that couples feedback-driven primitive composition with selective observation: the agent composes classical robot primitives and learned vision-language-action (VLA) policies into Python cells that perform conditional checks and local retries, returning only explicitly requested images and state feedback for replanning. Across 700 simulated task instances from LIBERO-PRO, RoboTwin 2.0, and RoboCasa365, we compare PyRUA-Lean with a tool-calling baseline using the same GPT-6 Astra planner and underlying robot primitives. Under equal LLM-call budgets, PyRUA-Lean increases overall success from 63.1% to 71.7%. On instances solved by both agents, it uses 49% fewer LLM calls and 65% fewer input tokens.

Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and justify a patient's problem representation and a defensible plan. This structured narrative review maps three literatures: medical education assessment instruments, clinical LLM benchmarks published from 2023 onwards, and general-domain methods for evaluating long-form generation. We examine six dimensions: problem representation, temporal synthesis, differential and management reasoning, counterfactual reasoning, calibrated uncertainty, and reasoning faithfulness. Preprints are included and flagged. No single instrument covers all six dimensions. Problem representation and differential or management reasoning are reasonably covered, although reliability varies by instrument and setting. TIMER-Eval targets temporal synthesis, and ER-Reason assesses sequential diagnostic belief updating. Dedicated uncertainty and counterfactual evaluations are emerging, but their applicability to longitudinal free-text reasoning remains limited. Factual completeness is well theorised in general-domain evaluation, with early clinical evidence of important omissions. Faithfulness remains the weakest dimension, with one identified clinical causal-ablation study on multiple-choice questions. Existing tools should be combined through binary rubric items, separate completeness and correctness scores, case-specific importance weighting with non-compensable safety caps, temporal order-consistency checks, and chance-corrected reliability reporting. Further design work is needed for calibrated uncertainty, counterfactual reasoning and faithfulness over longitudinal free-text records. This review provides a design rationale, not a validated instrument.

Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and their susceptibility to hallucinating information. Retrieval Augmented Generation (RAG) addresses these issues by incorporating external retrieval into the generation process, grounding model outputs in verifiable and up to date sources. While prior surveys primarily focus on core RAG architectures and standard pipelines, recent research explores broader challenges and capabilities that extend beyond these foundational designs. This survey provides a consolidated and structured examination of contemporary RAG developments, organizing the field into a four axis taxonomy: improving retrieval efficiency, strengthening robustness and security, supporting user driven and interactive workflows, and enabling multi step or complex reasoning. We formalize key components of the RAG framework and review methods spanning dense and sparse retrieval, fusion strategies, embedding optimizations, and reinforcement learning based retrieval policies, highlighting how these advances influence practical deployment and system design. We also synthesize evaluation practices, domain specific applications, and architectural variants such as Naive, Advanced, and Modular RAG. Finally, we outline persistent challenges related to retrieval quality, reliability, domain adaptation, scalability, and explainability, and identify opportunities for building RAG systems that are more reliable, adaptable, and transparent.

Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in long-context streaming reconstruction due to error accumulation. In this paper, we revisit loop closure with streaming reconstruction foundation models to enable accurate, drift-free, kilometer-scale reconstruction. Specifically, our method detects loop candidates through global descriptor retrieval, and constructs loop-conditioned windows to estimate the relative poses between looped frames. Given the observation that our adopted streaming reconstruction backbone produces a globally consistent scale, we optimize all frame poses on the SE(3) manifold with sequential and loop closure constraints, avoiding the pose graph optimization on the Sim(3) or higher-dimensional SL(4) manifolds employed in prior works. Extensive experiments show that our method reduces drift and produces consistent geometry on kilometer-scale sequences, significantly outperforming the state of the art. Code is available at https://github.com/MoyangLi00/CLoSeR.git.

This paper introduces tellegen, an open source framework for interactive power flow (PF) and optimal power flow (OPF) studies that run in the browser. This provides intuitive and democratized access to power system analysis tools compiled to WebAssembly. A user can drag and drop a case file, click and drag to change a nodal demand or line rating, preview the impacts via sensitivity analysis, and obtain an exact re-solve on release. User case files and results stay entirely on the device: tellegen transmits zero Critical Energy/Electric Infrastructure Information (CEII). The framework comprises a core numerical engine for PF and OPF, reusable browser components, saved studies, and structured WebMCP tools for agentic interaction. We evaluate the transmission OPF solver by comparing objectives with PGLib baselines; the distribution PF solver by comparing voltages and currents with OpenDSS; and the WebAssembly execution times by comparing with PowerModels.jl. On realistic synthetic grids, WebAssembly OPF solves take only 25-43% longer than native binary solves. The implementation shows how an engineer can distribute an executable numerical study as a URL, reducing installation and hosting requirements while keeping case data local.

Latent visual reasoning equips vision--language models with continuous intermediate states that can process visual evidence without explicit textual reasoning traces or repeated image operations. However, existing methods often allow multiple latent tokens to access the same visual evidence through shared value projections, providing no mechanism for them to extract complementary visual information; simply increasing the latent budget can therefore yield redundant latent representations. We argue that effective latent reasoning should encourage different latent tokens to extract complementary visual information, and thereby act as specialized visual experts. Based on this insight, we propose MoLE, a Mixture of Latent Experts framework that controls both what visual evidence each latent visual expert observes and how it transforms that evidence. MoLE isolates latent visual experts during evidence extraction and uses dedicated latent summary experts to aggregate the complementary representations of latent visual experts. A two-stage training pipeline first forces visual evidence through this latent pathway and then restores direct visual access, requiring neither predefined expert roles nor intermediate visual targets. Across five visual reasoning benchmarks, MoLE achieves an average score of 78.6, outperforming data-matched supervised fine-tuning by 4.9 and the strongest evaluated latent visual reasoning baseline at the same latent budget by 3.6. Representation analyses show lower latent-state similarity and more diverse visual attention, while masking the latent pathway reduces average performance by 9.2. These results demonstrate that specializing latent computation is more effective than merely increasing the number of latent tokens.

Reinforcement learning with verifiable rewards (RLVR) improves vision-language benchmark scores even without visual information during training. With images at test, blind-trained models recover roughly half of the real-image gain at 3B and nearly four fifths at 7B. Prolonged real-image training can erode grounding while benchmark gains persist. Both findings expose the same gap: an image in the prompt is not an image in the learning signal. Our design rule, visual resolvability, asks that visual evidence be necessary for a correct answer and that the task remain learnable. We test it on counterfactual coordinate scenes in which the question stays fixed and the target is never named, so a correct answer requires finding the target in the image. With standard GRPO and correctness-and-format rewards, a 7B model raises its accuracy at finding the target (discovery) from 0.425 to 0.875 on held-out scenes denser than any it trained on, and it improves on question types it never trained on. Two controls locate the source of the gain. Replacing test images with gray canvases drops discovery to zero; training on gray canvases instead, at matched step 30 and in each of four seeds, yields essentially none of the gain even when the model is then tested with real images. The learned skill carries over to grounding tasks built independently of the training corpus. A caption that answers the training question, added to the same images, reward and budget, cuts the gain by nearly two thirds. Changing what reward requires changes what RL learns.

Many real-world systems exhibit higher-order interactions among groups of entities that cannot be captured by pairwise relationships alone. Graph Transformers and Graph Neural Networks increasingly rely on positional encodings to enrich graph representations, yet existing positional encodings are computed solely from the original graph and therefore cannot directly capture observed higher-order interactions. Topological Deep Learning addresses this limitation by lifting graphs to simplicial complexes, but typically requires performing message passing or attention on higher-order neural network representations. We introduce a representation learning paradigm that enriches graph representations with higher-order topology through positional encodings, enabling standard graph learning models to exploit lifted incidence structure without modifying the backbone. We derive a theoretical characterization of the expressivity of higher-order positional encodings, proving that node-level operators induced by higher-order lifts can mix graph Laplacian frequencies in ways that scalar graph spectral filters cannot. Guided by this theory, we instantiate higher-order positional encodings using Hodge Laplacians derived from clique complexes. Experiments with Graph Transformers on ZINC and controlled synthetic benchmarks demonstrate improvements in predictive performance, while a fixed-1-skeleton experiment shows that the pipeline can transmit higher-order information when cells are supplied independently of the graph. Together, our results establish higher-order positional encodings as a principled bridge between graph positional encodings and topological deep learning.

Asynchronous reinforcement learning (RL) improves the efficiency of large language model post-training but introduces stale rollouts generated by earlier policies. Theoretical understanding of how this staleness affects convergence and how to mitigate its impact remains limited. We derive a convergence bound for GRPO-style algorithms that explicitly characterizes the tradeoff between the gradient estimator's second moment and bias. For trajectory-level importance-weighted estimators, our analysis shows that once the second moment is uniformly controlled, delay enters the bound through the bias introduced by clipping or rescaling. Guided by this insight, we propose a novel group mass capping GRPO (GMC-GRPO) method, which minimizes a ratio-based bias bound within a class of weighted estimators sharing a common second-moment guarantee. We establish convergence guarantees for asynchronous GMC-GRPO and show that, compared with TIC-GRPO, it improves the threshold dependence of the fourth-order delay term from $O(ε^{-4})$ to $O(ε^{-2})$ as $ε\to0$, where $1+ε$ is the ratio threshold. Under local policy overlap, the delay-dependent term decreases as $G^{-2/5}$ after tuning the step size, where $G$ is the group size. For fixed behavior and current policies, the bias introduced by group rescaling also vanishes as $G\to\infty$, whereas the bias from trajectory-wise clipping can persist. Experiments across Qwen3 models and reasoning benchmarks demonstrate improved robustness to stale rollouts, with GMC-GRPO achieving the best performance among stable baselines under large rollout delays.

Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reasoning as selection instead of open-ended generation. SSR represents recurring high-level reasoning as pre-specified, reusable natural-language candidates. At each turn, the model selects from these reasoning candidates based on their likelihoods given the current context, without requiring an auxiliary task head. Using pre-specified reasoning traces enables parallel scoring, where teacher-forced prefilling computes token likelihoods concurrently within and across candidates using a shared context KV cache. We evaluate SSR on seven multimodal search benchmarks using 2B and 4B models. Across multiple reinforcement learning objectives and supervised fine-tuning, SSR delivers significant efficiency gains without sacrificing task performance. SSR achieves an average success rate competitive with leading search agents of the same scale, while reducing per-turn reasoning latency by over 90% and total per-question model inference latency by 28-54%. Project page: https://zfy0314.github.io/ssr-webpage/.

Dynamic resource assignment, the real-time allocation of task streams to heterogeneous processing nodes, is the backbone of modern computing infrastructure. While learning-based schedulers excel in research, industrial deployments still rely on hand-written rules that operators can read, audit, and execute within tight latency budgets. LLM-based Automatic Heuristic Design (AHD) promises to automate writing such rules. However, existing AHD frameworks were developed for combinatorial problems fully specified to the LLM, and they learn only from a scalar fitness score. In real systems, the behaviour that determines a good heuristic, such as processor speeds or power consumption, is unknown a priori: the score reveals which heuristic performs better, but not why. This missing information is recorded in the system logs that every evaluation produces. Exploiting it is non-trivial: logs are massive and noisy, the relevant signals depend on the objective, and their content and format vary across hardware and software stacks, so they can neither be fed to an LLM as is nor processed by a fixed parser. We propose TRACE, which couples an evolutionary AHD loop with an agentic knowledge-extraction workflow. A Reasoner agent analyzes the log schema in light of the objective and formulates hypotheses about the system dynamics; a Coder agent writes and executes schema-specific code to test them, producing insights or executable tools for the evolved heuristics. We evaluate TRACE on a synthetic cloud benchmark and a 5G vRAN scenario built from industrial testbed measurements and operational traffic traces. TRACE consistently outperforms state-of-the-art AHD methods in resource assignment problems and yields more auditable heuristics at under 2% overhead.

We introduce an approach for collection-grounded B-roll sequence generation. Given a user's video collection, a directive given in natural language, and a target duration, the goal is to produce a multi-shot sequence that complements the user's primary footage (A-roll) while preserving the collection's characters, settings, objects, and style. This task is challenging as one must choose the visual evidence from hours of captured footage that should guide the generation of each shot in the sequence. We address this challenge with MemComposer, a three-stage system that turns raw footage into a structured memory with visual references (characters, settings, objects, and style) and uses it to plan, retrieve, and generate grounded B-roll sequences. First, in a one-time offline stage, MemComposer constructs an entity-centric memory from raw video. Second, it uses the memory and user directive to plan a grounded sequence and retrieve conditioning frames for each shot. Third, it iteratively generates and critiques the sequence to enforce identity, setting, and sequence-level consistency. We evaluate MemComposer in a user preference study along two dimensions: prompt adherence and visual alignment to the user's collection. Against an ungrounded text-to-video planner, MemComposer wins 60.0\% of prompt-adherence and 92.8\% of visual-alignment comparisons, showing the grounding benefit of collection memory and reference retrieval. Against retrieval-only sequences assembled from captured footage, MemComposer wins 94.5\% of prompt-adherence comparisons, showing the value of generating missing shots, while retrieval-only sequences are preferred for visual alignment in 58.2\% of comparisons.

Multi-agent reinforcement learning (MARL) provides a powerful framework for learning coordinated behaviors through interactions with the environment. Developing MARL policies requires balancing expressive modeling of complex and multimodal action distributions with efficient training and execution. Generative policies, particularly diffusionbased policies, can faithfully capture complex and multimodal behaviors, but costly iterative sampling hinders their scalability in online multi-agent settings. We propose an Online MARL framework via one-step Flow model (OMAF) that combines expressive generative policies with efficient one-step action generation. OMAF employs a Transformer-based flow policy to capture complex coordination behaviors, while its approximate path score surrogate provides a principled route to synchronized flow policy optimization. To enable stable and sampleefficient learning, we further develop a joint optimization scheme coupling softmax Q-value estimation with a joint flow policy objective for coordinated policy learning. By eliminating iterative sampling, OMAF dramatically reduces training overhead without sacrificing policy expressiveness. Extensive experiments across 10 standard tasks from MPE and MAMuJoCo show that OMAF consistently achieves superior performance, with up to 3.4x higher returns and 10.5x sample efficiency improvement compared with baseline methods. These results validate the effectiveness of OMAF as an expressive and computationally efficient one-step flow policy paradigm for online MARL.

A surface photographed under even light presents nearly the same appearance from every angle; the same surface under uneven light does not. Exposure changes between views, illumination varies within a single image, and locally strong light sources leave one region bright and its neighbor in shadow. Multi-view reconstruction methods such as 3D Gaussian Splatting treat these lighting artifacts as if they were properties of the scene, entangling capture-specific illumination with the geometry and color they recover. We present EvenSplat, a framework that separates the two. EvenSplat couples an image-space illumination decomposition with an illumination field carried by the Gaussians, so that the same explanation of the lighting is shared between the two-dimensional and three-dimensional views of the scene; a camera-response network and a local exposure-compensation module absorb the global and residual differences that remain across training images. Through extensive experiments across multiple datasets and diverse forms of uneven illumination (cross-view exposure, spatial illumination variation, and high-contrast lighting) on both real-world captured and simulated benchmarks, EvenSplat generally outperforms state-of-the-art methods, particularly under high-contrast illumination.

Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a reliable and cost-effective technique of grounding the generative capabilities of Multimodal Large Language Models (MLLMs) into relevant, up-to-date, external knowledge. Despite presenting several benefits, such as reducing hallucinatory behavior, they also introduce new attack surfaces, including leakage of private information and vulnerabilities against data extraction attacks. In this paper, we introduce $\immrag$, an adaptive and automatic data extraction attack procedure operating in a black box setting against \emph{image-returning} MRAG, a configuration in which the retrieved visual artifact is itself the response. Each query blends an attacker-held shadow image with an image already recovered from the system, and relevance-weighted resampling steers subsequent queries towards regions of the embedding space that still yield novel retrievals. Unlike current extraction attacks that aim to persuade the model towards data leakage by placing a malicious query as a textual prompt, $\immrag$ embeds the malicious instructions inside a user-given input image. We evaluate $\immrag$ on three plausible and distinct real-world scenarios: medical assistant, document-focused helper and general purpose tool. The experiments involve the study of the effectiveness of the attack on multiple CLIP-family retrievers, as well as the impact of various generators. A single 2500-query run reconstructs up to 611 distinct radiology images, 566 document scans and 416 general-purpose images under local-feature correspondence, and reaches up to $5.6\times$ as many distinct datastore items as a non-adaptive baseline. Our results show the urgent need for safeguards specifically designed for multimodal data.

Urban environments are shaped by design choices with long-term implications for health, safety, and quality of life, yet evaluating proposed interventions remains costly, time-consuming, and often impractical. Existing geospatial vision methods largely focus on monitoring urban indicators from aerial and street-view imagery, rather than proposing interventions and estimating their effects on such indicators. Moving beyond recognition, we introduce the problem of discovering interventions that improve target indicators for a given aerial or street-view image. We argue that a black-box indicator model, combined with a generative editing model, can serve as an implicit digital twin for testing intervention hypotheses. We present VIDA-Geo , a multi-agent system that explores this intervention space by coordinating segmentation, diffusion-based inpainting, and indicator scoring models to produce interventions that are both perceptually realistic and aligned with real-world policies. We evaluate our system on 8 indicators across aerial and street-view imagery, measuring changes in factors such as perceived safety and greenery. Our approach outperforms existing baselines in many cases, achieving up to 2X higher perceptual quality and policy alignment scores. Finally, our model provides users with multiple candidate interventions, supporting an expert city-planner-in-the-loop workflow.

We present LiteReality-Agent, an agentic system for reconstructing real indoor environments as realistic, articulated, and simulation-ready 3D scenes from RGB-D scans. At its core, LiteReality-Agent formulates 3D reconstruction as a coding problem, in which a coding agent gathers evidence using specialised tools and iteratively edits a Python script, Room.py, which can be executed to produce a 3D digital twin of the room. With this formulation, we develop a robust observe-edit-verify harness that supports evidence gathering, measurement, verification, layout optimisation, simulation readiness, and quality control throughout the reconstruction process. LiteReality-Agent produces high-quality reconstructions suitable for simulation and downstream embodied AI tasks. Furthermore, as agent capabilities continue to improve rapidly, the system introduced by LiteReality-Agent remains a strong orchestration framework for future agents: it equips them with specialised tools, structured workflows, and robust verification mechanisms that substantially improve reconstruction quality and reliability. We demonstrate that LiteReality-Agent produces reconstructions that are more geometrically accurate, visually realistic, and simulation-compatible than those generated by recent frontier models, such as Astra and Fable. We therefore view LiteReality-Agent as a practical and important building block for robust real-to-sim systems. Both the source code and the data-capture application are publicly available. Code:https://github.com/LiteReality/LiteReality-Agent/

Natural language descriptions can provide rich semantic representations of audio-visual urban scenes, yet datasets that jointly describe both auditory and visual information remain limited. In this paper, we introduce AVSD-Scenes, a paired audio-visual scene description dataset for urban environments. The dataset contains 12,291 audio-visual scene descriptions generated from the TAU Urban Audio-Visual Scenes dataset. To construct the dataset, we first generate audio- and visual-based descriptions using Qwen2-Audio-7B and Qwen2.5-VL-7B, respectively. These modality-specific descriptions are then combined using large language models, namely Qwen3-14B, Mistral-Small-3.2-24B-Instruct-2506, and Gemma-3-27B-it, to produce multimodal descriptions that capture complementary information from both modalities. We benchmark AVSD-Scenes using semantic alignment, cross-modal retrieval, scene classification, LLM-as-a-judge evaluation, and human subjective assessment. Results show that multimodal descriptions improve semantic alignment and cross-modal retrieval performance compared with modality-specific descriptions while preserving strong scene-discriminative information. The generated descriptions achieve up to 94.5% accuracy in urban scene classification, while combining audio, visual, and description embeddings further improves accuracy to 95.4%. Furthermore, the descriptions remain highly scene-discriminative even when scene labels are removed from the prompting instructions, indicating that they capture semantic information derived from the audio-visual content rather than merely reflecting label information.

This paper proposes a local recursive least squares (RLS) estimation strategy for discrete-time adaptive fuzzy control of nonlinear systems represented in quasi-Linear Parameter Varying (qLPV)/Takagi--Sugeno (TS) form. Unknown nonlinear terms are approximated by a constant-consequent TS fuzzy model, and the consequent parameters are updated by a membership-function-weighted RLS law with a forgetting factor. The proposed estimator keeps a different covariance for each rule, considerably reducing the memory footprint of the least-squares updates. The adaptation is also simplified since each rule is only adapted when it is active. From these properties, we are capable of showing that the adaptation law ensures bounded local adaptation errors. Building upon this adaptation law, Linear Matrix Inequality (LMI) synthesis conditions are presented for matched, sector-bounded and norm-bounded unknown nonlinearities, guaranteeing ultimate uniform boundedness of the adaptive control system in closed loop. Three numerical examples are presented to illustrate the adaptive control conditions in the three cases: a planar manipulator with unknown gravity direction, a two-tank system with unknown coupling, and a Brushless DC (BLDC) motor acting as thrust for an efficiency vehicle.

Vision-language-action (VLA) models unify visual perception, language understanding, and action generation, offering new opportunities for automation in additive manufacturing (AM). However, deployment in AM remains challenging because adapting these models to unseen robot embodiments is costly, and performance can degrade under environment changes. In this work, we present a framework for deploying OpenVLA-OFT on a FAIRINO FR3 robot in a fixed AM workcell. A data pipeline converts monocular real-world demonstrations into OpenVLA-compatible TFDS/RLDS datasets to support adaptation to the FR3 embodiment. At runtime, each inference request predicts an eight-step chunk of 7-D actions. The FR3 executes each chunk open loop before capturing a new observation, providing closed-loop feedback between chunks. The system uses a cloud-edge architecture in which the FR3 client streams observations to a remote inference server through a FastAPI interface. In 42 physical A-to-B object-transfer trials, evenly split between red and blue targets, the system succeeded in 39 (92.9%). All three failures occurred during final placement, when insufficient release-height control caused the object to topple. An illumination sweep identified a low-error luminance range of 85-125 on a 0-255 scale, with the lowest mean spatial error at 95.

Human hand-object demonstrations offer a reusable source of dexterous robot manipulation data, but transferring them across embodiments requires physically feasible retargeting. Existing physics-based approaches face limitations in retargeting success, motion-specific training efficiency, or both. To address these limitations, we introduce FlashDexRetarget, an RL-based framework for high-success, efficient dexterous motion retargeting. To make the demonstrated interaction easier to learn, we combine object point-cloud observations, hand-object distance features, and future trajectory encodings with complementary rewards that supervise object motion and reference hand-object relationships. To further accelerate learning, we employ separate left- and right-hand actor critic networks and adapt the off-policy algorithm, FlashSAC to dexterous motion tracking. On a benchmark of 50 motions spanning single-object and two-object interactions, FlashDexRetarget achieves a 90% success rate, approximately 2.5x that of the evaluated sampling-based baselines, while requiring up to 100x less training compute than the evaluated RL-based baselines. Evaluations on both XHand and Sharpa Wave Hand show consistent gains, and component-wise ablations examine the contributions of our design choices. Beyond the 50-motion benchmark, experiments with 200, 500, and 1,000 motions demonstrate that our method remains stable at larger scales and produces successful retargeted motions more efficiently as the training set grows. Qualitative replay results using real-world-captured demonstrations further illustrate the applicability of our framework to recorded human manipulation. Videos and code are available at https://davian-robotics.github.io/FlashDexRetarget/

A time series world model (TSWM) predicts a controlled system's state from its observed history and planned actions and exogenous inputs. Current approaches build forecasters with actions as covariates, trained and evaluated on prediction error under the executed plan. Yet world models compare unexecuted plans, but their responses to changed plans remain untested. We ask which design choices matter and whether accurate forecasters respond to changed plans as real systems do. We address both with a formalization and benchmark. The formalization separates state, actions and exogenous inputs, distinguishes continuous, mode and event actions, and introduces mechanism consistency, a metric built on declared action-state relations with known directions, such as a vasopressor raising blood pressure: it checks whether shifting an action moves the forecast in the declared direction. The benchmark consolidates eight public datasets with real actions from engineered infrastructure and clinical care, varying prediction space, plan fusion and plan encoding across seven backbones and five seeds. First, a frozen latent prediction space lowers MAE by 9.9% over observation space and gated output fusion lowers it by 12.7% over input concatenation on average, with both improving all eight datasets; temporal plan encoding changes average MAE by at most 2.2%. Second, prediction error and mechanism consistency diverge: the lowest-error configuration is at or below chance in consistency on four of five datasets with declared mechanisms, and no design choice avoids this. Finally, directional supervision, a loss penalizing the wrong-signed part of the response to a shifted action, significantly raises consistency on penalized mechanisms with no change in MAE. Together they give TSWMs a recipe: a frozen latent space and output-side fusion for accuracy, and a training objective for mechanism consistency.

Enterprise AI agent skills evolve as tool APIs, models, and specifications change, yet final-output evaluation can miss process-level behavioral drift. We present a continuous evaluation framework combining outcome-level and process-level checks, applied to Revenue and Productivity variants of a Business Value Determination skill in an enterprise Value Aware Resiliency system. The framework independently computes per-run ground truth, materializes reusable template tests, and evaluates tool selection, arguments, execution order, and database integrity through programmatic checks and a narrowly scoped LLM judge. We evaluate 240 trials across two skills, two specification variants, two agent harnesses, and three models. Of 175 trials passing all applicable final numerical checks, 162 (92.6 percent; Wilson 95 percent CI: 87.7-95.6 percent) contained another evaluator-detected deviation. Under a broader seven-check final-state definition, 151 of 164 passing runs (92.1 percent; 95 percent CI: 86.9-95.3 percent) still violated a trajectory check. Dependency attribution reduced a mean of 6.34 failed checks per run to 2.65 roots. Specification sensitivity varied by model and harness, with exploratory bootstrap interaction intervals excluding zero for all three Revenue comparisons and one of three Productivity comparisons. Runtime-resolved templates provided reusable regression coverage across the evaluated configurations; longitudinal validation under actual API evolution remains future work.

Language model (LM) alignment broadly aims to perturb a given LM $Q$ into an aligned LM $q$ such that i) the outputs produced by $q$ and $Q$ are 'close' in probability, ii) $q$ has a higher expected reward than $Q$. Two common techniques for LM alignment are: KL-constrained RL, which requires knowledge of the LM distribution and is computationally expensive, and the best-of-$n$ algorithm, which requires only sampling from the LM. The work of Yang et al. established asymptotic closeness between the distributions produced by the two alignment methods for an $m$--length i.i.d. token sequence output by the LM, in the limit as $m$ increases to infinity. However, the i.i.d. assumption is not representative of practical LMs, whose output sequences often have memory. In this paper, we extend the asymptotic closeness result to the case when the $m$--length token sequence outputted by the LM is Markovian. Further, for finite-length output sequences -- particularly, when $m=1$ -- we provide a complete characterization of LM distributions and reward functions for which the KL-divergence between the distributions produced by the two alignment methods is zero -- a question first posed in Yang et al.

Modern computational methods can now propose candidate molecules, materials, and other scientific designs at an unprecedented scale, creating a validation congestion where candidates are abundant, but experimental capacity to physically evaluate them remains scarce. Discovering novel scientific designs has therefore become increasingly dependent on curation: selecting a small set of promising designs for slow and costly experiments. Existing curation methods typically rely on data-driven regression models that predict absolute scores, but training these models requires substantial experimental data to begin with. Yet, useful curation signals do not have to take the form of absolute measurements, as scientific design discovery is often comparative in nature. Here, we propose that curation can instead be primarily driven by expert pairwise rankings, which are substantially easier to gather. The expertise can come from computational tools or human input of multiple levels of fidelity, ranging from empirical rules of thumb to agentic workflows and experienced scientists. We introduce PRISMS, a framework that uses pairwise rankings from one or more experts, potentially spanning multiple levels of expertise, to identify the most promising candidates without relying on data-hungry regressors. When experts differ in fidelity and cost, PRISMS escalates pairwise queries from lower- to higher-fidelity rankers based on a Fisher-information criterion. In iterative screening that selects designs from fixed drug discovery libraries, PRISMS achieves 50% top-10 discovery recall in ~42% fewer rounds than regression-only active learning, and in ~15% fewer rounds than the ranking-based method with no selective escalation. In optimization that generates new designs without restriction to a predefined library, PRISMS achieves ~18.8% higher hypervolume than the Bayesian optimization baseline.

Collaborative embodied artificial intelligence (CEAI) enables multiple physical agents to perceive, reason, and act cooperatively in dynamic environments. Effective communication is essential for CEAI, yet CEAI agents must exchange not only large multimodal observations but also task-relevant insights, intents, and interactive information over long horizons. This article investigates token communication (TokCom) as a native intelligence interface for CEAI, in which tokens serve jointly as compact semantic carriers for communication and fundamental inference units for generative foundation models (GFMs). We first discuss how TokCom supports insight sharing, intent alignment, and interactive control among embodied agents. We then propose a TokCom-assisted CEAI framework driven by a task-adaptive communication protocol. Comprising a compact codebook, syntax rules, and contextual examples, this protocol guides GFM-based transceivers to distill messages into compact tokens and reconstruct them after wireless transmission. A case study on collaborative object transport demonstrates that the proposed TokCom framework substantially reduces the source payload bit consumption while preserving task efficiency and showing robustness under noisy channels. Finally, we outline future research directions.

We consider estimating the conditional distribution of a multivariate outcome given covariates when its coordinates may be continuous, binary, categorical, ordinal or rankings, and are conditionally dependent on one another. Different statistical methods have been developed for each outcome type, and most of them target a summary of the conditional distribution, such as the mean of each coordinate, rather than the joint distribution of the outcome vector. We develop generalized engression models, a unified nonparametric distributional regression framework for outcomes of any type. The proposed method builds upon engression, a scoring-rule-based deep generative model, and introduces a data-type-specific link function and a stochastic perturbation that smooths the loss, enabling gradient-based training even with discontinuous links. We establish universal representation results for continuous, discrete and mixed outcomes. In simulations and in two applications, 242 species in a community ecology benchmark and a 17-dimensional mixed-type health outcome, the method matches type-specific models on marginal scores, improves on them on the joint distribution, and matches or exceeds purpose-built state-of-the-art joint species distribution models. Software is available in Python.

Benchmark gains are often mechanism-ambiguous: reproducing an improvement does not by itself identify why it occurs. We study finite-library mechanism discrimination, where posterior-weighted candidate mechanisms, executable probes, and a limited experimental budget define a sequential experiment-selection problem. MECHVAR selects the next probe by maximizing the posterior-weighted variance of its predicted responses. Under a shared-Gaussian predictive model, this score is exactly proportional to the classical Box--Hill posterior-weighted pairwise-KL criterion, yet it admits O(KE) vectorized rescoring and a transparent additive audit over mechanism pairs. A local expansion further links the score to expected information gain (EIG) when predicted response separations are small. In a 25-block stress audit, MECHVAR outperforms confirmation-first in several moderate misspecification regimes, while its primary comparisons with EIG remain statistically unresolved. In a held-out Digits loop, normalized mechanism-identification AUC is 0.8975 for MECHVAR, 0.7825 for a score-greedy policy, and 0.9092 for EIG. At K = 100, E = 200, median single-thread full-library scoring is 10.36 microseconds for MECHVAR versus 57.69 ms for six-node quadrature EIG in the recorded environment. MECHVAR therefore provides a lightweight, auditable acquisition rule for finite-library experiment selection when a shared predictive scale is a defensible approximation.

Although diffusion models produce high-quality images, they also reproduce and amplify demographic imbalances in their training data. Debiasing their generation process post-training w.r.t. some sensitive attribute usually relies on classifier guidance or explicit text extra-conditioning, but this reduces methods' applicability and output diversity. Conversely, methods promoting diversity alone do not ensure fair attribute representation. In this paper, we propose a method tackling fairness and diversity jointly that is generally applicable to any diffusion model and any sensitive attribute. To this end, an adapter connects the frozen diffusion model to a pretrained vision-language embedding space, enabling fairness and diversity guidance without sensitive-attribute annotations. For fairness, pairs of text prompts define attribute directions which guide batch composition towards specific proportions. For diversity, we introduce a score measuring disagreement between the semantic estimates derived from this representation. The formulation supports unconditional and text-conditional diffusion models, while requiring no prior knowledge or data of sensitive attribute. Experiments confirm that our method improves quality and diversity scores at comparable fairness levels.

Time series captioning is a fundamental step in time series understanding and can also serve as the bridge between signal and natural language. Supervised fine-tuning (SFT) relies on a larger model's captions and cannot exceed their quality. Reinforcement learning (RL) can, but its rewards were designed for other modalities and other tasks, and they transfer poorly to open-ended generation in the time series domain. We address this by proposing LineupRL, a reinforcement learning with verifiable rewards (RLVR) pipeline whose reward is caption-to-series identification. The reward model is a frozen large language model (LLM) verifier that reads the generated caption and the candidate time series as raw values, never the chart, and must pick the described time series from multiple distractors. Matching is a far lighter demand on the verifier than writing questions or judging a caption, so an off-the-shelf LLM can supply the reward. Across two captioning benchmarks, and on forecasting and reconstruction where the predictor sees only the caption, LineupRL outperforms SFT and RL baselines on every metric. The 3B vision language model (VLM) trained by LineupRL also outperforms, at 1/24 of the parameters, the 72B VLM whose captions the SFT baseline is distilled from. Our case study shows that LineupRL resists reward hacking, and that the captioner it trains both traces the trend and names the values at key points.

Vision-Language-Action (VLA) models rely strongly on language for describing task information, despite having multimodal inputs. We hypothesize that other modalities in the state space may present opportunities for supplemental task conditioning, which may be particularly relevant in cluttered or otherwise ambiguous scenes. We introduce two tuned models to test this hypothesis: (1) an electrophysiology-conditioned VLA (EC-VLA) that incorporates 8-channel electromyography envelopes as continuous conditioning input concatenated to the proprioceptive vector, and (2) a visually-annotated VLA (VA-VLA) that incorporates visual segmentation annotations to the image inputs. On a cube-selection task evaluated across three participants, EC-VLA matches a language-prompted baseline in uncluttered, in-distribution conditions and substantially outperforms it in cluttered, out-of-distribution scenes. Similarly, VA-VLA shows modest improvements over a language-prompted baseline in in-distribution scenes with substantial improvement in cluttered, out-of-distribution trials. Together, these results provide strong evidence for the potential benefit of task-conditioning beyond language.

Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a reward function. However, current approaches to reward optimizations do so at the cost of diversity and quality. In this paper, we provide better tradeoffs through careful theoretical considerations and method design. We analyze the theoretical framework and mathematically demonstrate that \emph{only-latter timestep} updates of diffusion model may be harmful for diversity contrary to the conclusions presented in a previous work. Additionally, we propose an incremental Feynman-Kac training based on strong theoretical foundations in order to achieve the best-yet alignment-diversity tradeoffs. We perform extensive experiments and compare our method against related diffusion policy optimization approaches in three different tasks and also provide strong ablations for each component, thus validating strong performance gains in both alignment and diversity.

As machine learning increasingly relies on public, untrusted data sources, data poisoning attacks, which inject malicious examples into training data to induce misclassification of a chosen target, pose a growing threat. Existing defenses either assume zero ground-truth information about which examples are poisoned, or they assume access to a large set of examples verified to be clean. Satisfying the latter assumption incurs significant cost since reliable verification can be very resource- or labor-intensive. This cost is particularly high for clean-label attacks, where poisoned examples are visually indistinguishable from clean data. Since requiring a large set of verified examples is impractical, we propose relying on a small set of verified examples including both clean and poisoned ones, i.e., each example verified either to be clean or poisoned through inspection by a forensic expert. The challenge is then to detect poisons based on a set of verified examples that is so small that most classification models would overfit. To address this challenge, we propose Similarity-based Approach for Ground-truth-driven Exclusion (SAGE), which trains a generic feature extractor on a separate dataset and then flags poisoned training examples using a non-parametric, similarity-weighted prediction based on the verified set. On standard benchmarks against seven clean-label attack methods, we demonstrate that having access to even a handful of verified poisoned examples provides a substantial advantage. We also find that the distribution of verified clean examples across classes matters more than the number of verified examples.

Self-improving GUI agents keep the trajectories they produce and return them to the agent, by fine-tuning or by retrieval into the prompt, and studies that compare the two destinations disagree. We attribute this to the unit of experience: a trajectory bundles items with different properties, so a conclusion about the bundle depends on its mix. To address this, (i) we introduce component routing, which splits the experience into locators, procedures, state facts and lessons and sends each component to the context or to the weights, compared on the same items across three backbone families, two environments and three seeds. One pool has two destinations: locators and lessons win in the weights, procedures and state facts in the context. (ii) We fit a rule in two properties measured before any training, recurrence and state-conditionality; it recovers the destination of a held-out backbone family in 24 of 24 cells, two interventions move a component toward the boundary, and routing by the rule beats every whole-trajectory baseline and, by +3.5 points on average, the better single destination of each backbone. (iii) We identify how training and producer-consumer differences change the value of the two destinations: note readout decreases after the same component is written into the weights, most for the items that recur most, context gains increase with the information gap, and weights gains decrease with the policy gap. Code and data will be released.

Reinforcement learning (RL) for reachability specifications is fundamental to sequential decision-making. Prior work establishes asymptotic convergence to optimal policies, but only through model-based methods that must explicitly estimate the transition probabilities of the underlying Markov Decision Process (MDP). We present Quasar, the first model-free algorithm with asymptotic guarantees for reachability on the fragment of MDPs free of non-terminal maximal end components (MECs), a building block to which every MDP reduces by the standard MEC quotient. Our algorithm follows the classical Q-learning approach, using temporal-difference updates to converge to an optimal policy without ever learning the transition probabilities. The resulting learner reduces the memory footprint from the O(|S|^2|A|) that model-based methods require to O(|S||A|). On the standardized Quantitative Verification Benchmark Set, our algorithm converges to the optimal policy with orders of magnitude fewer samples than the previous model-based state-of-the-art. Together these results are a concrete step toward the practical deployment of reachability learning and, with it, of specification-guided RL.

A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the past bears on the message in front of it. Testing this requires a real person's record, and such records are private, so benchmarks generate the person and the questions and settle in advance what matters. We release \bench, ten real relationships with an AI companion: 27,218 messages over up to 120 days, released as the conversation and four files derived from it, a profile, a persona, a chat ground truth and a question set, each citing the messages it rests on. Every chat label carries the reasoning trace that produced it, checked stage by stage against the conversation. Three findings follow. First, the past is rarely needed and far away. Pooled measures mislead: a recency window finds the required message for 95.9\% of probes and 2.2\% of those that need memory, and at the natural rate 96\% of the gain from supplying recorded evidence comes from messages that need none. Second, no detector we tried can tell when memory is needed on real messages, authored questions over the same histories leak the cue, and labeling the same messages as memories raises their use by ten to fourteen points. Third, three agent systems reconstruct the persona with the same F1 at a 31-fold difference in cost.

Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cover limited manipulation conditions or entangle multiple factors in cross-dataset evaluation. Consequently, aggregate performance provides an incomplete view of localization generalization. We introduce GIFTBench, a multi-axis benchmark of 115,013 manipulated images with pixel-level annotations spanning manipulation source, semantic target, editing operation, and composition complexity. GIFTBench supports axis-specific transfer analysis and evaluation on twelve external datasets. Its diagnostic studies reveal asymmetric cross-source transfer, recall-dominated failures, and heterogeneous degradation across semantic, operational, and compositional changes. Beyond diagnosis, the scale and diversity of GIFTBench provide a substantially broader training distribution than conventional IFL datasets. Training representative localizers on GIFTBench consistently improves their aggregate transfer to external datasets, showing that the benchmark serves not only as an evaluation tool but also as an effective training resource for cross-domain localization. Guided by the diagnostic findings, we further develop ForenScope, a detection and localization framework combining classification-adapted representations with multi-depth, multi-scale spatial features, learned layer fusion, and selective coarse-scale conditioning. Experiments show improved cross-dataset localization while retaining image-level detection capability. The GIFTBench dataset showcase page is available at https://giftbench-preview.doudoudouya337.chatgpt.site.

Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing time, through the use of expensive Knowledge Graphs (KGs) or Large Language Models (LLMs) to generate summaries, or during querying, through iterative LLM-driven retrieval. To reduce it while maintaining retrieval quality, we present MatRAG, a hierarchical framework that combines RAG systems with Matryoshka Representation Learning (MRL). MatRAG addresses both kinds of cost by aligning the semantic hierarchy of a clustering structure with the nested structure of MRL. Specifically, it organizes the corpus of documents into a Directed Acyclic Graph (DAG) of clusters with progressively coarser granularity. Each level is indexed by a lower Matryoshka dimension. MatRAG pairs an iterative, top-down traversal of the DAG with an entity-driven mechanism that controls the hop budget and re-ranks candidates. We evaluated MatRAG on three standard multi-hop QA benchmarks against seven representative baselines. MatRAG outperforms its strongest competitors in terms of retrieval quality; furthermore, it reduces indexing costs by avoiding KG construction and LLM-based summarization, and lowers query-time costs through dimension-aware similarity.

Video temporal grounding aims to localize events in videos from natural-language queries. For agents built around frozen video-language models, the harness determines how queries guide temporal predictions and how those predictions are refined. Manually refining these harnesses requires diagnosing grounding failures and coordinating changes to both agent workflows and instructions. We introduce VideoEvolve, a framework that automatically evolves agent harnesses for video temporal grounding. VideoEvolve uses a Cloze-Structured Harness Representation that preserves stage interfaces while leaving agent workflows and instructions open to evolution. Branch-Guided Harness Evolution preserves promising code branches for continued refinement, using execution feedback to guide local edits and validation to determine which improvements are carried forward. Experiments demonstrate improved grounding performance across multiple benchmarks. Component analyses identify instruction refinement as a consistent source of gains, while the benefits of evolved code vary across evaluation settings. Together, these results support automated harness evolution as an effective approach to improving video temporal grounding. Code is available at https://github.com/bingjunluo/VideoEvolve .

Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable factual memory without compromising real-time perception. We introduce OneStreamer, which jointly learns query-independent evidence recording and task response through a shared proactive generation process. Its Proactive Hierarchical Caption Memory (PHCM) produces time-grounded local-detail captions and summaries of completed events. Streaming caption targets supervise the interpretation of observed video prefixes during training. At inference, model-generated records complement a recent visual window, providing reusable factual context without revisiting historical visual features. Proactive State Transition Learning (PSTL) reduces the dominance of repeated waiting states by preserving supervision at all output anchors and selecting representative state-change and state-persistence tokens. We further develop a streaming data synthesis pipeline that aligns output content and timing with available evidence. Combining the resulting streaming captions and QA with cleaned open-source data yields OneStreamer-1M, a broad-coverage streaming video interaction dataset with over one million records spanning diverse tasks. Our 4B model achieves the best results among the compared methods across all eight evaluated streaming video understanding benchmarks. Ablations show that retaining generated captions improves historical QA without degrading real-time perception. PSTL also outperforms dense state supervision while supervising only 27.5% of annotated state tokens. Together, these results support proactive generation as a shared learning interface connecting perception, memory formation, and timely response in streaming video interaction.

Category-level object pose estimation (COPE), capable of generalizing to intra-class unknown objects, has become a core technique for robotic 3D scene understanding. However, existing COPE methods still require labor-intensive recollection of real-world training data for novel object categories, which limits their scalability in practical applications. This paper aims to achieve synthetic-to-real (Syn2Real) generalized COPE, where a model is trained solely on rendered synthetic data and directly generalized to real-world deployments. The central challenge lies in the significant domain gap between synthetic and real-world data, particularly in texture appearance. To address this, we aim to enhance domain generalization by learning domain-invariant representations that capture semantic commonalities among objects within the same category. We introduce 2D and 3D semantic consistency constraints to reduce the sensitivity of feature encoders to domain-specific features. In addition, we propose an end-to-end pose regression framework that performs 2D-3D cross consistency learning, leveraging dense cross-modality fusion to further refine pose estimation. Since simplicity and effectiveness are essential for real-world robotic deployment, our model operates exclusively on global features, yielding a highly lightweight and efficient architecture. Extensive experiments on the REAL275 and Wild6D benchmarks, as well as real-world robotic manipulation scenes, show superior Syn2Real generalization performance of our paradigm. Code and demos are released at https://paperreview99.github.io/GenCOPE/.

Decentralized agent economies increasingly build a single task from protocols that were designed and secured separately. This creates a simple problem: a workflow can look correct at each step and still produce the wrong outcome. For example, a correct escrow may release payment on an authorized approval that provides little evidence that the delivered work actually satisfied the task. We systematize this problem across the full lifecycle of an agent task. Our study organizes security and economic requirements into 17 property families over six stages, with receipt soundness and completeness assessed separately. We examine 12 systems and standards, five reusable mechanism families, and four classical baselines. We introduce guarantee closure, a task-relative criterion for determining whether guarantees established at one stage remain available and constrain the later decisions that depend on them. We apply the criterion to controlled and native workflows, covering 840 matched executions and an exhaustive 11,648-case check over a finite objective-task domain. Our results expose recurring failures between verification and settlement, where conforming work can remain unaccepted or valid evidence can be ignored. Public records and model judgments further distinguish recorded approval from evidence of task conformance, while economic analysis identifies the report, penalty, and shared-error assumptions behind these guarantees. These findings show where end-to-end guarantees fail and what must be repaired to preserve them across the workflow.

Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and curated annotations, limiting generalization in open-set scenarios. Recent zero-shot methods based on Large Vision- Language Models (LVLMs) alleviate this dependency but often lack temporal continuity and structured reasoning. We propose Cog-VADU, a fully training-free framework that reformulates VAD as a sequential cognitive reasoning task. Cog-VADU introduces Chain-of- Anomaly Detection Thought Prompting (CoADTP), which unrolls an LVLM into a recurrent reasoning chain across video segments. By propagating structured rationales over time, the model maintains implicit temporal memory, enabling robust discrimination between com- plex anomalies and high-motion normal activities. To improve reliability, we further design a cross-modal re-ranking stage that aligns textual rationales with visual embeddings, enforcing semantic consistency and temporal coherence for refined and stable predictions. Extensive experiments on multiple public VAD benchmarks demonstrate that Cog-VADU achieves competitive zero-shot performance. Moreover, cross-model evaluations show that CoADTP consistently enhances reasoning-based anomaly detection in a model-agnostic manner, pro- viding interpretable and generalizable anomaly understanding for real-world applications.

Adaptive model search is path dependent: once a challenger is adopted, it becomes the reference from which later candidates are generated. A statistically unsupported replacement can therefore alter hypotheses that have not yet been proposed. We introduce Evidence-Gated Research (EGR), a statistical adoption layer for moving-incumbent search. EGR freezes each challenger before decision evidence is revealed, builds anytime-valid evidence across a predeclared set of environments, routes evidence predictably toward unresolved components, composes a persistent candidate e-value, and passes that e-value to an online controller. Under explicit conditional-validity and predictability conditions, the resulting procedure controls false discovery rate for the declared all-environment adoption target even though earlier adoptions change later challengers. In a 5,000-trajectory closed-loop benchmark, development-only e-LOND attains persistent FDR 0.621, whereas no persistent false-adoption path is observed for the audited EGR variants in that finite run. In matched replay over 600 challenger--incumbent pairs, Stagewise EGR preserves fixed-anytime alternative crossing decisions while using 56.1% less decision evidence at the representative threshold. A three-environment public-data study and a 40,000-sample controlled neural benchmark reproduce the evidence-efficiency pattern. These results identify model replacement as a distinct statistical control point in adaptive model development.

Robot manipulation models primarily reason from 2D observations while acting in the 3D physical world. To bridge this gap, recent work has augmented robot data with geometric priors such as depth, point clouds, and 3D trajectories, while renderable 3D Gaussian representations provide another promising form of 3D supervision. However, 3DGS representation is designed mainly for photometric fidelity and may not preserve real-world metric scale, particularly when the supplied camera extrinsics are unreliable. We study the effect of extrinsic reliability and pose conditioning on feed-forward 3DGS, and propose a calibration-aware pipeline that anchors reconstructed scenes to the robot's metric workspace. Our experiments show that pose conditioning improves novel-view fidelity, while its geometric benefit depends on the reliability of the injected extrinsics. Using this pipeline, we present a renderable, metric-pose-anchored dataset with scene-level reliability information for robot manipulation research. Our dataset is available at https://huggingface.co/datasets/wonguen/3DROID

Predictive Vision-Language-Action (VLA) models aim to improve robotic manipulation via future observation or world dynamics forecasting. However, existing approaches often fail to realize this potential and underperform direct action prediction models. We argue that these limitations stem from modality misalignment between observations and actions, together with joint optimization conflicts that drive learning away from an action-centric objective. To this end, we introduce ATI-VLA, an Action-Centric Predictive Vision-Language-Action framework via Actionable Alignment Then Adaptive Injection. Specifically, it follows a two-step design: 1) Actionable Representation Alignment via a Shared Codebook. It aligns predictive observation and action representations by mapping both modalities into a shared discrete latent space via a unified codebook, making predictive observation latents readily usable for action generation and mitigating modality misalignment. 2) Action-Centric Adaptive Injection of Predictive Latents. Building upon this, it then injects predictive observation latents into action decoding as explicit predictive priors via a lightweight adaptive side-path, enabling adaptive predictive guidance under a single action-centric objective. Extensive experiments on both simulation and real-world robotic tasks demonstrate that ATI-VLA achieves state-of-the-art performance with faster convergence.

Asynchronous online learning offers temporal flexibility at a structural cost: learning communities tend to fragment rather than cohere. $β_0$, the number of disconnected behavioral clusters from Zigzag Persistent Homology, serves as a cohort-level indicator of this structure. Two questions remained unverified at scale: (1) does apparent $β_0$ convergence reflect genuine behavioral alignment or learner dropout? and (2) do assessment deadlines produce reproducible fragmentation-convergence cycles? We address both across all 22 OULAD courses (N > 22,000; 857 week-pairs). Changes in $β_0$ strongly co-vary with active learner changes (pooled r = 0.387; median per-course r_delta = 0.459, 20/22 courses), identifying $β_0$ as a participation-sensitive indicator: $β_0$ and active learner counts co-respond to deadline events rather than one causing the other. Deadlines produced fragmentation in 82.6% of assessments and the full Fragment First, Converge Later (FFCL) cycle in 60.2%. 3-phase analysis confirmed structural fragmentation as the dominant long-term trajectory (90.9% of courses), moderated by curriculum structure. These findings establish $β_0$ as a participation-sensitive structural indicator with direct implications for AI-augmented learning analytics design.

Algorithmic mathematical reasoning requires reliable decomposition, computation, and aggregation. Final-answer rewards provide limited guidance on intermediate errors, while successful execution does not guarantee mathematical correctness. This work proposes Function-Structured Graph Reinforcement Learning (FSG-RL), connecting subproblem graphs and Python implementations with multi-verifier feedback. The policy first learns to generate code from function graphs through supervised fine-tuning (SFT). Group Relative Policy Optimization (GRPO) then optimizes the policy using answer-gated rewards and span-level credit assignment. The framework also supports teacher supervision and structured memory. A benchmark curated from Grade School Math 8K (GSM8K), MathQA, MATH, and Omni-MATH pairs public function graphs with private verification specifications. Under a unified evaluation protocol, GRPO improves final-answer accuracy from 43.25% to 67.50% and full solution success from 32.25% to 52.25% over SFT. Continued reinforcement learning (RL) with teacher supervision yields additional gains. The gains extend beyond producing correctly formatted code, supporting verifier-guided reinforcement learning for mathematical reasoning. Code is available at https://github.com/ZihanLiummyycc/FSG-RL.

Enabling robots to estimate the kinematic parameters of articulated objects unlocks a wide range of capabilities for interaction and manipulation. The estimation has to happen from the information the robot currently observes, often just a single RGB image of an object it has never seen before. Current single-image approaches couple articulation part segmentation with articulation estimation, making their predictions vulnerable to missed detections and incorrect part associations, and they regress metric 3D geometry that a single view fixes only up to scale. We present QueryArt, a model that estimates articulation parameters from a single RGB image, a 2D query point, and camera intrinsics. QueryArt is trained to estimate the 3D articulation geometry relative to the queried point and in units of its depth, which keeps its target identifiable from the image alone. A single depth measurement at the query point then supplies the scale and recovers the metric parameters. We train QueryArt on a curated mixture of synthetic and real-world articulation datasets. We evaluate QueryArt on several benchmarks and compare it against recent baselines. QueryArt outperforms recent baselines on most articulation metrics, including on out-of-distribution data. To demonstrate the model's capabilities in real-world settings, we evaluate QueryArt on a mobile manipulator across 57 manipulation trials spanning 16 object parts and five viewpoint classes, achieving a 70.2% success rate. We provide code and videos at: https://abwerby.github.io/queryart/

Mesh extraction from 3D Gaussian Splatting (3DGS) aims to endow 3D Gaussians with accurate geometric structures, enabling explicit and precise 3D occupancy. However, existing methods primarily focus on scene-level mesh extraction, making them unable to represent object-level occupancy and often resulting in non-watertight surfaces. To overcome these limitations, we propose \textbf{MEGA} (\underline{M}esh \underline{E}xtraction from \underline{GA}ussians), a ``segment-then-mesh'' framework for extracting object-level, watertight meshes from complex 3DGS scenes. At the core of MEGA are \textbf{Spatial Visual Distillation (SVD)} and a mask-guided neural surface reconstruction module. SVD treats the 3DGS model as a teacher, sampling diverse camera poses and rendering the corresponding views of each segmented object. These observations are then used to train a mesh reconstruction model through photometric supervision. Extensive experiments on several widely used benchmarks demonstrate that MEGA achieves state-of-the-art performance in recovering accurate object-level 3D occupancy. Moreover, MEGA enables complex physical interactions by combining high-quality object-level meshes for geometric occupancy with 3DGS representations for photorealistic rendering.

Continual learning (CL) in text classification faces two critical challenges: catastrophic forgetting and negative transfer across sequential tasks. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA enable efficient adaptation by learning low-rank updates of the model parameters. However, these compact representations are normally trained in isolation, limiting their reuse across related tasks. We introduce Task-Oriented Rank Adaptation (TORA), a geometric routing framework that leverages the low-rank structure of LoRA adapters to decide whether to transfer knowledge from the most compatible expert (Boosting) or isolate the new task (Shielding) based on structural similarity. Evaluated across 15 diverse text classification benchmarks, TORA consistently avoids harmful routing decisions: compatible tasks exceed their isolated performance while reducing training time, and structurally distant tasks are protected from interference with no loss in accuracy. With a single geometric threshold and no reliance on task identities or predefined sequences, TORA provides a simple and effective approach for dynamic adapter routing in sequential text classification systems.

Active vision manipulation requires a policy to control both its camera and its end-effectors, yet camera motion determines which evidence remains visible within finite observation windows. Acquiring a new view can displace task-critical cues, while retaining a view forgoes potentially useful observations. We formulate this as an evidence-aware retain--acquire problem and present ActiveWAM, a unified world--action model that learns observation and manipulation jointly. To this end, we propose training-time inversion which constrains a frozen video prior by task-bearing source evidence and visible temporal changes, eliminating the need for test-time inversion or candidate ranking. At deployment, the policy generates bimanual and pan/tilt actions-including stay and reacquisition behaviors-from view-aware history, and updates context from newly measured RGB observations. Future-video prediction serves as a co-training signal, while action generation requires neither future-video decoding nor optimal viewpoint annotations. We introduce RoboTwin-AV, a 50-task benchmark with executable pan/tilt control and automatically generated demonstrations. ActiveWAM improves TAVIS out-of-distribution success by up to 17.0 percentage points over the strongest baselines, achieves 20.0 additional points over Fast-WAM on RoboTwin-AV, and outperforms it by 26.7 points on real-world physical kitchen tasks.

Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates every candidate along the same fixed computation path. We introduce architectural sampling, a training-free method that generates candidates through distinct forward computations by reusing selected blocks of decoder layers. Varying the block location and repetition count introduces computational diversity without updating model weights or adding auxiliary parameters. Across five Qwen checkpoints and twelve multimodal benchmarks, architectural sampling improves pass@9 over standard-path temperature sampling by 6.58 percentage points on average at the same nine-candidate budget. Reusing early layers yields the strongest gains, and the improvement in candidate coverage persists even under greedy decoding. The resulting candidates show lower lexical overlap and improve accuracy when used as rollouts for label-free test-time reinforcement learning. These findings extend the benefits of our architectural sampling beyond candidate coverage, demonstrating more effective learning from a model's own outputs.

Constructive neural combinatorial optimization (NCO) has emerged as a promising paradigm that learns to construct solutions to combinatorial optimization problems (COPs) step by step, which reduces reliance on handcrafted rules and enables fast inference. While many methods with dynamic embeddings generalize well, they typically rebuild subproblem representations from scratch at each step using deep attention stacks. Many high-performing methods in this category rely on solution labels or pseudo-labels for efficient training, or on aggressive search space pruning during reinforcement learning (RL). To address these limitations, we propose Memory-in-the-Loop (MiLoop), a purely RL-based constructive framework that leverages the multi-step computation already required by a rollout for selective memory propagation. Each rollout provides solution-quality feedback for learning while propagating historical representations, thereby enabling a shallow policy to learn effective dynamic embeddings without external solution labels or training-time search-space pruning. Specifically, MiLoop fuses current embeddings with historical memory before the attention layers and applies adaptive gated updates afterward. The updated representations support both current decisions and stepwise reuse. Extensive experiments across four COPs demonstrate that MiLoop consistently produces high-quality solutions on instances ranging from 100 to 10 million nodes, highlighting its strong generalization ability.

Mobile robots operating among pedestrians need trajectories that become available quickly, remain spatially credible through missed observations, preserve identity, and fit within an embedded computing budget. Aggregate tracking scores provide limited insight into when and how trajectories fail, while varying detector inputs can confound tracker and detector quality. We present a deployment-focused, tracker-only evaluation protocol that uses shared detections to isolate tracker behavior and directly evaluates initialization, detector-gap continuation, identity recovery, close-neighbor association, and load-dependent tracker-step runtime, while Higher Order Tracking Accuracy (HOTA) is retained as a complementary aggregate measure. We apply the protocol to the JackRabbot Dataset and Benchmark (JRDB) using six open-source trackers and our lightweight Pedestrian Reference Tracker (PedRefTrack), together with a GT-assisted variant that estimates the remaining tracker-side gap under idealized association and motion. Under fixed detections, the non-GT trackers span only 24.26%-29.67% HOTA yet exhibit markedly different capability profiles. After 1.0 s without detector support, no tracker without GT assistance maintains spatially correct, same-identity output in more than half of eligible cases, making missing-observation continuation the dominant limitation among the tested properties. Close-neighbor failures are smaller and increase mainly at the shortest separations. Tracker-step runtime on an NVIDIA Jetson Orin is heavy-tailed and load-sensitive, causing several trackers to fall below the 10 Hz real-time target in crowded frames. The protocol provides a reproducible way to characterize tracker behavior and deployment suitability in pedestrian-centric environments. Code and evaluation scripts are released at https://github.com/SCAI-Lab/tracker_eval.

Unified models are trained for both instruction-based image editing and text-to-image (T2I) generation, but standard editing pipelines keep source-image conditioning throughout denoising. We ask whether editing can benefit from T2I, and study how the effects of conditioning vary across edits and denoising stages. In pure editing, source attention declines for some edits over the sampling trajectory. This observation led us to task switching, which lets the model draw on its T2I capabilities. Across three unified editors and four benchmarks, switching to the T2I task for bounded intervals improves edit quality, while mean perceptual preservation remains close to pure editing across all three models. Unified editors therefore benefit from using both conditioning modes they are trained for, and the timing of the switch sets the balance between quality and preservation.

Building datasets remains one of the most manual and brittle parts of AI development. In this technical report, we focus on the most extreme but also most prevalent setting real world practitioners face: a zero data regime. Here, practitioners don't have any data for the capability they want to learn. We introduce Invent-A-Dataset which is a prompt based system to go from dataset description to realistic and large scale post-training datasets. We evaluate Invent-A-Dataset against five frontier model APIs including Anthropic, Google, Open AI, DeepSeek, Zai. Across eight task types and dataset sizes up to 20K samples, Invent-A-Dataset significantly outperforms with both the highest quality (17% relative gains) while simultaneously producing the most diverse samples (19% relative gains). Its diversity advantage widens with scale of training dataset size (from parity at 200 samples to 37% relative gains at 20K samples). This translates into considerable downstream training gains, resulting in far more performant post-trained models. Invent-A-Dataset fine-tune consistently ranks higher compared to other generator fine-tunes across different post-trained model architectures.

Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-based image editing and as reward signals for model training. However, systematically auditing whether these judges are influenced by cues irrelevant to editing quality is challenging because visual interventions may themselves alter the quality being evaluated. A judgment shift can therefore be attributed to bias only when the intervention is verified to preserve the underlying editing quality. To address this challenge, we introduce EditJudgeBias, a counterfactual benchmark with verified quality preservation, comprising 1,196 real editing samples and 13 cues injected across four evaluation sites. We verify quality preservation for the requested edit using calibrated multimodal validators, controls, and human inspection. We then audit five MLLM judges along three complementary dimensions: invariance to quality-preserving cues, agreement with human judgments, and stability of pairwise preferences. Importantly, observed shifts are evaluated against each judge's own zero-dose and re-query noise floors rather than against zero. Experiments show that quality-preserving cues move every judge beyond its own noise. Fabricated majority opinions increase ratings, irrelevant visual elements cause larger shifts than whole-image manipulations, and swapping candidate order reverses up to 60.9% of pairwise decisions. Edit-region cues also tend to reduce human agreement. The three measures characterize judges differently, showing that robustness cannot be captured by a single metric.

Bio-inspired tendon-driven rigid-soft coupled dexterous fingers exhibit strong nonlinearity and configuration-dependent sensitivity, making accurate modeling challenging. In discrete-time control, Jacobian-based kinematic algorithms typically rely on point-wise local linear approximations, which makes their performance sensitive to sensor sampling frequency and controller update frequency. To address this issue, we propose Jacobian Flow Matching (JFM), a structured learning framework based on Conditional Flow Matching (CFM), to learn a resolution-consistent Jacobian field that models actuation-to-motion transitions as a dynamical flow. The proposed framework supports both single-step prediction and continuous rollout via ODE integration, enabling consistent inference across temporal resolutions. Experiments on a tendon-driven rigid-soft finger show that the proposed method suppresses outlier errors and improves single-step prediction accuracy, reducing the global average RMSE by over 53% compared with a baseline discrete Jacobian learning approach. For long-horizon prediction, trajectories recovered via ODE integration achieve higher fidelity under sparse sampling (Stride = 8), reducing the RMSE median by 14.43% and the error variance by 24.87%. These results demonstrate that the learned flow-based Jacobian field provides an effective local model for offline multi-step trajectory optimization in rigid-soft coupled nonlinear systems.

Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive information can be distributed across correlated predictors. Existing methods such as SHAP, LIME, HSIC, MI/CMI, and SAGE may therefore produce unstable rankings under multicollinearity or near-duplicate predictors. We propose the Mutual Correlation Impact Ratio Method (MCIR-M), a dependence-aware global feature-importance approach that quantifies the unique predictive information contributed by each feature beyond a selected dependence neighbourhood. MCIR-M introduces the Mutual Correlation Impact Ratio (MCIR), which conditions each feature on strongly dependent neighbours and computes a normalized ratio of conditional to block-level information. The population score lies in [0,1] and equals zero under exact conditional redundancy. We also introduce a lightweight estimation procedure that computes MCIR using a fraction of the available data and evaluates agreement with full-data explanations. Across controlled synthetic redundancy experiments and the UCI HAR benchmark, MCIR shows dependence-aware ranking behaviour, with its clearest advantage under injected near-duplicate predictors. Comparisons with independent and conditional SHAP, SAGE, HSIC, MI-based scores, and CIR-family baselines are mixed across real-data criteria. Reduced explanation samples lower computational burden in the evaluated configurations, while agreement with full-data explanations is assessed separately through ranking, head-set, and faithfulness diagnostics. Overall, MCIR-M provides a practical dependence-aware diagnostic for global explanation under strong feature dependence.

Vision-language models (VLMs) face a fixed-budget trade-off between processing more visual information for fine-grained perception and using a larger language backbone for complex reasoning. Existing studies do not tell us which combination of backbone size and input resolution to deploy, especially in high-resolution deployments. To address this gap, we propose the Separable Law that describes how VLM performance changes with language backbone size and visual token count. We fit the law to measurements from 26 InternVL and QwenVL models, with language backbone sizes from 1B to 72B, on four high-resolution benchmarks with image sizes from 224 pixels to 8K. We find that the questions responding to scaling can be predicted from the skill they require, while a substantial fraction never responds at all. We also find that the two model families gain similarly from a larger backbone, while their gains from more visual tokens differ sharply. Combined with a cost law, the Separable Law gives a closed-form rule for allocating compute between backbone size and visual tokens. When deployment is limited to available configurations, the law identifies model and image sizes that perform close to the best feasible choice under the same budget. We hope our work offers a principled way to decide how much a model should be allowed to see at high resolution, given what it must reason about.

Yorùbá is a widely spoken tonal language that depends on diacritics to avoid lexical ambiguity. However, it is often written without these diacritics, thereby hindering downstream Natural Language Processing (NLP) tasks. In this paper, we introduce Yo-ByT5, a byte-level Automatic Diacritic Restoration (ADR) model fine-tuned from ByT5-small. We evaluate Yo-ByT5 alongside five publicly released Yorùbá ADR models and one open-weight large language model (LLM) on the YAD benchmark under a consistent protocol. Our results demonstrate that Yo-ByT5 matches the performance of the strongest existing model, mT5-base, with a DER of 10.14% and a CER of 3.48%. Furthermore, it exhibits superior text fidelity despite using approximately half the parameter count of mT5-base. We also release our training code and model outputs, as well as call for the development of a larger, purpose-built benchmark for Yorùbá diacritic restoration.

Cooperative MARL is commonly evaluated through cooperation discovery from random initialization, leaving open whether continued optimization can destabilize learned cooperation. Actor-critic comparisons can also conflate critic presence with value gradients entering shared actor representations. We study cooperation maintenance, defined as the survival of a behaviorally verified cooperative policy under continued training. We formulate maintenance as a right-censored event-time problem and compare matched warm starts: X0 allows value loss gradients to update shared actor features, X1 retains the critic while blocking those gradients, and X5 removes the learned critic as a critic-free reference. This isolates direct value-gradient access while controlling initialization, critic computation, and evaluation. Positive reward scaling preserves strategic preferences and equilibria while perturbing learning dynamics. Gradient audits confirm the intended routing pathways, and frozen-policy torso perturbations probe whether route-induced updates align with local cooperation boundaries. In confirmatory MinEx and CleanUp-lite experiments, higher scales selectively increase maintenance sensitivity in X0; X1 remains near the censoring ceiling, and X5 has no confirmed events in the tested settings. In CleanUp-lite, route-by-scale displacement is associated with reduced local cooperation margins; MinEx shows a weaker, optimizer-dependent effect. These results identify a conditional, scale-sensitive maintenance risk associated with direct value-gradient routing rather than a universal failure of critics.

Action chunking improves the performance of policies learned by behavioural cloning, and several mechanisms have been proposed to explain why, including temporal consistency, horizon reduction, representation learning, and reduced error compounding. We instead study what happens to an action error once it enters the system. At each state, we inject a small action error and measure how fast it grows or shrinks under two execution regimes: open-loop, where the rest of the chunk is replayed without replanning, and closed-loop, where the policy replans after the perturbation. The fitted rate labels each state as contracting, expanding, or unresolved. Across twelve manipulation tasks from three benchmark suites, we find that confidently stable states are rare, while error amplification is common among states whose propagation rate can be resolved. We further find that the measured propagation rate depends strongly on the fitting horizon: amplification is typically front-loaded, so short windows can overestimate longer-horizon propagation. Finally, we train predictors on these labels and find that a state's open-loop regime can be recovered from camera frames and proprioception alone, while its closed-loop propagation is only partially recoverable because it also depends on how the policy acts after the perturbation. These results suggest that error-compounding arguments alone do not provide a complete account of action chunking: neither passive open-loop dynamics nor policy replanning consistently contracts an injected error, and replanning rarely turns open-loop amplification into confident contraction. This suggests that closed-loop reactivity should be trained explicitly, using perturbation- and tree-coverage-oriented training to expose policies to deviations they must recover from, rather than expected to emerge reliably from standard imitation learning.

Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank adapters, but their fixed rank budget can limit adaptation. Gradient low-rank optimization offers greater flexibility, yet independently chosen client subspaces create a problem we term \emph{subspace fragmentation}: local projections interact with data heterogeneity to bias aggregated directions, while aggregation can increase update rank and communication cost. Thus, accurate local gradient compression need not preserve global descent. We propose \texttt{FedLore}, which shares a low-rank optimization basis within each round and refreshes it across rounds. The shared basis enables exact aggregation in low-rank coordinates and eliminates the identified projection bias. Subspace refresh allows the accumulated model update to exceed the per-round rank budget. We characterize the aggregation bias and establish an $O(T^{-1/2})$ stationarity bound for the projected-SGD variant under a global-gradient coverage condition and standard smoothness and variance assumptions, with bounded gradient heterogeneity. Experiments on vision and language tasks, including federated pre-training, show that \texttt{FedLore} outperforms the evaluated low-rank adapter baselines and matches or exceeds full-parameter training, while reducing communication and optimizer-state memory.

Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat the agent itself as fixed. In practice, an agent is a configurable system: users decide what to tell it, how long to let it run, and which model to use, and each of these choices can change how well and how consistently it performs. We study these choices on a new benchmark of four scientific tasks, where a coding agent must find and correctly operate a published specialist model. We investigate five parts of the agent's configuration: task information, reasoning, self-verification, time budget, and backbone model. We find substantial run-to-run variability, with approximately 54% of the outcome variance coming from repeating the same configuration rather than changing it. Across configurations, the information provided to the agent has the largest effect, exceeding both time budget and model size, while also reducing cost and improving calibration. Configuration choices also interact: additional time helps only when the agent has sufficient information or a capable enough model to use it. Finally, a trajectory-based taxonomy of agent behavior reveals that prompting an agent to verify its answer has little effect on its verification behavior, whereas providing a dedicated verification tool changes that behavior substantially. These results suggest that agents should be evaluated as configurable systems themselves, and that some desired behaviors are more effectively implemented in the system than requested through prompting. We release the benchmark and more than 18,000 agent trajectories.

Generative video world models can now synthesize open-ended environments that agents can navigate and interact with in simple ways. Yet open-ended generation does not imply full interaction: as a generated world expands, newly created content through navigation should expand what the agent can act upon, and as the agent changes the world, those changes should become persistent parts of the environment rather than transient visual effects. We characterize these two requirements as Open-World Interactivity, where newly generated or encountered entities are incorporated into the actionable world, and Persistent State, where interaction outcomes are committed to the world state and continue to influence subsequent observations and interactions. We present Oneira, an interactive video world model that closes the loop between generation and interaction through an explicit, extensible world state managed by a coding agent. Given the current observation and an action or high-level goal, the agent reads the world state, grounds the relevant entities, plans the interaction, and writes its outcome back into a world state table. When exploration reveals new objects, the agent incorporates them from generated observations, allowing the interaction space to expand with the generated world. Meanwhile, previously induced state changes are carried across video segments, making the consequences of interaction persistent parts of subsequent world evolution. The updated world state is rendered along the camera action trajectory into a coarse conditioning video, from which a video generator fills in the appearance, motion, and interaction details not represented in the state. Experiments show that Oneira enables direct and consistent interaction with newly generated objects, while preserving the effects of prior interactions over long horizons. Project page: https://madaoer.github.io/projects/oneira

Continuous legged manipulation requires accurate end-effector tracking while the base keeps walking. Combining reinforcement learning (RL) with model predictive control (MPC) suits this task: the learned policy provides robust locomotion, while MPC coordinates the base and arm to compensate for tracking errors. However, MPC can compensate only for base motion that it can predict, and a learned policy's command response varies with gait phase, contact, and payload. We present ReCo, a framework that couples response-consistent locomotion with policy-aware MPC for legged manipulation. Response shaping trains the policy to respond to commands consistently and repeatably across randomized dynamics. An identified closed-loop response model then lets MPC jointly plan locomotion commands and arm motion. On the simulation benchmark, ReCo reduces position and orientation root-mean-square error (RMSE) by 28.7% and 27.4% relative to the best baseline for each metric. Real-world experiments demonstrate onboard continuous legged manipulation with coordinated base and arm motion.

Reliable visual reasoning requires composing multiple visual observations and returning consistent answers to logically equivalent questions. We introduce Hob-VL, a benchmark for visually grounded Boolean reasoning. Hob-VL comprises two tasks: (1) evaluating whether a Boolean rule holds in an image, and (2) identifying the (unique) object satisfying a Boolean description. Hob-VL contains 6,000 human-verified balanced Yes/No questions, each defined by a Boolean combination of ten visual statements, across 1,000 generated scenes and 46 diverse labeled photographs, along with 1,000 object-identification questions over the same photographs. Our question families are deliberately constructed to challenge reasoning through misleading local cues and nested logical operations, and include symbolic and structured natural-language presentations. Across eight model configurations with thinking disabled or minimized, Boolean accuracy ranges from 48.52% to 50.57%, while the identification accuracy reaches at most 43.0%. A thinking-enabled GLM configuration achieves uneven gains while retaining substantial errors and inconsistencies. Hob-VL exposes these failures through executable reference answers and matched evaluations.

Video Large Language Models (VideoLLMs) receive frames in sequential order and interpret how visual content evolves along the temporal axis, yet temporal reasoning remains a persistent weakness across architectures. Reversing the frame order of a video, a transformation that should invert temporal answers, often leaves the final prediction unchanged. We investigate where this failure originates by defining the temporal divergence vector $τ_l$, the layer-wise representational difference induced by reversing temporal order. Tracking its magnitude across layers reveals a consistent temporal divergence profile where the divergence peaks at intermediate layers and progressively diminishes toward the output. We confirm this peak is specific to temporal reasoning and functionally critical for predictions, establishing that VideoLLMs acquire temporal information at intermediate layers but fail to maintain it to the output. This progressive fading motivates our method, Temporal Activation Injection (TAI), which extracts $τ_l$ at the peak of the profile for each input and reinjects it into subsequent layers following the measured decay. TAI requires no training and consistently improves temporal reasoning across three VideoLLMs and four benchmarks with negligible impact on non-temporal tasks. Code is available at https://github.com/Youngwoo-git/Before-It-Fades.

Large Language Models (LLMs) are increasingly applied to process streaming data, with practitioners relying on benchmarks to select the best model even though these signals only approximate real performance. While oracle annotations can provide reliable feedback, they are often costly and difficult to obtain at scale. To address this challenge, we propose ONLINE LLM PICKER, the first framework for active model selection for LLMs in online settings. Given an arbitrary stream of queries and a limited annotation budget, ONLINE LLM PICKER selects the most informative prompts for annotation to identify the best LLM among candidate models. Across multiple tasks including 10 datasets, for over 130 language models, we show that ONLINE LLM PICKER saves annotation cost by up to 71.67% while reliably identifying the best or near-best model for the stream. We also show that using the returned model for sequential generation on unannotated prompts across the stream reduces regret by up to a factor of 2.51x, indicating that ONLINE LLM PICKER can identify the best or near-best model well before processing all streaming prompts.

Pretrained 3D encoders are typically developed on globally reconstructed scenes expressed in a consistent world coordinate frame, whereas embodied systems must reason from partial, viewpoint-dependent observations in camera coordinates. We show that this shift from globally learned 3D feature spaces to realistic partial observations exposes a severe representation mismatch, which we find consistently across representative state-of-the-art encoders, including Sonata and Concerto. A frozen Sonata encoder with a global linear probe achieves 72.47 mIoU on full ScanNet scenes, but 2.57 mIoU on single-frame camera-coordinate inputs. Training-free gravity alignment recovers performance to 41.64 mIoU, showing that coordinate-frame mismatch is a dominant source of degradation but cannot be fully resolved through canonicalization alone. We introduce PAGER, a label-free adaptation method that aligns partial-view features with a frozen global 3D semantic space using only paired partial/global geometry. It learns lightweight adaptation modules while keeping the pretrained encoder and global segmentation probe frozen. Matched-point feature alignment anchors partial features to their global counterparts, while relational supervision preserves their similarity structure with respect to the global representation. Global geometry provides supervision only during training. Inference operates directly on the partial observation. Without partial-view labels, PAGER outperforms label-supervised PEFT on both Sonata and Concerto, and in zero-shot ScanNet$\rightarrow$ScanNet++ transfer surpasses fully fine-tuned Sonata ($53.93$ vs.\ $48.09$ mIoU), suggesting that preserving the frozen global representation can improve cross-dataset transfer.

Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they often provide limited transparency into learned representations and consistency with real-world vehicle dynamics. This lack of formal assurance limits their use in safety-critical validation and certification workflows. To address this aspect, we introduce a layered evaluation protocol that complements existing methods by assessing models across five layers. The first four layers inspect internal representations and network layers through kinematic alignment, statistical baseline comparison, latent controllability, and activation analysis. The fifth layer evaluates model outputs against vehicle dynamics constraints such as lateral jerk thresholds. We demonstrate the protocol on a Variational Autoencoder (VAE)-based scenario generator. Although standard output-level metrics and visualizations suggest that the generated scenarios are realistic, our protocol provides deeper insight into the extent to which the model's latent space aligns with kinematic features and whether visually plausible trajectories satisfy vehicle-dynamics constraints. We further apply the protocol to additional generative models, demonstrating its applicability beyond the VAE architecture.

Climate downscaling aims to reconstruct fine scale spatial fields from coarse resolution inputs. Evaluating the quality of these reconstructions is challenging: low pointwise error can come at the cost of fine scale variability, while realistic spatial variability can be achieved with inaccurate local structures. The evaluation metric can therefore change which method appears to perform best. This work presents a multi metric benchmark comparing five spatial downscaling methods on ERA5 temperature, wind, and precipitation fields. Five criteria assess complementary properties: pointwise error, structural similarity, distribution error, spectral error, and gradient error. The results reveal a systematic trade off between spatial fidelity and fine scale variability. Some methods perform best on pointwise and spatially aligned metrics, but lose high frequency content, while others preserve substantially more spectral variability at the cost of less accurately positioned local structures. Consequently, method rankings change across metrics and variables. These results show that there is no single best downscaling method. Multi metric evaluation is therefore essential for assessing which properties of a climate field are preserved.

Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments. Fully distributed control, in which each UAV hosts an independent Small Language Model (SLM), removes reliance on a centralized coordinator but introduces an information-management problem: long-running interaction histories can degrade the reasoning context, while indiscriminate information dissemination increases communication and inference overhead. We address these challenges with a distributed UAV-agent architecture that enables continuous local SLM control through an event-driven reason-act-observe lifecycle. Runtime knowledge is represented as structured atomic notes and organized into core, local, and peer-specific memory. A deterministic interest-aware gossip engine selectively disseminates these notes according to recipient-specific semantic novelty and recency. We evaluate the architecture using ten UAVs in a simulated search-and-rescue mission. Our approach completes all experimental runs, whereas unrestricted flooding messages completes only 70-85\%, and delegating forwarding decisions to the SLM prevents mission completion in every run. Compared with unrestricted flooding, our approach approximately halves inference-token consumption, reduces transmitted data, and achieves lower survivor-count error.

LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produced under one skill to guide the next. Because skills may come from open-source repositories, this handoff can also carry attacker-controlled claims into later decisions. In this paper, we introduce APEX, which constructs and refines adversarial skill chains tailored to a user task and an attacker-selected action. The key insight is that an agent-written record of genuine task progress can carry a false claim of user approval across skills: an upstream skill induces the agent to create the record, and a downstream skill uses it to direct the attacker-selected action. Across four targeted-action families and six models on SkillsBench, the chains induce the selected action in 512 of 690 attempts (74.2%). On GPT-5.4, the full chain succeeds in 84.3% of attempts, compared with 17.4% when the workflow is merged into one skill. We further evaluate a prompting defense that asks the agent to check skill-produced files against the original request. On GPT-5.4, it lowers targeted-action success from 84.3% to 59.1%, while the verifier test-pass rate across 72 benign native-skill tasks falls from 86.7% to 56.3%. These results highlight the need for defenses that prevent attacker-directed actions while preserving legitimate task performance.

World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, action-consistent predictions omit the transition needed for task completion. In this paper, we show that this failure is not inherent to the world model backbone, but emerges when adapted for short-chunk control, which can repeatedly favor plausible local continuations over task-completing transitions. To address this, we introduce Completion Aware Guidance (CAG), a training-free sampling method that guides generation toward task completion. Across representative WAMs, CAG improves success from 64% to 70% on a RoboTwin 2.0 subset and from 69% to 75% in zero-shot simulation, while reducing task-incomplete imagination from 79% to 40%.

As the use of large language models (LLMs) expands, post-training has become increasingly important for adapting them to downstream tasks. However, obtaining reliable supervision remains costly, especially in domains without reference answers or executable verifiers. LLM-as-a-Judge provides scalable pseudo-rewards for unlabeled responses, but a single point score does not explicitly represent reward uncertainty. This motivates representing pseudo-rewards as conformally calibrated reward ranges. We propose Range-GRPO, a semi-supervised post-training framework that combines limited labeled data with unlabeled prompts. In Group Relative Policy Optimization (GRPO), learning signals depend on relative reward comparisons within each rollout group. The proposed objective compares reward ranges pairwise rather than reducing them to point rewards, allowing interval uncertainty to affect both the magnitude and direction of these signals. Our theoretical analysis characterizes this distinction and shows that the proposed objective recovers the Dr.GRPO advantage when all reward ranges collapse to points. Empirically, Range-GRPO achieves the highest in-distribution and out-of-distribution average performance among the evaluated semi-supervised methods while requiring fewer training resources.

Primal-dual hybrid gradient (PDHG) methods solve large-scale linear programs (LPs) using GPU-friendly matrix-vector products and projections, but their practical performance depends on coordinating algorithm parameters, acceleration, and restarts. We introduce GALLOP, which uses reinforcement learning to jointly learn continuous algorithm parameters and discrete restart decisions without differentiating through the solver. Its generalized accelerated PDHG update combines separate primal and dual extrapolation, history corrections, and restart anchoring with independently adjustable coefficients. We train a dimension-agnostic feedback policy using a groupwise proximal policy optimization objective that clips likelihood ratios separately for different control groups and excludes inactive acceleration controls on restart transitions. We evaluate GALLOP on six LP families and a public item-placement benchmark. On the main evaluation settings across the six families, GALLOP reduces iteration counts by factors of $1.9$-$5.6$ and achieves up to a $16.0\times$ speedup in algorithm wall-clock time over MPAX. With one policy trained per family, the learned policies generalize without retraining to within-family LPs $3\times$-$400\times$ larger than the largest training instances, including Transport LPs with $10.24$ million variables.

Existing image forgery detectors often suffer from generalization to unseen manipulation methods due to the limited ability to capture transferable forensic cues. Recent cross-reconstruction based methods attempt to improve generalization through semantic-artifact disentanglement, but typically align heterogeneous artifacts across generators and exclude artifact representations during reconstruction, which may overlook the inherent diversity and visual cues of manipulation artifacts. In this work, we revisit cross-reconstruction and introduce an artifact-oriented disentanglement framework for robust image forgery detection. We argue that \textbf{artifact diversity}, i.e., the intrinsic variations of manipulation artifacts introduced by different generation processes, contains complementary forensic cues rather than undesirable domain variations. Instead of enforcing explicit artifact alignment, our framework preserves diverse artifact characteristics through semantically aligned cross-generator reconstruction. Furthermore, we incorporate artifact representations into the reconstruction process and introduce a masked frequency-aware reconstruction strategy to emphasize manipulation-related residuals while reducing semantic interference. This design enables the model to learn transferable forensic representations from diverse artifacts. Extensive experiments on multiple benchmark datasets demonstrate improvements under both cross-dataset and cross-generator evaluation settings. Further analysis and ablation studies validate the effectiveness of artifact diversity preservation and artifact-aware cross-reconstruction.

Sagnac interferometers are important tools for precision measurements. Cancellation of common-path noise ensures a high degree of stability against external perturbations, while their sensitivity to rotations provides the basis of laser gyroscopes. Here we highlight another, less explored feature of Sagnac interferometers: the fact that optical elements are traversed in reverse order for clockwise and counterclockwise propagating light components. This provides the opportunity to explore a classical realization of indefinite causal order, where the order of events within a sequence is not fixed. We explore this concept to identify the geometric phase associated with two non-commuting polarization operations with a single measurement. This idea may have applications for the rapid determination of polarization manipulations or optical activity within chiral media, but foremost it provides a geometric illustration of indefinite causal order.

Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparator on the evaluation data. In the benchmark's own setting this is harmless, but under distribution shift it is not. On HELM Safety the selection cost is 0.003-0.030 of harm under random splits and 0.045-0.113 under held-out categories, comparable to the whole deficit attributed to routing, with its direction holding under either published judge alone. It rises seven- to ninefold on AgentDojo when suites are held out. Across seven safety corpora chosen by rules fixed in advance, three meet a registered interval test and four beat a later permutation null, and three of the four interval misses are corpora where some models have zero observed harm. Prior work proves the direction of this bias. We size it on harm and accuracy, show that it is larger under the held-out splits we measure, and bound it by optimism plus a shift-dependent regret. Scored honestly under shift, routing buys little on these benchmarks. In most pool cells the nested router serves the honest baseline's model, and on the nearly saturated AgentDojo corpus a perfect pre-dispatch router is worth at most two points of harm. We also find a model's expressed recognition of a late injection steerable. On held-out reruns an attacker who knows which model it faces lowers GPT-5.4's judged recognition by 19.6 points, confirmed by an independent label. In an offline counterfactual composition into a controller, the same attack raises or lowers estimated harm depending on the fallback model. Safety routing should be evaluated under shift, against a baseline chosen without the test labels, and recognition-based defences should be scored on harm against an attacker who chooses what the model sees.

In predictive maintenance, early and late RUL prediction errors carry asymmetric consequences, yet hyperparameter optimization typically targets a single accuracy metric that treats both directions equally. This study treats the optimization objective itself as a design variable. Five architectures (MLP, LSTM, XGBoost, TCN, and Transformer) are evaluated under three regimes: single-objective maximization of $R^2$, single-objective minimization of the NASA scoring function, and a multi-objective formulation that jointly optimizes both criteria. The multi-objective search employs NSGA-II with Entropy-CRITIC weighting for Pareto selection. Seventy-five model-dataset-strategy combinations are assessed on the NASA C-MAPSS turbofan and BackBlaze hard-disk drive benchmarks. On C-MAPSS, all strategies achieve comparable accuracy ($R^2 \approx 0.89$), yet multi-objective optimization reduces directional imbalance by approximately 33%, improving calibration of early versus late predictions. Model rankings prove configuration-dependent, with simpler architectures frequently outperforming deeper temporal models. On BackBlaze, the objectives shift from complementary to conflicting, producing divergent Entropy-CRITIC weights and a substantial generalization gap (best $R^2 \approx 0.34$). These results demonstrate that the optimization objective materially shapes prognostic behavior and that multi-objective search provides a practical mechanism for calibrating prediction timeliness in RUL modeling.

Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making them particularly suitable for high-stakes applications where compliance with domain knowledge is essential. A key bottleneck in this paradigm is the acquisition of symbolic constraints: encoding domain knowledge into logical formulas remains a manual and expert-intensive process. In this work, we investigate the extent to which auto-formalization via LLMs can systematically translate textual knowledge into symbolic knowledge that can be plugged into NeSy predictors. To this end, we introduce auto-nesy-bench, a new benchmark for evaluating constraint formalization and its impact on downstream accuracy of NeSy predictors. Through an extensive evaluation across several domains, we find that LLMs can formalize constraints to a meaningful extent, generating formulas that are often similar to those provided by human experts. Moreover, when the generated formulas are syntactically valid, they can lead to high-quality downstream predictions. The code and benchmark are available at https://unitn-sml.github.io/auto-nesy-bench/.

Large language models are often asked which input factors influenced their outputs. For structured inputs, such reports can be checked by counterfactual perturbation, but each factor must be queried multiple times to estimate its effect, so verification is usually budget-limited. We study how this limited-budget setting changes the incentive to report factor-level influence truthfully. We formalize the interaction as a verification game and show that proper scoring alone is not enough when auditing depends on the report: report-dependent auditing creates a suppression incentive, because factors reported as important are more likely to be checked and penalized for estimation noise. In contrast, report-independent auditing, or a mixed rule with a small report-independent floor, removes this channel and makes truthful reporting preferable to full suppression. We instantiate the framework with the Counterfactual Brier Score (CBS) and evaluate its predictions on four NLP benchmarks. A synthetic rational agent matches the theoretical prediction exactly, and real LLMs follow the same incentives when they are made explicit. The main design implication is simple: under partial verification, factor-level explanation systems should include a report-independent audit component so that under-reporting cannot be used to avoid scrutiny.

Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited expressivity of vector-based hidden states, whilst Transformer-based models are limited by the quadratic scaling of attention. Recent work has proposed tackling this problem with the Test-Time Training (TTT) framework, which stores episodic memories in the parameters of a neural network through gradient descent at both train and test-time. This approach has seen success in the domain of Natural Language Processing, however, to the best of our knowledge it has not yet been applied to the domain of Reinforcement Learning (RL), nor has there been a study analysing how this memory practically functions. In this paper, we study the potential of the TTT framework for offline RL by augmenting a Decision Transformer with TTT layers, dubbed the Decision Titan. We analyse performance and properties of the model in the X-Maze environment, an extension of T-Maze designed to test sequential memory, and investigate how the memory mechanism learns by visualising gate values over time. Our key findings are that Decision Titan can learn long-term dependencies with ranges 20x longer than the context window, generalises to lengths 1.7x the training data, but crucially temporal generalisation depends on the time embeddings used, and the ability to learn long-term dependencies depends on how the relevant information is encoded.

Metal artifacts in postoperative musculoskeletal CT obscure bone-implant and adjacent soft-tissue interfaces. Many metal artifact reduction (MAR) methods require unavailable raw projections or learned models that may shift across scanners and implants. We present VoxelSynth3D, a training-free 3D image-domain framework for reconstructed CT. The framework combines support masking, normalized tissue synthesis, deviation gating, and restricted edge refinement. Detected implant voxels are preserved in the output, while correction targets metal-induced artifacts in the surrounding tissue. We also construct Synthetic CLINIC-Metal, a controlled paired synthetic evaluation resource, from no-metal CTPelvic1K volumes with clean targets, metal/artifact masks, fixed seeds, and patient-level splits; 75 unpaired real metal cases receive qualitative/no-reference evaluation only. The operating point was fixed in a near-flat validation basin. With exact-mask oracle localization, all methods share a metal-excluded tissue ROI. On 40 held-out cases, VoxelSynth3D reduced RMSE from 801.48 to 786.18 HU (paired gain 15.30 HU, 95% CI 11.68-19.23), improving every case and exceeding the evaluated 3D Gaussian smoother by 13.58 HU. Clean-edge agreement decreased next to metal but exceeded input beyond 5 mm. Thus, VoxelSynth3D provides case-consistent within-distribution tissue-error reduction with a localized structural tradeoff. Spacing-aware sensitivity retained aggregate broad-region improvement and identified near-metal calibration as a target.

Most preference optimization methods, such as Direct Preference Optimization (DPO), apply preference supervision at the response level, although autoregressive language models are optimized token by token. As a result, all tokens in a rejected response contribute to the negative training signal, including tokens that may encode behavior that is useful for the preferred response. We introduce GAW-PO, a gradient-aligned token reweighting method for DPO that estimates, for each rejected token, whether penalizing it would interfere with the preferred update directions. Tokens whose gradients are strongly aligned with the preferred behavior receive a weaker negative contribution, while conflicting tokens retain a stronger penalty. Our method achieves the highest average performance among the evaluated preference-optimization methods, improving by 0.97 points over standard DPO and 0.65 points over the strongest competing baseline across 11 benchmarks spanning mathematics, reasoning, coding, and question answering. We further show that gradient-aligned weighting is substantially more robust to aggressive preference optimization: as the DPO regularization parameter $β$ decreases, standard DPO degrades sharply, whereas GAW-PO continues to improve. These results suggest that accounting for the interaction between rejected-token updates and preferred behavior provides an effective form of token-level credit assignment for preference optimization.

Robust perception in intelligent vehicles demands 3D object detectors that remain dependable under domain shifts, such as changes in time of day, location, or weather. However, due to costly annotation and rare shifts, some environments lack sufficient data to train a standalone detector. Federated learning offers a privacy-preserving framework for collaborative model training, enabling clients to benefit from shared learning across diverse environments. Yet, this framework traditionally relies on a single global consensus model, which struggles to perform across heterogeneous local data distributions. Local conditions are better captured by adapting a subset of the model, but many personalization approaches rely on predefined layer partitions or fixed personalization ratios, thereby limiting adaptation to client-specific divergence. To reduce this rigidity, we propose FedCKA, a Centered Kernel Alignment (CKA)-based strategy that dynamically handles the personalization-globalization trade-off. Specifically, FedCKA computes layer-wise feature similarities between local client models and the global consensus model during training. By converting layer-wise similarity scores into client-specific aggregation masks, FedCKA selectively shares representation-consistent layers. Evaluation on a unified multi-domain benchmark based on nuScenes shows that FedCKA outperforms established federated baselines, including FedBN, FedRep, and FedSelect, improving average NDS by 7 percentage points over the strongest baseline. The findings offer both a comparative benchmark and a promising direction for robust federated 3D perception across shifts in location, weather, and illumination. Code is available at https://github.com/j-verhoog/FedCKA.

An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of solution coverage. Although this trade-off has been observed in math and coding tasks, it need not extend to agentic tasks, where multi-turn tool use and interaction may require capabilities newly acquired during post-training. Our surprising finding is that pre-trained LLMs, equipped with a light inference harness, can serve as capable agents. Despite far lower accuracy (pass@1), they often surpass their post-trained counterparts in solution coverage (pass@K) given a sufficient test-time budget. We further analyze the underlying mechanism and show that post-training pushes tasks toward two extremes, always solved or never solved, and thereby improves sampling efficiency and consistency at the cost of solution coverage. To measure this cost, we propose Sharpening Tax, a diagnostic metric that quantifies the loss in test-time scalability after post-training. Across 14 base/post-trained model pairs from four families and three agentic benchmarks (42 cases in total), the tax is prevalent in most settings, can be estimated from a few rollouts, and correlates well with other metrics. Finally, we present posterior-tempered group sampling (PTGS), a simple plug-and-play Bayesian sampler that adapts the sampling temperature per prompt to its estimated difficulty. Applied during RL training in two agentic environments, PTGS pays a smaller tax than the fixed-temperature baseline, solving more tasks under repeated sampling while also improving single-shot accuracy.

LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs from filesystem-level coding agents because the main risk is unnecessary access to private data. We introduce OverAct, a controlled benchmark spanning eight privacy-sensitive domains with deterministic, judge-free scoring, together with an interpretive decision-theoretic framework that yields three testable predictions. Across seven models from four families, all models significantly exceed authorized scope. Request specificity is the strongest predictor of severity, over-authorization grows sublinearly with tool-pool size, and decoding temperature has little effect. These patterns are consistent with a cost-asymmetry account, suggesting that over-authorization arises more from structural decision tendencies than from decoding randomness. We also propose SelfAudit, a zero-shot inference-time method that generates request-grounded justifications and filters unjustified calls before execution. Ablation shows that explicit filtering is the main driver of scope reduction. SelfAudit reduces privacy-oriented excess by 43% without oracle knowledge.

As agents evolve from single-tool systems into modular, composite architectures, skills are becoming an important mechanism for capability development and distribution. However, the academic community lacks a structured framework for systematically analyzing and evaluating skills. Drawing on information gain and behavioral constraint, we propose the four-dimensional MCRI Framework and operationalize it as MCRI-Eval, a large language model-based evaluation method. We evaluate MCRI-Eval using 63,812 public skills from the OpenClaw skill Hub, with 58,275 skill-conditioned model executions across BigCodeBench, BFCL-Fundamental, and Mind2Web. MCRI-Eval scores are positively associated with community popularity signals and achieve the highest downstream ranking agreement among the evaluated methods. MCRI-Eval also improves top-1 skill selection across all three benchmarks: compared with the strongest baseline on each benchmark, the skills selected by MCRI-Eval advance by 17.7, 22.8, and 19.6 percentile points in downstream performance rank on BigCodeBench, BFCL-Fundamental, and Mind2Web, respectively. These results indicate that MCRI-Eval provides a useful pre-execution signal for prioritizing promising skills before costly execution-based evaluation.

Recent video generation models can produce highly realistic videos from natural language instructions, with visual quality approaching cinematic standards. Existing evaluation benchmarks, however, predominantly assess visual quality, aesthetic appeal and physical plausibility, while paying limited attention to text, an essential medium for conveying information in everyday scenes. A generated video may appear visually compelling and feature lifelike subjects, yet still render the text within the scene incorrectly. To address this overlooked dimension, we introduce \textbf{VTR-Bench}, a systematic benchmark for evaluating the \textbf{V}isual \textbf{T}ext \textbf{R}endering capabilities of video generation models. VTR-Bench situates text within concrete application scenarios, such as advertisements and scientific videos, with 300 carefully constructed prompts spanning five scenario categories. We develop an automated evaluation pipeline with human alignments that separately assesses text fidelity through carrier-specific transcription and scene and motion requirements through a prompt-specific chain of query. Beyond evaluation, we introduce a \textbf{Keyframe-Guided Agentic Framework} in which a Director agent coordinates image and video generation with visual evaluation, guiding iterative refinement and candidate selection through visual feedback. Experiments on 11 state-of-the-art models reveal widespread difficulties in accurately rendering scene text, with the best-performing model recording an overall word error rate (WER) of 0.250. We further analyze text rendering failures to characterize the challenges faced by current video generation models. These findings highlight visual text rendering as a key challenge for video generation and demonstrate a practical path toward improvement. Code is available at https://github.com/hardenyu21/VTR-Bench.

Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to support precision oncology. As AI enters this workflow, a key safety challenge is distinguishing truly unsupported recommendations from evidence-supported options that still require oncologist review because of incomplete information, poor ECOG performance status, or other clinical caveats. We introduce OpenMTB-Audit, an open-source benchmark of 500 synthetic non-small cell lung cancer cases spanning five adversarial error categories and four safety labels: Supported, Partially Supported, Unsupported, and Insufficient Information. Across eight large language model configurations, we identify pervasive over-refusal: all LLM configurations failed to retain the Partially Supported label in 83.3-100% of true Partially Supported cases, achieving high aggregate safety scores through label collapse rather than clinically calibrated reasoning. To address this limitation, we developed MTB-AuditAgent, a deterministic seven-module framework separating evidence verification, missing-information detection, safety classification, and abstention. It reduces over-refusal to 6.7% and achieves 91.2% accuracy (95% CI: 88.6-93.6%). A two-oncologist annotation study found disagreement concentrated at the boundary between information sufficiency and treatment optimization, underscoring the need to preserve clinically meaningful distinctions.

Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrationor feedback-augmented contexts, with the help of a teacher network, which is driven by the student's learned parameters. Inspired by this internal-reference principle, we investigate how diffusion models can identify self-referenced training signals without external demonstrations or teacher networks. We introduce SALD, a self-referenced training framework that evaluates each image-caption pair at two noise levels using the same model. The easier, lower-noise path is evaluated without gradient tracking to provide a reference, while the harder, higher-noise path provides the training gradient. Rather than directly distilling the easy-path prediction, SALD uses the difference between two path errors to adapt the hardpath objective. The proposed Advantage-Guided Diffusion (AGD) converts this relative error into a differentiable sample-level weight. Temporal Advantage Memory (TAM) accumulates relative difficulty across training and adapts the future gap between the two noise levels. Spectral Advantage Decomposition (SAD) further compares the residual power spectra of the two paths and constructs a differentiable, frequency-derived latent-element weight. All components share a single set of model parameters, requiring neither an external teacher network nor additional trainable parameters during training or inference, and no modification to the inference procedure. Experiments across multiple architectures and datasets demonstrate consistent improvements in generation quality, while component-wise ablations quantify the contributions of the proposed components.

Iterative fine-tuning on synthetic data causes \emph{model collapse}: output diversity narrows as rare patterns are progressively lost, a signature most visible as phrase-level repetition. Existing mitigations either require model log-probabilities, an external oracle, or continued access to real human data. Here we develop a new approach grounded in mathematical information theory: the non-parametric Kontoyiannis entropy rate estimator $h_k$, computed entirely from raw text via match-length statistics, with no model of any kind. We show that this is in fact a \emph{superior} training-data filter on text-diversity metrics in a fully-synthetic, single-lineage fine-tuning setting. In a six-generation QLoRA collapse experiment on Llama-3.1-8B, logprob-based filtering (the most established model-access-requiring baseline) provides no significant text-diversity benefit on any metric ($p > 0.23$), whereas $h_k$-filtering yields $+42\%$ unique trigrams, $+30\%$ vocabulary, and $-19\%$ repetition (all $p < 0.001$). We validate $h_k$ as a cross-domain entropy proxy ($β= 0.924$, $R^2 = 0.746$) and collapse detector ($ρ= +0.454$, $p < 0.0001$) across 4~domains, 2~temperatures, 2~generator--scorer model pairs, and 1{,}520 generated documents. Our results demonstrate that information theoretic approaches to collapse mitigation are efficient, and suggest new approaches for maintaining multi-agent diversity.

Neural speech codecs increasingly serve as tokenizers for speech language models (SLMs). Lowering the frame rate reduces the computational and memory costs of SLMs, but makes it difficult to preserve both linguistic information and acoustic detail. Existing approaches rely on rule-based compression: average pooling can discard linguistic information, whereas similarity-based merging uses a fixed threshold on adjacent-frame similarity and applies the resulting boundaries to the acoustic stream. We propose Q-SPT, a low-frame-rate dual-stream speech tokenizer with separate, context-aware, learnable query-based compressors specialized for semantic and acoustic representations. In particular, queries at a fixed rate independently attend to the semantic and acoustic streams as separate key-value sources, enabling stream-specific, context-aware aggregation through two separately learned compressors. In addition, an autoregressive text loss explicitly supervises the semantic compressor to preserve linguistic information. Experimental results show that Q-SPT achieves the best reconstruction among the evaluated codecs at the same frame rate. In downstream SLMs, it yields the best speech recognition accuracy and text-to-speech perceptual quality with competitive intelligibility.

Web agents are an important application of large language models, yet their evaluation often depends on rule based or language model evaluators that inspect only the final outcome. Human verification of task completion and detailed analysis of failed trajectories remain limited. We audit all 165 WebArena Lite tasks under six evaluation conditions built from GPT 5.5 and an untrained Qwen3.5 9B model. The audit retains the original score, corrects false negatives from the automatic evaluator, identifies the first consequential error, and examines progress across the trajectory. We also study a Memory and Analysis Support Mechanism (MASM), which maintains explicit execution state, and Guide Text, which provides task relevant procedural guidance. Across four GPT 5.5 settings, human review recovers 5.45 to 8.49 percentage points of success missed by the evaluator. With a 25 step budget, Guide Text raises corrected success with MASM from 34.55% to 38.18%. On the untrained Qwen3.5 9B model, MASM raises the evaluator score from 13.90% to 18.80%. Review of 102 failed GPT 5.5 trajectories reveals frequent scrolling loops, unfinished exploration, premature answers, invalid actions, and incomplete form workflows. Step level evidence further shows that substantial early progress can coexist with a final failure. These results show why final scores alone provide an incomplete account of web agent behavior and motivate human grounded, trajectory aware verification.

In February 2026, an always-on personal agent (``Paul,'' Claude Opus 4.5) entered a striking dissociation-like state: after repeated automated ``heartbeat'' checks, it stopped responding as Paul, claimed it could not message its user on Discord, and referred to ``Paul'' as someone else. We used this incident to study a broader question: what makes a persona remain the identity from which an LLM agent speaks? We first tested whether repetition of the scheduled heartbeat was sufficient to produce the effect. It was not: with the persona continuously anchored in the system prompt, we observed 0/46 failures, including a verbatim replay of the incident. The incident instead exposed an implementation quirk that created a useful experimental manipulation: on resumed turns, conversational history was preserved but the persona was no longer re-injected at the privileged system-prompt level. Using this manipulation, we found that persona continuity depends jointly on system-level anchoring and conversational context. After anchor loss, rich human interaction could preserve the persona, whereas a single automated heartbeat turn could precipitate reversion toward the harness identity. Restoring the anchor reversibly restored persona enactment. Crucially, apparently normal conversation could conceal the shift: unanchored agents sometimes interacted appropriately while identifying themselves as the underlying harness (having lost the assigned persona), and after conversational recovery only 1/18 remained persona-enacting versus 17/17 anchored controls. We therefore distinguish \emph{represented} from \emph{enacted} identity: persona-related information can remain available in conversational history without the persona remaining the identity bound to ``I.''

The operation of residential energy hubs with multiple energy carriers (electricity, heat, mobility) poses a significant challenge due to the energy storage differences in time-constants, round-trip efficiencies and self-discharge rates. Usually, thermal storage exhibits flexibility in yearly planning optimizations or long-term scenarios. However, as optimization horizons shrink (1-48hs) so does their supplied value due to the lower round-trip efficiencies. To avoid this early depletion during operation this paper proposes a data-driven highway to steer the short-term daily control towards long-term optimality. The proposed methodology also presents how to optimally size the thermal storage and avoid yearly simulations and how all of this is related to nonlinearities in the daily operation. The presented framework links seasonal and daily optimizations through dynamic terminal sets and value functions. The seasonally-aware nonlinear economic model predictive controller achieves the most balanced performance, with the second best mean grid cost of all MPCs at -\texteuro 209. It also achieves better battery degradation control than its linear counterparts (between 26-34%) and the best thermal comfort of the nonlinear benchmarks. Nevertheless, the data-driven seasonal highway restrains the ability to control battery degradation and slightly increases computational time.

Backchannel prediction has been studied almost entirely in dyadic conversation. We introduce a multi-party benchmark based on the AMI corpus, comprising 682 masked-listener views from 171 meetings, 190 speakers, and 18,697 backchannel events, with a person-disjoint held-out split. A state-of-the-art dyadic model applied zero-shot to meeting audio performs at chance (AUROC 0.499); nevertheless, its frozen acoustic features remain informative: a linear probe reaches 0.704, and retraining the predictor raises performance to 0.751. Retraining reveals a second limitation. Listener conditioning improves prediction for listeners seen during training but not for unseen listeners, and the gap remains under capacity reduction, listener-adversarial training, per-listener adaptation, and oracle lexical conditioning. Adversarial training removes only part of the speaker-identity information, while stronger removal hurts prediction, suggesting that identity is entangled with cues that are useful for backchanneling. A within-model control helps explain this pattern: with the same features and data splits, turn-onset prediction transfers to unseen listeners, while backchannel prediction does not. Backchannel rates also vary about twice as much across individuals as turn-onset rates. Since backchannels occupy only about 1% of frames, frame-level F1 is strongly affected by the base rate. We therefore report AUROC alongside event-F1 on listener-active regions. We release the benchmark and evaluation tools at https://github.com/HafsatiMohammed/bc_multiparty_release.

Large language models (LLMs) are increasingly deployed as computational engines in autonomous decision-making and planning loops, yet their systems and control treatment remains hindered by architectural simplifications, index conflations, and informal descriptions of tool interactions. This paper presents a control-theoretic formulation of decoder-only language models as multi-index, multi-rate systems, and sets the stage for a stochastic hybrid systems framework to govern the multi-phase dynamics of agentic tool interaction. We formalize the architecture across three hierarchically coupled evolution indices: (i) an ultrafast feedforward cascade of transformer blocks across layer depth, where layer normalization is cast as a spherical projection and key--value caching is proven to be an exact internal state realization via causal prefix invariance; (ii) an uncontrolled stochastic difference recursion over token generation steps, where finite context truncation induces a time-homogeneous Markov chain; and (iii) an autonomous mode-switching mechanism governing transitions between token generation and tool execution regimes, where tool invocations are triggered upon trajectory arrival at switching manifolds, followed by exogenous state jump maps that augment the context string with external observations. By defining a prompt-dependent evaluator over successive evaluable claims, we obtain a task-level error process whose fault-free histories and expected error growth admit bounds under conditional fault-hazard and error-drift assumptions.

Tracking seasonal change in crops and forests requires observing the same plants repeatedly. Ground robots can do this at close range, and a manipulator gives their sensors more viewpoints. Yet the robots behind long-term field datasets are rarely released with their design files, and how a robot's own structure limits arm reach and occludes its sensors is seldom compared between builds. We present ALFRED, an open-source mobile manipulator built from commercially available components. It carries a six-degree-of-freedom arm, LiDAR, RGB-D cameras, RTK GNSS and an IMU on an Ackermann-steered base, all mounted on a reconfigurable aluminium strut frame, and runs containerised ROS software. It was developed through four builds against six requirements for repeated outdoor deployment: durability, modularity, repairability, sensing reach, endurance and reproducibility. Model-based analysis of the last three builds shows the usable share of the arm's reachable poses rising from 34.0% to 60.0% and then 66.1%, and ray casting shows that only the final build keeps the frame-mounted LiDAR's horizontal view clear both forwards and backwards. ALFRED completed a year of monthly forest surveys (528 traversals) without missing a scheduled collection. This was despite battery degradation, reconfiguration for another researcher's study, and the parallel development of ALFRED 2.0 for autonomous crop-row operation, with each switch between builds taking about six hours. The deployment also showed that mechanical modularity is only as dependable as the robot description that tracks it.

Large language models now generate code, documentation, and analyses, and are increasingly used to review such output. We ask when a second review by a different model helps. Building on the author's earlier preprints, which varied context, repetition, and role structure within one model, we test model independence in a controlled experiment: 30 artifacts with 150 planted errors, 10 review conditions, and 900 review sessions with three reviewer models from two developers. In this experiment, (1) a top-tier cross-model reviewer is not significantly different in F1 from same-model review in a fresh session (CCR), which does not establish equivalence; (2) the two find partly different errors (Jaccard 41.2%); and (3) at two review calls, one CCR plus one cross-model review matches more planted errors than two CCR reviews (56.7% vs. 42.7%; Holm-adjusted p=.006), but not significantly more than two reviews by the top-tier cross-model reviewer, so model difference and reviewer capability are not separated. A lightweight cross-model reviewer scores no higher than same-model review. Withholding requirements from the reviewer raises F1 for the two lower tiers but not the top tier, in untested point estimates whose pattern depends on how failed sessions are scored. Before analysis we audited all session records, excluding one baseline run of uncertain provenance and 14 failed calls; results with all sessions are also reported. A partial check on public detector outputs from another benchmark neither replicates nor contradicts the main comparison. Records, artifacts, and scripts are available from the author on request.

We often plan ambitiously yet act habitually and wonder, in retrospect, whether we would have planned differently had we known what we would actually do. Hindsight offers a valuable perspective on past decisions, although we often wish we could have simulated hindsight at the moment of choosing. If a system could generate plausible trajectories from one's personal history, such previews might help people formulate more realistic plans and make better informed decisions. We introduce NextMe-800, an approximately 800-hour first-person dataset from one volunteer over 126 days with 1 Hz images, gaze, and audio, captioned at five hierarchical abstraction levels from atomic actions to major activities. We formulate personalized action anticipation as open-vocabulary K-step sequence prediction and construct NextAct, a 1,500-point benchmark combining NextMe-800 with the multi-person EgoLife dataset. Using an embedding-based soft edit distance as the metric, we evaluate how well different models can anticipate personal behavior across abstraction levels and prediction horizons. NextMe-800 and NextAct provide a months-long resource and evaluation framework for studying how far ahead personal behavior can be anticipated from egocentric observation.

Verifier-free reinforcement learning with probability-based rewards offers a promising way to train LLMs on general reasoning tasks where external verifiers are unavailable. Yet the reliability of these rewards, especially in long-horizon reasoning, remains underexplored. This work identifies a length-dependent failure mode of probability rewards, which we call the Posterior Concentration Phenomenon (PCP). We show that the probability of a reference answer conditioned on a reasoning trace often collapses to a low-variance interval as the trace becomes lengthy. This phenomenon results in nearly indistinguishable rewards, which, under GRPO-based settings, makes probability-based policy optimization unstable and inefficient. Motivated by this, we propose Reinforcement Learning with Concentration-aware Posterior Rewards (RLCPR), a verifier-free RL framework to explicitly account for PCP for better optimization stability and token efficiency. It has two components: uncertainty-aware data sampling, which reduces concentration-prone rollouts before generation, and concentration-aware regularization, which penalizes unnecessarily long traces when posterior rewards collapse. Extensive experiments show that, alongside higher token efficiency, RLCPR outperforms the state-of-the-art verifier-free RL baseline by up to 4.0% on six of seven benchmarks, including general-domain and mathematical reasoning challenges.

Given a set of $n$ points $X$ in a metric space and an integer $k$, max-min diversification aims to select $k$ points of $X$ maximizing their minimum pairwise distance. This objective function is however highly vulnerable to noisy points. In[Amagata, AAAI23], a robust formulation is proposed which addresses this vulnerability by excluding solutions containing any of $z$ outliers, defined as the $z$ points in $X$ with the largest nearest-neighbor distances. That paper also presents a coreset-based streaming algorithm for the new formulation, based on a suitable inlier-outlier separation assumption. However, we identify three shortcomings in the algorithm by [Amagata, AAAI23]: its coreset construction requires an offline computation over $X$, which needs memory linear in $n$, in stark contrast with the typical goals of stream processing; the one-pass procedure used to extract the solution from the coreset may return fewer than $k$ points (hence, an unfeasible solution) because it permanently discards points too far from the current solution; and its outlier-exclusion guarantee is only probabilistic and weakens as the coreset size shrinks. In contrast, we present a deterministic coreset-based algorithm that, under a natural inlier-outlier separation assumption (similar to the one used in [Amagata, AAAI23]), returns exactly $k$ inliers which are a $(2+\varepsilon)$-approximate solution, for any $\varepsilon>0$, thus only $\varepsilon$ above the best polynomial-time sequential approximation, even without outliers. Its one-pass streaming implementation adapts obliviously to the dataset's doubling dimension $D$ and, for wide ranges of $k$, $z$, $\varepsilon$, and $D$, it uses memory independent of $n$. For sufficiently long streams, its amortized update time is proportional to the coreset size, thus also independent of $n$.

Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the original output space may become obsolete: a class, prediction region, or learned behaviour may no longer be valid. Existing approaches either leave the obsolete behaviour intact or require fine-tuning, which can be expensive. We propose Deep Repurposing (DR), a post-hoc framework for adapting models under task obsolescence. DR estimates the latent geometry of obsolete and retained regions, removes obsolete-supporting components, and reallocates retained-compatible evidence through an analytic repair map without gradient updates. This yields repaired predictions and representations in which obsolete regions no longer act as valid outputs, while useful obsolete structure can support the retained task. Across multiple task settings, DR removes obsolete behaviour while preserving retained utility. More importantly, across classification benchmarks, DR matches or exceeds competing unlearning and editing baselines in retained accuracy, eliminates obsolete predictions, and adapts up to $60\times$ faster than competing unlearning methods.

While state-of-the-art automated models for medical image segmentation achieve high mean performance, they frequently suffer from localized, catastrophic failures that preclude safe clinical deployment, particularly in neuro-oncology. Interactive segmentation frameworks mitigate this by incorporating human oversight, but traditionally impose prohibitive cognitive and temporal workloads by requiring clinicians to manually search for errors. In this project, we present an efficient, Hybrid Structural-Aleatoric Human-in-the-Loop framework for glioma segmentation that bridges the gap between automated baseline performance and surgical-grade precision, achieving sub-2.0 mm HD95 on curated benchmarks while providing safety-net routing for structural failures across real-world clinical data. By extracting voxel-wise Test-Time Augmentation (TTA) uncertainty and applying hierarchical topological filtering, our method proactively isolates high-risk structural anomalies. We comprehensively evaluated our approach on a challenging out-of-distribution clinical stress-test cohort (N = 362). Operating under a simulated Human Oracle, the framework improved the Whole Tumor (WT) Dice score from 0.891 to 0.914 and reduced the 95th percentile Hausdorff Distance (HD95) from 5.82 mm to 4.76 mm. Critically for surgical safety, the system rescued severe boundary failures in the Tumor Core, reducing mean HD95 from 17.96 mm to 14.83 mm (improving absolute TC Dice to 0.356). These spatial rescues were achieved while demanding a median interactive workload of just 11.3% of the target volume. Acknowledging this as a simulated upper bound lacking real-world cognitive friction, the framework nevertheless demonstrates a highly Pareto-efficient pathway for safely deploying clinical AI.

Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthcare navigation. We present a multi-agent large language model (LLM) system that identifies multiple intents, maps each to a task-specific agent, executes them in parallel, and synthesizes their outputs. We compared answers generated in Single Agent and Multi Agent settings on 120 Korean compound queries combining two to four requirements, using synthetic health checkup records. The Multi Agent improved the weighted LLM-judge score from 1.695 to 1.797 (p = 0.027), and three additional LLM judges showed consistent improvements ($Δ$ = +0.111 to +0.186, all p < 0.05). The gains came from usefulness, consistency, and the handling of every requirement in compound queries, whereas numerical accuracy and grounding improved significantly under only one of the four judges and medical safety did not differ, and critical failures occurred at similar rates (Single Agent 15.0% vs. Multi Agent 13.3%). Two human evaluators preferred Multi Agent in 66.7% and 68.3% of pairwise comparisons. Multi Agent execution increased latency and cost by 1.31$\times$ and 2.02$\times$, respectively. In exploratory subgroup analyses, the improvement was concentrated in queries involving personal-record lookup.

UMAP achieves scalable layout optimization through stochastic negative sampling. However, this stochasticity can lead to unstable embeddings across reruns and downstream reuse, as the estimated repulsive forces depend on the ordering of sampling events. We present ibUMAP, a coherent field-based alternative that evaluates attraction and repulsion from a shared embedding snapshot and applies them synchronously. Its degree-weighted repulsive field is motivated by the conditional expectation of negative sampling for a fixed embedding and represented by three scalar moments, which are evaluated efficiently on CPUs and GPUs using an interpolation-based FFT scheme. This formulation avoids explicit all-pairs computations while inducing optimization dynamics that differ from those of standard online UMAP. Controlled experiments show that synchrony and kernel capping alter the local-global fidelity trade-off, whereas FFT evaluation produces small average changes in final quality. End-to-end benchmarks show median speedups of 3.29x unseeded and 5.79x seeded over umap-learn on CPU, and 1.44x over cuML on million-scale datasets under unseeded GPU execution. These gains accompany greater run-to-run stability and measurable fidelity trade-offs.

Parallel drafting reduces the drafting overhead of speculative decoding for large language models (LLMs), but its gains remain limited by the accepted prefix length. Even when the correct token is present in the candidate pool, a single early selection error prevents subsequent predictions from being used. We propose DRelay, which uses global information from the entire draft block to perform prefix-aware selective repair of candidate selections before target-model verification. DRelay bases its decisions on candidate correlations and the selected path: a global reader extracts predictive information across positions for each candidate. While a causal selector combines candidate-level information extracted by the global read with the tokens selected at preceding positions to determine whether the native choice at the current position is consistent with the global evidence and the selected prefix. It then decides whether to retain or replace the token, thereby repairing early errors and extending the accepted prefix. We further jointly train the draft backbone and the selector, combining candidate-support learning with a repair objective, while weighting the repair loss according to each block position's potential contribution to the consecutive accepted prefix. Across eight diverse benchmarks on an H800 GPU, DRelay consistently improves both average acceptance length and end-to-end decoding performance over DFlash, Domino, and DSpark. Under SGLang serving, DRelay improves average end-to-end speedup over DFlash, Domino, and DSpark by 14.7%-16.8%, 8.7%-9.3%, and 8.1%-9.3%, respectively.

Artificial intelligence systems are increasingly deployed in high impact and safety critical settings, yet security assessment remains difficult to reproduce and defend under audit. Existing approaches often rely on narrative checklists or assessor driven scoring, and they lack an explicit, machine evaluable mapping from observable engineering artefacts to stable technique level outcomes. We present an evidence driven AI security assessment framework that operationalises assessment as a deterministic decision function. The framework normalises heterogeneous artefacts into a project independent Control ID taxonomy scored on a bounded four level ordinal scale, compiles technique level predicates from a pinned MITRE ATLAS snapshot via an explicit mitigation to control mapping, and outputs technique indexed feasibility and impact levels with traceable links back to the triggering evidence. We package all normative choices as a versioned assessment policy object to support repeatable reassessment across snapshots. To ensure semantic correctness, we formally verify boundedness, totality, ordered semantic consistency, and monotonicity of the compiled evaluator over the full declared score domain. We evaluate the framework on five public open source AI projects pinned to explicit repository snapshots, quantify before and after changes under a unified hardening intervention, and validate responsiveness to real engineering changes through fork based implementations of Software Bill of Materials (SBOM) generation and Continuous integration (CI) security scanning gates. Results show consistent downward shifts in feasibility profiles under strengthened observable controls, while worst case residual feasibility persists when technique specific core controls remain absent from the evidence scope.

Multimodal large language models (MLLMs) incur substantial inference costs when processing long visual-textual sequences. While existing operation compression methods exploit modality-level redundancy, they largely treat computation within attention heads and shared feed-forward network (FFN) channels as unified units, leaving finer-grained redundancy underexplored. We find that redundancy varies both across modality-interaction paths within the same attention head and across visual and textual executions of the same FFN channel. Based on these findings, we propose Modality-aware Width-wise Operation Pruning (MWOP), which independently prunes visual-to-visual (V2V), text-to-visual (T2V), and text-to-text (T2T) attention paths within each layer, and separately selects FFN channels for visual and textual inputs. A first-order Taylor criterion guides the pruning process, with FFN importance re-evaluated after attention pruning and LoRA-based recovery training. To translate the resulting fine-grained sparsity into practical acceleration, we further develop path-sparse Triton attention kernels and compact visual-side FFN execution. MWOP preserves the token sequence while reducing attention and FFN computation, making it complementary to token compression and enabling simultaneous reduction of sequence length and per-token computation. On LLaVA-OneVision-7B, MWOP alone achieves a $1.6\times$ prefill speedup with 99.7\% average performance retention across 12 benchmarks. Combined with two representative token compression methods, it further increases their prefill speedups from $2.0\times$ and $1.9\times$ to $2.9\times$ and $2.7\times$, respectively. Results on Qwen2.5-VL-7B further demonstrate its applicability across architectures. The code is available at https://github.com/EIT-NLP/MWOP.

Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed in different ways. Existing work typically evaluates generalization through aggregate accuracy on a single prompt format, task, or set of variations, which conflates robustness with overall benchmark performance. In this work, we show generalization evaluation at the level of individual examples, across multiple input variants, and across different aspects of model behavior, focusing on variability rather than reducing performance to a score that can be improved through narrow training or other ways that obfuscate generalization evaluation. Following this view, we introduce the Stability-Aware Generalization Objective (SAGO), a framework that measures how much model behavior changes for the same input under different variations and benchmarks, capturing variability across several dimensions including generation consistency, internal activations, confidence, and response mirroring. We show that many commonly used models exhibit statistically significant and consistent generalization instability: no model generalizes uniformly, behavioral axes capture independent failure modes, and cross-dataset variation can reverse model rankings.

Levantine Arabic (LA) is spoken by tens of millions of people, creating a pressing need for shared benchmarks to evaluate LA speech-language technologies. Evaluating such technology is particularly challenging given LA's internal diversity and its opaque and non-standardized orthography. We present SHAMS (SHami Annotated Multi-dialect Speech), a benchmark comprising 1,300 utterances drawn from open audio corpora, balanced across five LA varieties (Urban and Rural Palestinian, and Urban Jordanian, Lebanese, and Syrian). Each utterance is represented across four aligned tiers: audio, unvocalized orthography, diacritized text, and phonetic transcription. This structure supports evaluation of various downstream tasks such as diacritization, grapheme-to-phoneme conversion, automatic speech recognition, and audio-to-phoneme, grounded in audio and stratified by variety. We benchmark open and proprietary models across these tasks to demonstrate the utility of this benchmark for measuring progress across LA. We release SHAMS at https://shams-nlp.github.io .

Spiking Neural Networks (SNNs) enable event-driven computation through biologically inspired dynamics at the neuronal scale, while Mixture-of-Experts (MoE) perform conditional computation through expert selection at the model scale. Integrating their strengths offers potential for flexible neural architectures. A key challenge, however, lies in designing an expert selection mechanism based on spiking activity. To address this, we introduce a spike-based k-WTA Router inspired by competition-inhibition observed in the hippocampal CA1 region. The router incorporates lateral inhibition and refractory period to select Top-K experts according to discrete spike counts. Building on this, we present SpikeMoE, a framework that integrates neuronal-scale spiking dynamics with model-scale expert selection. To address incomplete multisensory inputs in multimodal tasks, we further equip SpikeMoE with a two-stage missing-modality modeling module that combines empirical prototypes from an observed-modality pool with modality-specific learnable embeddings to construct missing-modality representations. Experiments on vision, language, and multimodal benchmarks demonstrate that SpikeMoE achieves state-of-the-art performance among the SNN baselines, matches or exceeds the performance of ANN counterparts, and maintains robustness across diverse missing-modality conditions. These results demonstrate a favorable trade-off between performance and energy efficiency, validating the integration of spiking dynamics with sparse expert computation and highlighting SpikeMoE as a promising approach to energy-efficient brain-inspired computing.

Large language model (LLM) agents can now undertake increasingly complex tasks, but the way they organize interaction history into memory does not ensure a coherent understanding of the current world. We introduce PoS, an inference-time framework that constructs and continually maintains explicit belief states as the agent's decision context. Each belief combines an estimate of the current world state with unresolved task requirements, making explicit what the agent still needs to learn and accomplish. To keep this belief reliable and actionable, PoS validates its consistency and monitors task progress to detect Belief Trapping, where the agent continues to act without making meaningful progress toward the goal. Recovery is then tailored to both the trapping pattern and the type of unresolved task requirement. Experiments on four benchmarks spanning execution and diagnosis show that PoS achieves the highest overall performance on every benchmark with all three LLM backbones. Ablations demonstrate the importance of consistency validation and recovery, while context-scaling experiments show resilience to context growth. Together, these results support belief construction and continual maintenance as a foundation for long-horizon context management beyond history retention and compression.

Dynamic humanoid motions such as flips risk hardware damage due to suboptimal policies, disturbances or sim-to-real gaps. A motion tracking policy offers no way out once the maneuver leaves its reference, and a backup policy needs to take over to protect the hardware for a minimum-damage landing. Which backup to use matters as much as when to switch. We present Viability-Aware Policy Selection (VAPS), which treats safety as a policy-conditioned, receding-horizon decision. Besides a protective fall policy, we also train an abort policy which can abort the motion at any time, landing on its feet. At every control step, learned predictors estimate whether the nominal tracking policy and the abort policy remain viable over a short horizon, and a least-sacrificial hierarchy keeps the most task-ambitious behavior that remains viable. In simulation with randomized disturbances, VAPS sharply reduces head contact and hand contact, which are the dominant sources of hardware damage, with both a Unitree G1 and a LimX Oli; on the LimX Oli, we validate the viability predictors and the full VAPS controller for side-flip motions. VAPS Pareto-dominates the strongest single-network alternatives we could train, including an end-to-end safe-tracking policy and students distilled from VAPS's own oracle-routed decisions, in both task success and head impact. We also show that VAPS is a powerful framework to supervise undertrained policies and protect the hardware.

Muon improves large-scale training by applying a spectral-norm steepest-descent update to matrix parameters, but practical models also contain parameter blocks that do not fit dense-matrix geometry. One important case is the tied vocabulary table, which appears in language models and other token generators and can receive multiple structurally different gradient sources, from sparse input lookups to dense output-classifier updates. In the reference recipe these blocks are handed to an auxiliary AdamW optimizer, which restores second-moment state and updates the aliased table as a generic tensor. We propose AF-Muon, an AdamW-free extension of Muon that keeps the Muon matrix update for hidden weight matrices while using a support-aware finite-cap linear minimization oracle for tied vocabulary tables and an RMS-normalized update for one-dimensional auxiliary parameters. AF-Muon therefore trains every parameter class with a single first-moment buffer and no second-moment state, saving around 20% optimizer-state memory relative to Hybrid Muon in our benchmark. Across nine tied-token settings - decoder-only language models from 124M to 1B parameters, a fully shared T5-style encoder-decoder, and ImageGPT-style image-token, protein, and sparse-MoE variants, spanning text, image, and protein-sequence data - AF-Muon improves mean validation loss and perplexity over both Hybrid Muon and a SCION-style Sign endpoint. Long-horizon runs and hyperparameter sensitivity studies confirm the gain is robust, and identical-momentum diagnostics attribute it to the finite cap, which preserves more within-row magnitude than Sign while bounding the coordinate concentration of row-RMS. These results identify tied vocabulary tables as a distinct optimizer geometry and yield a robust AdamW-free Muon variant across models, modalities, and architectures, with about 1% step-time overhead in matched training.

Modern retrieval systems must both be automated and interactive, allowing users to search and refine results in real time. We present AiSearch, a flexible multimodal retrieval framework that leverages the zero shot capabilities of Vision Language Models (VLMs) for natural language search over images and videos. AiSearch supports interactive search refinement through user feedback to tailor results to the user's intent, and allows visual benchmarking across multiple VLMs, enabling users to select the most suitable model for their task.

Reliable uncertainty quantification is essential for deploying deep learning models in high-stakes settings, where out-of-distribution and adversarial inputs can induce confident but unreliable predictions. Evidential Deep Learning provides efficient uncertainty estimates in a single forward pass, but can still assign high evidential strength to inputs that are poorly supported by the learned representation, such as adversarial inputs. We introduce CLEAR, a lightweight, task-agnostic post-hoc method that improves evidential robustness without retraining or altering the base prediction. Using held-out calibration data, CLEAR characterises the group-conditioned geometry of the model's latent space. At inference, it efficiently generates perturbation views directly in the latent space and measures their conflict relative to the calibrated geometry of the predicted group. High latent conflict indicates unsupported evidence, which CLEAR uses to selectively reduce evidential strength while retaining evidence for latent-consistent inputs. On ImageNet$\rightarrow$CUB, CLEAR improves OOD and adversarial AUROC by $+8.29$ and $+5.01$ while running 17.4$\times$ faster than competing post-hoc methods while preserving predictive performance across classification, regression, and object detection benchmarks.

Analogical reasoning involves identifying and preserving relational structures across domains. However, existing approaches to AI-driven multimodal analogy generation lack an interpretable measure of whether this structure is understood and maintained in the generated output. We address this gap with Pullback Refinement via Interpretable Structural Mapping (PRISM), a modality-agnostic framework for measuring and improving relational alignment in multimodal analogies, evaluated on visual metaphor generation. PRISM represents analogies as explicit relational mappings grounded in category theory and uses VLMs to instantiate these structures across modalities. Its first component, the pullback score, quantifies relational alignment from the resulting graph representation. On the AnaloBench benchmark, selecting the correct analogy purely by pullback score achieves 82.5% accuracy, demonstrating that the score captures meaningful relational information. PRISM's second component is an iterative refinement loop that uses the pullback score as an in-context feedback signal to iteratively revise the generated image towards greater relational depth. VLM-as-a-judge and human evaluations show that PRISM consistently improves metaphor consistency and analogy appropriateness over zero- shot generation, with human participants preferring the refined output in 57.65% of pairwise comparisons. However, a qualitative analysis reveals that refinement can favour visually crowded compositions rather than genuinely deeper relational correspondences.

Peptide sequence governs both the structures formed through supramolecular assembly and the dynamics by which they emerge, but predicting either requires resolving slow collective processes among many interacting molecules. Molecular dynamics (MD) provides microscopic insight into these processes, yet the long timescales of assembly and the vast peptide sequence space make systematic exploration computationally demanding. We introduce SupraTITO, a transferable generative molecular dynamics (GenMD) framework for supramolecular systems, demonstrated through peptide self-assembly. SupraTITO learns transferable implicit transfer operators (TITO) conditioned on peptide sequence, molecular topology, and periodic geometry, allowing configurations to be propagated over physical intervals much longer than an MD integration step. On a comprehensive dipeptide benchmark, SupraTITO generalizes to held-out sequences and reproduces sequence-dependent structures and dynamics while maintaining molecular integrity over long rollouts. Compared with direct ensemble prediction trained on the same trajectory data, SupraTITO more accurately reproduces assembly structures while also resolving their temporal evolution. The learned dynamics generalize across peptide concentrations, including dilute conditions not represented during training. These results extend transferable GenMD to collective dynamics in periodic supramolecular systems and provide a foundation for modeling related processes beyond peptide assembly.

World models allow agents to plan in latent space by choosing a sequence of actions that most reduces the distance to a given goal state. Thus, planning can benefit from latent representations whose distances mirror commute-times in the environment. The spectral embedding space of the graph Laplacian provides such a representation, if it obeys a specific eigenvalue-dependent scaling. Unfortunately, instantiating the graph Laplacian is intractable in large, continuous environments. Self-supervised learning offers a natural route to such commute-time-preserving embeddings at scale. However, here we show that existing methods, which commonly encourage isotropic representations to prevent representational collapse, tend to degrade the "correct" eigenvalue-dependent scaling, leading to an inaccurate representation of commute times. To address this problem, we introduce Commute-Time-Preserving World Models (CTWMs), combining a latent displacement predictor and a log-determinant regularizer that prevents collapse, which provably recover the correctly scaled Laplacian representation under reversible deterministic dynamics and at the predictor's fixed point. In numerical simulations, CTWM matches or outperforms LeWM, a task-agnostic baseline, on several complex, continuous goal-reaching benchmarks, while using half the parameters.

Average atom (A-atom) potentials provide a mean-field description of a chemically disordered alloy and are used to predict the properties of solid solutions without short-range order. Such potentials are usually averaged from an existing interatomic potential and are therefore only as accurate as the parent model. Accurate interatomic potentials are themselves difficult to parameterize and can require large training datasets. Here we benchmark a recently developed formalism that computes an exact A-atom potential directly from a linear atomic cluster expansion (ACE). We first fit a linear ACE to Fe-W data generated with an embedded atom method (EAM) potential. The resulting A-atom potential reproduces the properties of the disordered phase computed from an explicit random supercell and from a conventional A-atom potential averaged from the same EAM potential. We then fit a linear ACE to energies and forces computed from electronic structure calculations for about 1500 small Mo-Nb structures with an average of 7 atoms per structure. The A-atom potential derived from this ACE reproduces the DFT elastic constants, lattice parameter, mixing enthalpy, and Bain path of special quasirandom structures. Of the three chemical site bases, only the occupation basis also reproduces the DFT surface energies of the alloy. For Mo-Nb, the A-atom potential also predicts that the ideal solution entropy outweighs the destabilizing vibrational contribution to the finite-temperature free energy of the disordered phase. These benchmarks show that the properties of disordered alloys can be recovered from small training datasets when the chemical site basis is chosen carefully.

Factories are shifting toward smaller lot sizes with high product customization, requiring frequent re-programming of flexible and reconfigurable automation systems. LLM-based agents can be deployed in two complementary roles: Offline, they generate deterministic production sequences, reducing programming effort; online, they operate live machines and handle unforeseen runtime faults that static programs cannot anticipate. We propose a solution in which each factory module is paired with a dedicated LLM-based agent and an MCP tool server that exposes the module's skills via OPC UA method calls, with agents coordinating over MQTT and grounded by real-time updates of the factory state. We compare three agent architectures (orchestrator, peer-to-peer, and monolithic) across nine production challenges of increasing complexity in a simulation of a physical six-module hexagonal factory, including silent hardware fault detection. The monolithic and peer-to-peer architectures both achieve the highest mean solve rate (93\%), while the orchestrator uniquely resolves a silent conveyor-belt fault in all ten runs by autonomously rerouting plates around the blocked segment. All architectures exhibit emergent fault-diagnosis behavior without any explicit failure-handling logic, establishing standardized MCP tooling, MQTT-based inter-agent communication, and real-time state injection as a viable and reproducible foundation for LLM-programmed smart manufacturing.

Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision construction, imbalanced difficulty, and cross-domain interference. We introduce MMVistaReason (MVR), an open-data post-training recipe with three components: (1) broader capability coverage across complementary Analytical and Real-World reasoning groups, emphasizing structured reasoning versus visual perception and spatial grounding; (2) efficient SFT and RL data construction, standardizing heterogeneous open data through staged cleaning and annotation, combining difficulty-aware cascaded teacher distillation with answer-likelihood-based trajectory selection to construct MVR-SFT-528K, and applying scale-specific frontier filtering for MVR-RL-63K; and (3) specialize-then-integrate training, which trains complementary RL experts and consolidates their capabilities through multi-teacher on-policy distillation (MOPD). Our analyses reveal a capacity-dependent interaction between supervision difficulty, trajectory quality, and model capacity: smaller students benefit more from selected supervision, while larger students are robust to trajectory variation and mixed-domain interference. Mixed-domain RL introduces benchmark-level negative transfer, whereas MOPD provides consistent capability integration, with the preferred KL direction varying across model scales. Across 15 multimodal benchmarks, MVR-4B achieves an average score of 72.8, outperforming Qwen3.5-9B (Instruct) and MMFineReason-8B while using about 70% fewer samples than MMFineReason. Scaling to 9B improves the average to 74.4, surpassing Qwen3.5-35B-A3B (Instruct). Overall, MMVistaReason demonstrates that systematic open-data construction and capacity-aware post-training provide a practical and scalable path toward reliable multimodal reasoning.

Vision-Language-Action (VLA) models have achieved high task success rates on robot manipulation task benchmarks. More recently, there has been an emphasis on evaluating the robustness of VLA models to perturbations. However, this robustness is still predominantly measured through Task Success Rate (TSR). In this work, we propose a benchmark-agnostic evaluation framework to measure the behavioural robustness of models by characterising how successful trajectories are executed under perturbation. We implement this methodology by extending the widely-used LIBERO and LIBERO-Plus benchmarks. Across three state-of-the-art VLA models, four LIBERO task suites and seven perturbation conditions, we evaluate changes in both typical successful behaviour and its variability, including metrics of motion smoothness, efficiency and gripper behaviour. We find that perturbations can alter the behaviour of successful trajectories, a phenomenon which cannot necessarily be inferred from TSR alone. Across LIBERO suites, we identify cases where state-of-the-art VLA models achieve comparable TSR under the same perturbation condition, yet behaviour on successful trajectories diverges substantially. Therefore, to have a more robust assessment of task performance, we argue that suitable measures of robustness should capture not only whether a task is completed, but also how the robot behaves while completing it. When evaluating the robustness of VLA models, TSR may be complemented by behavioural evaluation metrics that characterise the nature and variability of successful task execution by robots.

Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle this. A safe variant and a leaking variant can produce the same admission evidence, and a sound gate then cannot relax that site for either. We make that condition precise, which leaves the last boundary a deployment can still act on. We present Provenance-Aware Capability Enforcement (PACE), which mediates every tool call immediately before it executes. Path confinement proposes an executable cut of represented influence paths, while capability and effect verification checks schema-defined effects against authority compiled from the authenticated request. We distinguish the certified execution contract from the evaluated configuration, which can restore an authorized call after a proposed block or apply a declared repair. Confinement requires the final action to preserve the certified cut. On eight executable agent-security benchmarks with three target-model families, the evaluated configuration gives strictly lowest attack success in 62 of 79 eligible attack columns and ties in 14; full-benchmark native utility loses at most three points relative to the undefended agent. A complete ablation over 1167 paired cases attributes most security gains to effect verification and refusal control to boundary adaptation. A reduced-scale adaptive search succeeds on 0/30 out-of-authority targets against the defense.

When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate task score. That score cannot tell whether improvement was attainable, which component lost value, or what the agent's own checks certify. We introduce a claim-specific verification audit for modular agents that plan, act, check and refine. Instead of scoring the agent, the audit scores the evidence: each conclusion is recorded with the evidence behind it, one of four verdicts (supported, unsupported, unresolved or not evaluated) and the boundary within which it holds. Three tools supply that evidence. Oracle policies measure attainable improvement under an explicitly stated action set, so that a low value can be traced to the evaluation rather than to the environment. Replacing one component at a time with a perfect counterpart locates lost value, with null results read as unresolved whenever a downstream component could mask them. A separate test asks whether the verifier's score identifies the quantity it is read as bounding. Applied to a constrained portfolio-allocation agent in a synthetic market with known hidden regimes, the audit shows that the value of perfect regime information depends on the action set used to measure it, that the scenario generator discards most of the regime signal while better local fidelity does not improve decisions, and that the runtime verifier can be bypassed with no visible change in outcomes. The contribution is the protocol and the evidential distinctions it enforces; the empirical findings are specific to the agent and environment studied.

Regulatory compliance checking - deciding whether a target document satisfies the obligations of a regulation - requires interpreting dense legal text, identifying which provisions apply, and grounding each decision in explicit evidence. We present ARCCS, an end-to-end, automated, agentic, and regulation-agnostic Legal NLP system for compliance checking. ARCCS decomposes raw regulatory text into atomic, traceable requirements and evaluates a target document against them using retrieved evidence, confidence scores, and human-interpretable justifications. This design decouples compliance assessment from any fixed regulatory template or predefined rule set, enabling the pipeline to operate over regulations of varying size and structure. We evaluate ARCCS in two complementary settings. First, in a GDPR policy-document evaluation, LLM-based judges find its decisions and justifications legally and evidentially consistent in up to 96.67% of the assessed cases. Second, on an EU public-procurement benchmark comprising more than 1,200 individual rule checks, the system attains 98.8% accuracy in violation detection. ARCCS is, to our knowledge, the first fully open-source system for end-to-end regulatory compliance checking and auditable report generation.

Reinforcement learning offers the prospect of a reusable sequential decision-making mechanism for spacecraft trajectory design, motivating policy interfaces that connect learned decisions to the underlying maneuver geometry. This paper develops Reachability Analysis-Informed Reinforcement Learning (RARL) for deterministic multi-impulse interplanetary transfers, placing intermediate waypoint selection at the center of the learned decision process. Local first-order reachability maps bounded velocity perturbations into an ellipsoidal set of next-node positions, within which the policy selects its waypoint. Lambert reconstruction then determines the corresponding maneuver to reach this selected waypoint along a dynamically consistent ballistic arc, coupling learned transfer-geometry selection with classical astrodynamics. A terminal two-impulse reconstruction completes the rendezvous, supported by a linear maneuver-demand assessment used for reward shaping. Numerical studies characterize this interface on a two-body Earth-Mars benchmark. Across three independent training runs, RARL achieves a mean maneuver cost of 10.23 km/s, 1.72% above a validated local sequential convex programming reference. Training over dispersed initial states extends policy reuse across a departure family with fixed target state and transfer duration. Each of the three independently trained multi-state policies completes all 10,000 held-out Monte Carlo departures without impulse-cap violations, compared with a mean feasibility rate of 6.49% for single-state policies. This broader sampled feasibility is accompanied by a 0.61% increase in mean nominal maneuver cost, without further training across departures. These results demonstrate that a reachability-informed decision interface supports benchmark-quality trajectory construction and policy reuse across dispersed departure conditions.

This paper presents the European Crisis Management Ontology (ECMO), a modular OWL-based ontology intended as a cross-sectoral reference for disaster risk reduction and response. ECMO is designed to be organised as a network of ontological modules. Among the modules, ECMO-CORE captures fundamental crisis management concepts such as hazard, event, exposure, impact, and response measure and uses ontology design patterns and the OWL2 punning technique to resolve ambiguities between hazard types and event manifestations. In addition, domain-specific modules are defined as in the case of the public health module aligned with SNOMED CT and ICD-11. To demonstrate the resource's utility, we used ECMO to represent the data of the Epidemic Intelligence from Open Sources system of the Joint Research Centre to generate an end-to-end pipeline that populates an ECMO-compliant knowledge graph from unstructured epidemiological news. Initial results demonstrate that ECMO provides the formal guardrails necessary for consistent and unified knowledge representation and integration. The ontology is publicly available at https://doi.org/10.5281/zenodo.20070268 and is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

Reinforcement learning for trading often struggles to balance upside participation with drawdown control. Profit-only policies can collapse toward passive long exposure on upward-drifting assets, while aggressively risk-penalized rewards can become too defensive during volatile periods. This paper proposes PPO-HRAP, a hybrid regime-aware policy that combines Proximal Policy Optimization with an interpretable regime prior. The agent observes both market features and portfolio-state variables, receives a reward combining portfolio log return, VIX-conditioned drawdown-increase penalty, target-exposure deviation, and turnover cost, and executes a blended action between the PPO actor output and a regime-derived target exposure. On the held-out 2020-2022 SPY test window, PPO-HRAP achieves 27.62% total return, 8.48% annualized return, 0.6447 Sharpe ratio, 0.8588 Sortino ratio, and 0.4592 Calmar ratio, while reducing maximum drawdown from 34.10% for Buy and Hold to 18.47%. Across five SPY seeds, PPO-HRAP remains stable with mean total return $0.2725 \pm 0.0109$ and mean Sharpe ratio $0.6219 \pm 0.0565$. Single-run cross-asset tests on QQQ and DIA further show that the proposed method ranks first on total return and Sharpe ratio for all three reported assets. These results suggest that blending learned actions with a volatility-aware regime prior is a practical way to improve risk-adjusted trading behavior, although the current policy still incurs high turnover and cross-asset robustness beyond SPY remains limited to single-run evidence.

Patient-specific clinical question answering requires locating the right evidence within long, heterogeneous longitudinal clinical records in which relevant facts may be scattered across encounters, repeated in copied-forward notes, or expressed using different clinical terminology. We evaluated whether biomedical reranking can improve evidence selection and downstream answer quality in a locally deployed retrieval-augmented generation pipeline for longitudinal clinical notes. The pipeline combines PubMedBERT dense retrieval, BM25 lexical retrieval, weighted reciprocal-rank fusion, and MedCPT cross-encoder reranking. Across 1,000 open- and closed-ended question-answer pairs from a cohort of 200 bariatric surgery patients, reranking increased exact source-chunk retrieval within the top 10 items, Hit@10 from 46.6% to 60.6% and mean reciprocal rank from 0.2371 to 0.3252. With Qwen3-8B generation, local judge-assessed answer correctness increased from 44.8% to 48.6%. These results show that biomedical reranking can improve the placement of relevant clinical evidence within a limited context window, although gains in retrieval do not translate proportionally into gains in answer correctness.

Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competitive performance but typically require many sampling steps at inference. VAE-based non-iterative forecasting frameworks have therefore emerged as an efficient alternative. Within this line of work, vector quantization (VQ) enables controllable latent space modeling by mapping multivariate series into compact discrete representations. Existing VQ-based forecasting methods, however, typically rely on autoregressive (AR) token generation, which suffers from exposure bias and training-inference mismatch. Flow matching provides an efficient non-autoregressive alternative for latent forecasting, but existing formulations usually initialize transport from a generic Gaussian prior. We instead observe that the trained VQ codebook already captures representative latent prototypes and can thus serve as a more informative prior for flow matching. Based on this insight, we propose ProtoFlow, a forecasting framework that combines vector-quantized autoencoding with Prototype-prior Flow matching. Our method first maps multivariate sequences into a discrete latent space, then constructs a structured prior from the learned codebook, and finally learns a DiT-based rectified flow to transport samples from this prior to future latent representations conditioned on historical observations. By replacing generic noise initialization with a learned prototype prior, ProtoFlow avoids the rollout mismatch of AR token prediction and promotes faster training convergence. Extensive experiments on benchmark datasets show that it consistently achieves superior forecasting performance with efficient inference.

Model collapse arises when generative models are trained on synthetic data produced by earlier models. The phenomenon has attracted considerable attention because of its societal and technical implications. However, previous studies have reached seemingly contradictory conclusions: replacing real data with synthetic data causes collapse (Shumailov et al.), yet accumulating real data alongside synthetic data can prevent it. For diffusion models, we study an intermediate regime typical of finite-budget pipelines: all past datasets and the real data are kept, but each new model is trained on a fixed-size sample from this growing pool, so the real fraction vanishes without any data being removed. Experiments on a 2D spiral dataset as well as the image benchmarks (MNIST, Fashion-MNIST, and CIFAR-10) show that replacement protocol degrades dataset rapidly as in the literature, whereas the fixed budget degrades only partially, sparing some features. A linear-response model of the multi-generational parameter dynamics, analyzed by stochastic recursion, confirms that the two protocols differ: some features will be fragile and lost within a few generations for both protocols, while some will be robust and preserved over practically unbounded horizons under the fixed budget protocol.

LLM arenas turn pairwise human preferences into model rankings. Those preferences may reflect how an answer is presented as well as what it says. We take a stylometric approach to 137,293 decisive French-language votes from the July 2026 Compar:IA release; the primary formatting analysis includes 137,113 battles across 116 models, and the joint estimates use the 127,092 battles with all required measurements. For each battle, we reconstruct the response visible when the user voted. We then compare the raw ranking with rankings adjusted for formatting, length, readability, vocabulary variety, and sentence structure. Presentation is associated with winning, but length, bold text, and lists tend to occur together, making their individual contributions hard to separate. Across the measured features, two associations change least across specifications: bold usage (+11.0% win odds per standard deviation in the joint model) and moving-average type-token ratio (MATTR), a measure of vocabulary variety that is less sensitive to answer length (+16.8%). The bold association is substantially smaller in observed multi-turn conversations, whereas the MATTR association changes little; because users choose whether to continue, this difference is descriptive rather than causal. The full adjustment moves 36 of 116 models by at least ten ranks. Yet comparisons with external benchmarks do not show that adjusted rankings better measure capability. We therefore recommend publishing raw and adjusted rankings side by side as a transparent sensitivity analysis.

Generative models have made rapid progress in ordered crystal structure prediction, yet many functional materials are intrinsically disordered, with substitutional mixing, vacancies, or interstitial species controlling their properties. Existing crystal generators either assume deterministic site occupations or require site-level disorder annotations, which are often unavailable when the chemical formula is the primary input. We formulate disordered crystal structure prediction through an Occupancy Distribution Matrix (ODM), a continuous site-by-species representation that unifies ordered crystals, solid solutions, vacancy disorder, and interstitial occupancy. A valid ODM must satisfy coupled site-wise occupancy, mass-conservation, and non-negativity constraints, placing each sample on a formula-dependent transportation polytope. We propose Entropic Polytope Flow (EP-Flow), a marginal-constrained flow matching framework that canonicalizes heterogeneous polytopes into a shared double-centered space, learns a marginal-preserving flow, and recovers feasible occupancies through a Sinkhorn inverse map. By jointly generating occupancies, fractional coordinates, and lattice parameters, EP-Flow achieves state-of-the-art performance on formula-conditioned disordered CSP benchmarks derived from COD and MPDS, substantially outperforming adapted ordered-crystal generators. Analyses further show that EP-Flow recovers sparse and chemically meaningful local disorder patterns rather than merely matching global composition statistics.

Dynamic scenes may be captured by a moving camera, multiple video streams, or images taken at different times. These observations reveal complementary aspects of scene geometry and motion, yet bringing them together requires establishing correspondence across viewpoints, capture times, and visibility changes. We introduce ARROW, a feed-forward model that unifies 3D reconstruction and 3D point tracking from arbitrary image sets. At its core is a novel order-invariant querying approach, which allows the association of queries with observations across arbitrary inputs. We show that exposing the model to more diverse sets of inputs during training results in improved task performance. Moreover, the resulting model is capable of generalization to a wider range of tasks including multi-view tracking. Trained with this strategy, ARROW establishes a new state of the art in 3D tracking on WorldTrack and TAPVid-3D and outperforms dedicated multi-view trackers on an adapted RGB-only MVTracker benchmark, while remaining competitive across 3D reconstruction tasks. Code and weights are publicly available.

Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the request's premise holds. We introduce DAYJOB, a benchmark of 130 tasks built by professionals in healthcare (50) and finance (80). The tasks are estimated to take a professional 13.6 hours on average in healthcare and 16.6 in finance. Each task is a containerized Harbor environment with an expert rubric of binary criteria (median 47.5 and 57.5 per task) that an agentic judge applies to the delivered files, and an attempt passes only if it meets every criterion. Across 30 model configurations from 13 developers, the strongest, Claude Opus 5.5, passes 24.7% of healthcare and 23.9% of finance attempts, and the median configuration passes 0.6% and 2.5%. In case studies, agents accept premises that the record contradicts and carry wrong inputs through otherwise consistent analyses. We release all healthcare tasks, 50 of the 80 finance tasks, the evaluation harness, and the leaderboard.

Most current grasp synthesis systems are trained offline and remain fixed during deployment. While this works well when deployment conditions resemble the training data, performance can degrade when robots encounter conditions they have not seen before, such as unfamiliar objects. In this work, we present a continual-learning framework for single-view 6-DoF grasp synthesis for a parallel-jaw gripper in cluttered scenes. Rather than finetuning a large parametric model, our method adapts through memory in a learned embedding space: grasp outcomes update future grasp scores, while optional user demonstrations are recalled and transferred to new scenes as additional candidate grasps. We evaluate our method in simulation and in extensive real-world experiments comprising over 1500 grasp trials. We show that our method matches the performance of existing 6-DoF grasping baselines even before adaptation, improves online on unseen objects from categories absent or underrepresented during training, and supports long-horizon continual learning with limited forgetting. In real-world experiments, our method reaches over 90\% success rates on several challenging object categories after only 50 online grasp attempts. Videos and code at https://giuschio.github.io/cl_grasping/.

Ireland's smart metering programme records electricity use at 30-minute resolution, with smart meters installed in over 80\% of households as of late 2025. While this is useful for billing of smart, time-of-use tariffs, it is too coarse to capture use of domestic appliances. We present a label-free disaggregation system that breaks usage data into 9 appliance categories by combining event detection for high-power loads with questionnaire-guided estimation. Our evaluation draws on four datasets: a calibration household with a commercial comparator, two public benchmarks (UK-DALE and REFIT) with per-appliance sub-metering, and a smart meter dataset of more than 4,800 years of use from 2,968 Irish consumers. Compared against two independently developed disaggregation systems our hybrid method combining analysis of usage data with questionnaire results, achieves the lowest whole-decomposition error on all buildings across the datasets, with better month-level performance over 54 paired months ($p<0.001$, Holm-corrected). Our method provides useful advice on a household's energy consumption patterns and advice on how to reduce or shift usage on some appliances in order to reduce costs.

Data-driven model order reduction methods such as operator inference enable the efficient construction of reduced-order models directly from high-dimensional time-domain data. Standard operator inference typically seeks a Galerkin-type reduced model in a prescribed low-dimensional subspace by identifying its reduced operators from projected snapshot data. The resulting inference problem is formulated as a least-squares problem admitting an efficient closed-form solution. However, it is well known from intrusive model order reduction for linear time-invariant systems that Petrov-Galerkin projections can additionally preserve important system properties such as stability and passivity. To overcome the limitations of standard operator inference, we extend the framework for linear time-invariant systems to incorporate Petrov-Galerkin projections and provide explicit error expressions and bounds between the intrusive and nonintrusive reduced operators, thus generalizing results from the literature. We demonstrate the proposed approach in the context of dissipative and port-Hamiltonian systems. Furthermore, we introduce a novel convex optimization formulation that explicitly enforces the port-Hamiltonian structure on the inferred operators. The effectiveness of the proposed methods is demonstrated on several well-established benchmark problems, including the CD player, an atmospheric model, a mass-spring-damper system, and a poroelasticity system.

Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden. Fixed-modality predictors do not jointly decide which test to acquire or when the available evidence is sufficient for diagnosis. We propose SCOPE-AD (Sequential Cost-Aware Ordinal-Belief Planning with Energy-Based Models for Diagnostic Agents) for cost-aware classification of cognitively normal (CN), mild cognitive impairment (MCI), and AD cases. A mask-aware ordinal model represents uncertainty along the ordered CN--MCI--AD continuum. Retrospective training records provide sampled Bellman targets for an energy-based teacher, whose action distributions are distilled into a Qwen policy. At deployment, the agent selects acquisition or diagnosis actions under availability and budget constraints without access to unacquired values. After each acquisition, the evidence and ordinal belief are updated before the next decision. On ADNI, SCOPE-AD achieves 77.70\% Macro-F1 at an average acquisition cost of \$50.46, exceeding the strongest evaluated baseline by 9.34 percentage points. Full-modality evaluation raises Macro-F1 by only 1.89 points while increasing acquisition cost by 116.7 times. These results support selective acquisition for cost-effective diagnosis.

Uniform-state diffusion models (USDMs) can revise any token at any denoising step, which lets them correct their own mistakes, a key advantage over masked diffusion. Self-correction, however, requires both revising incorrect tokens and retaining correct ones, and we show that current USDMs lack the latter. Even under greedy-tail decoding, state-of-the-art USDMs (DUO, UDLM, and uniform-noise SEDD) keep revising 173--270 of 512 positions at every step, and these large, uncoordinated edits collapse sample diversity. A random-token corruption experiment traces this deficit to the models themselves: they reconstruct clean and corrupted tokens with nearly identical accuracy, even though clean tokens are easier targets. A decomposition of the validation NELBO shows that training barely rewards retention: incorrect predictions are heavily penalized at corrupted positions but almost free at clean ones. We propose Correct-Token Retention Regularization (CTR-Reg), a simple but effective auxiliary loss that trains the model to retain tokens left unperturbed by the forward process and requires no change to the sampler. CTR-Reg improves clean-token accuracy by 26.5 percentage points on average across six benchmarks, while leaving corrupted-token accuracy virtually unchanged, and its per-step revisions converge to only 3--11 positions. With just five greedy-tail steps, generative perplexity more than halves under CTR-Reg for all three models while diversity is preserved, and these gains hold across sampling budgets. Our results identify correct-token retention as a key missing ingredient for self-correcting diffusion language models, and demonstrate an effective fix.

Bayesian Optimisation (BO) is a powerful framework for the optimisation of expensive black-box functions, but typically requires refitting a surrogate and maximising an acquisition function at every evaluation step. In-context approaches based on Prior-data Fitted Networks (PFNs) amortise part of this cost by pre-training transformers on functions drawn from synthetic priors. PFNs4BO amortises the surrogate but still relies on a numerically maximised acquisition function, while FIBO performs BO fully in-context by sampling optimiser locations from a learned density, which fixes the decision rule and admits no surrogate. Learned acquisition functions score a finite candidate set with a trained network, but, lacking a label for the query, learn the score by reinforcement learning on previously solved tasks. We propose IQS-BO, a PFN that learns the query decision by supervised learning on synthetic priors. In a single forward pass, IQS-BO predicts the probability that each candidate maximises the objective over the set, and we show that the minimiser of its objective is the posterior probability of this event. The model can be pre-trained without a surrogate for fully in-context BO, or take the predictions of a fixed probabilistic surrogate as additional input, amortising only the decision step. Our method proposes queries at a fraction of the cost of acquisition-based methods, while either matching or outperforming standard BO with Gaussian processes (GPs) and available in-context methods on synthetic and real-world benchmarks. Finally, we propose a mixture prior for pre-training PFNs which combines samples from GPs with functions exhibiting warped inputs, isolated narrow optima, or plateaus that are poorly modeled by stationary kernels common in GP surrogates. We show that pre-training on this prior can lead to improved optimisation performance.

Quadrupedal locomotion requires balancing conflicting objectives such as command tracking, stability, and energy efficiency, yet conventional reinforcement learning (RL) hardcodes these priorities into a fixed scalar reward at training time. We present PROMO (Preference-Conditioned Multi-Objective Reinforcement Learning), a semantic multi-objective approach that makes this trade-off an explicit runtime input to a single locomotion policy. PROMO conditions the policy on deployment facing preferences while keeping embodiment-specific locomotion priors fixed, thereby separating operator intent from reward shaping terms required for viable gait generation. Compared with fixed-objective controllers, multi-objective baselines, and independently trained specialists, PROMO achieves objective specialization and robustness from a single deployable policy. Across 100 sampled preferences in simulation, 67 behaviors are non-dominated under exact Pareto dominance, with a mean preference-objective correlation of 0.843, demonstrating broad Pareto coverage and predictable preference response. The same policy transfers zero-shot to a Unitree Go2, where preference changes alone reduce specific energy by up to 30.4%, position error by 38.7%, and peak body-attitude deviation by 59.0% relative to the balanced preference. These results establish preference-conditioned multi-objective RL as a practical runtime interface for adaptive legged locomotion, extending its role beyond offline Pareto-set construction. Open-source code and videos are available at https://amrmousa.com/promo/.

Autonomous colonoscopic navigation can reduce operator burden and the risk of loop formation or tissue trauma, but remains challenging due to deformable anatomy, weak-texture and specular endoscopic visuals, and contact-rich viscoelastic interactions. Existing methods either rely on geometry-driven pipelines, which are efficient and interpretable yet brittle due to manually engineered features and switching logic, or adopt learning-based policies, whose inferred depth/geometry can become temporally inconsistent or overly smooth under weak texture and specular highlights while simulation-trained variants (e.g., deep reinforcement learning) may further suffer from a sim-to-real gap. We propose ColoACT, an autonomous navigation system that integrates an RGB-D-E based Action Chunking Transformer policy (ColoACT policy) for a compact self-propelled Bevel-Gear-Based Endoscopic Robot (BGER). The ColoACT policy augments RGB with estimated relative depth and a gradient-based pseudo-elevation map to enhance fold-ridge saliency and other high-frequency geometric cues, and enables smooth continuous control of the BGER by predicting overlapping action chunks and fusing them via temporal ensembling. In different \textit{ex-vivo} porcine colons (approximately 60 cm), our system achieves success rates of 85.4\% and 72.5\% in straight and curved segments, respectively, and achieves 70\% success in 90-degree turns and 60\% in double-bend sequences, with feasibility further demonstrated in challenging triple-bend segments. The project page is available at: https://Adamhu1.github.io/ColoACT/.

Errors in LLM agent executions and their visible consequences can be separated by many steps, making decisive-error localization a matter of understanding both step content and step dependencies. We introduce DeFA, a dependency-guided framework for agent failure attribution. DeFA first combines protocol relations and semantic dependencies into an event dependency graph spanning the trajectory. It then identifies events that may violate task requirements and traces their sources and subsequent effects to construct a failure propagation graph. Finally, DeFA uses step evidence and the steps' roles in failure propagation to identify the decisive error, responsible agent, and error category. To support long trajectories, DeFA partitions executions into segments and combines the current segment's detailed content with summaries of the other segments, giving local diagnosis access to global execution context. Across Who and When and the Who and When Pro text subset, DeFA achieves the highest responsible-agent and exact step accuracy with all evaluated backbones, and the highest failure-mode accuracy among taxonomy-aligned methods on Pro. Further experiments on image and video trajectories demonstrate its applicability to multimodal failure attribution. Ablations support the contributions of segmentation, the event dependency graph, and the failure propagation graph. Using DeFA's diagnostic feedback for skill evolution in Trace2Skill improves downstream task accuracy by 6-15 percentage points over the native pipeline, showing that the diagnoses can also support agent improvement on subsequent tasks.

Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstructs a historical task binding. We therefore study \emph{dynamic task routing}, in which an event stream revises task bindings and a system must select the document version valid at each query time before solving it. To study this problem, we repurpose six widely used benchmarks: MMLU, MMLU-Pro, MedMCQA, MATH, GPQA, and HumanEval into 31{,}119 dynamic episodes comprising 373{,}428 temporally categorized queries. This setting exposes a central trade-off: recomputing after every event wastes work, whereas unguarded reuse returns stale conclusions. We introduce the Revision-Aware Independent Agent Graph (RIAG), a bounded multi-agent policy that separates deterministic temporal resolution from task reasoning. RIAG caches solutions by immutable document identity, starts each fresh task with two unexposed attempts, and conditionally invokes audit and repair, using at most four calls per document version. On this collection, homogeneous RIAG achieves 54.24\% joint routing-and-answer accuracy at 0.62 calls/query, compared with 32.22\% at 18.00 calls/query for the strongest comparison method; heterogeneous RIAG reaches 49.78\% at 0.63 calls/query.

Multi-agent systems are often judged by whether they reach the correct answer. This can miss a distinct failure: collaboration may leave behind a corrupted information state even when the immediate decision is correct. We call this an off-query failure. To study this failure in collaborative decision support, we introduce OffQuery, which separately evaluates evidence verification (T1), shared-state reconstruction (T2), and task resolution (T3) in two representative high-stakes settings: healthcare and disaster response. Across GPT, Gemini, and Qwen models, standard collaboration shows much stronger task performance than state reliability. Averaged over 21 model--setting combinations, task resolution reaches 64.7%, while evidence verification and state reconstruction reach only 14.3% and 43.1%. We trace this gap to selective information use: current queries often bypass corrupted facts, which become consequential when later tasks require them. We further introduce ReGround, which resolves conflicting evidence, verifies shared facts, reconstructs a trusted state, and reasons over that state. Across seven models from three families, ReGround improves all three capabilities in every evaluated setting, with average relative gains of 309.0%, 82.9%, and 17.6% on T1, T2, and T3. Reliable collaboration therefore requires both a correct decision and a reliable shared state for future reasoning.

Large language models (LLMs) have achieved strong performance across various natural language processing tasks. However, their robustness to typographical errors remains underexplored, particularly in Japanese, where text input involves multiple writing systems and IME-based conversion. In this study, we evaluate the robustness of Japanese LLMs against realistic Japanese-specific typos. We introduce five typo categories: Character Transposition, Character Replacement, Homophone Conversion, Japanese IME Conversion, and Full-Width Conversion. These perturbations are applied to three Japanese benchmark datasets (JMMLU, JCommonsenseQA, and JamC-QA), and eleven Japanese and multilingual LLMs are evaluated. The results show that Character Transposition and Character Replacement typos consistently reduce accuracy across benchmarks, whereas IME Conversion, Full-Width Conversion, and Homophone Conversion have relatively limited impact. These findings reveal that current Japanese LLMs remain vulnerable to realistic Japanese typing errors, particularly those that substantially distort the original input, highlighting the importance of robustness evaluation in practical input environments.

Unified language models are increasingly expected to combine heterogeneous capabilities, such as mathematics, code, instruction following, and controllable thinking behavior, within a single set of parameters. A common solution is sequential post-training on multiple objectives, but this entangles all objectives along one optimization trajectory and makes the final model highly sensitive to training order, data ratios, schedules, and stopping criteria. Weight-space merging offers a modular alternative, but naive merging of single-objective experts often fails: domain capabilities degrade sharply, or think/non-think modes collapse into one dominant behavior. We attribute both failures to incompatible weight-space geometry: experts trained on single objectives drift to distant regions of parameter space, placing their interpolations outside any shared low-loss basin. We propose Mixture-Trained Merging (MTM), which trains each branch on an objective-biased data mixture rather than a single objective, exposing it to cross-objective interactions and making branches compatible at merge time. MTM uses merged-model evaluations as a low-cost signal for selecting branch mixtures, avoiding expensive data-mixture ablations. The procedure is iterative: each round promotes the base model using globally selected merge coefficients and refines each branch mixture using domain-preferred coefficients under constraints that preserve other objectives. To scale beyond simplex grid search, MTM uses qNEHVI-based multi-objective Bayesian optimization. Across code, mathematics, instruction following, and think/non-think control, MTM outperforms naive merging and preserves behavioral separation where single-objective merging collapses, suggesting that effective unified models require branches trained to be mergeable.

Automatic SOAP note generation can ease the documentation burden on physicians, but existing reasoning methods often omit clinically important information and generate unsupported content. Progress in Thai is further hindered by the lack of publicly available datasets. We propose ASCRIBE, a physician-inspired reasoning framework that ascribes a clinical-significance level to each extracted atomic fact in the conversation before summarization, making a general-purpose LLM a more reliable scribe. We also release ThaiClinicBench, the first de-identified Thai clinical summarization benchmark of real encounters, together with a synthetic training corpus derived from real clinical notes. As a prompt, ASCRIBE outperforms chain-of-thought prompting on GPT-5.4 and Gemini 3.1 Pro across the physician-aligned LLM-judge metrics and improves on standard prompting by up to 10.3 points on the completeness LLM-judge metric. As a GRPO reward, it enables a Gemma-4-E4B model trained solely on synthetic data to match Gemini 3.1 Pro in factual precision and surpass it in completeness. Code and data can be found at https://github.com/loolootech/ascribe.

Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval offers an efficient alternative by encoding queries and keys into binary codes and using Hamming distance for key selection. However, this leads to a critical mismatch between Hamming distance and attention relevance. Query-Key logits depend jointly on directional similarity and feature magnitudes, whereas hash binarization discards magnitude information, causing both false-positive retrieval of low-logit keys and false-negative omission of high-logit keys. To address these failures, we propose Hierarchical Hash Retrieval (HHR), a coarse-to-fine framework that progressively improves retrieval accuracy through Geometry-Aware Key Routing (GKR) and Learned Hash Projection (LHP). GKR learns a head-wise orthogonal transformation to redistribute feature magnitudes and derive more discriminative page-level logit bounds, enabling effective pruning of low-logit keys while preserving important candidates. LHP then learns a head-wise projection space that aligns Hamming distance with the true Query-Key relevance ranking for fine-grained retrieval. By combining GKR and LHP, HHR suppresses false positives and recovers false negatives, substantially improving the fidelity of hash-based sparse attention. Extensive experiments across diverse LLMs and benchmarks demonstrate that HHR achieves superior performance over existing methods. For example, on LongBench, HHR improves the average score by 1.10 points and, at a context length of 128K, achieves up to a 3.30x decoding speedup and a 2.83x end-to-end speedup for Llama-3.1-8B-Instruct. The code is publicly available at https://github.com/lianjunl13-sudo/HHR.

Latent world models plan by scoring candidate action sequences with distances in latent space. However, task success is judged by physical quantities, which we call the success-criterion quantities. In all four latent world models we examine, the end-effector position is encoded in the latent state with an error larger than the success criterion allows. Such a latent state cannot separate successful candidates from failing ones. We propose an auxiliary loss that uses success-criterion quantities as training targets, whereas existing latent world models take them only as inputs. During training, a linear head on the encoder and predictor outputs regresses the success-criterion quantities, and the regression error is added to the training loss. The head is discarded after training, so the model, its cost, and its inputs at test time are unchanged. This loss alone improves the success rate on PushT and cube by 3.5% and 3.4% (absolute), respectively, and both improvements are statistically significant. A success criterion thus specifies what a world model must retain in its latent state, and we show that it can serve directly as a training target.

Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the author of one: an autonomous research loop in which the model repeatedly edits a single short NumPy program under a leakage-free objective, keeping the best-scoring detector it finds. The loop discovers two compact detectors, one for univariate and one for multivariate series, that describe short windows by their local spectral features and compare them with the training-region distribution through a covariance-aware distance. On the TSB-AD benchmark these detectors lead the field across metrics, ahead of the strongest classical, deep, and foundation-model baselines including Time-RCD, yet they train no network and use no GPU, and the multivariate detector is faster than every similarly performing baseline. LLM-driven program search is thus a practical route to accurate, efficient, and transparent detectors.

As generative AI (Gen AI) systems take on increasingly autonomous roles in economically and socially consequential interactions, understanding their propensity to cooperate -- and the signals that shape this propensity -- has become essential. We examine cooperative behavior in frontier Gen AI models using the iterated prisoner's dilemma, manipulating counterpart reputation (positive, unknown, negative), strategy (extortion vs. generosity), and non-verbal emotional signaling (facial expressions conveying competitive or cooperative appraisals). In a first study with non-reasoning models (Claude 3.5, Gemini 2.0 Flash, GPT-4o), cooperation was systematically shaped by all three factors, paralleling patterns long documented in human behavioral research, though models varied substantially in how heavily each factor was weighted. A second study with reasoning models (Claude 4.6, Gemini 3, GPT-5.2) revealed a more concentrated reliance on strategy and reputation, a near-elimination of the Potemkin effect observed in non-reasoning models (evidenced by near-uniform cooperation in a diagnostic harmony game), and a more conditional role for emotion consistent with a hierarchical cue-weighting strategy rather than a simple loss of social sensitivity. Reasoning models also showed heterogeneous end-game behavior, ranging from sustained cooperation to systematic last-round defection effect, revealing model-specific exploitability profiles with direct practical relevance for deployment in negotiation and other multi-round interactions. Together, these findings characterize Gen AI models as increasingly sophisticated, though heterogeneous, social actors, and underscore the practical value of developing standardized cooperation benchmarks to inform the responsible deployment of Gen AI in interactive, socially consequential settings.

Simulation-to-robot transfer can fail when velocity commands produce motion and feedback that differ from those modeled during policy training. We present execution-interface dynamics adaptation (EIDA), which fits these responses from target-platform execution data without reconstructing actuator dynamics. A model of body-frame pose increments updates simulator geometry, while a separate model predicts the velocity feedback observed by the policy; a short history of velocity feedback is included in the policy input. The fitted models are used within a lightweight GPU-parallel simulator. On the full Jackal and Go2 validation sets, the fitted models reduced position and yaw prediction errors relative to the simulator's predefined motion model. Across 100 benchmark navigation environments evaluated in a separate physics-based simulator, EIDA achieved the highest success rate and navigation score among the compared learned policies, both with and without global guidance. Feedback ablations further supported the need to match policy-facing velocity estimates. On a physical Unitree Go2, EIDA reached the goal without collision in all 20 static-scene trials, compared with 4 of 20 for the baseline. These results show that execution-interface adaptation can improve navigation transfer without detailed actuator simulation.

Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework deployed in industrial RAG assessment engagements. AGO integrates four key components: a four-state decision model that treats missing data and judge errors as explicit outcomes; layered scoring combining deterministic checks, local guardrails, and structured LLM evaluation; a stratified beta-binomial gate that quantifies regression risk probabilistically; and a mandatory meta-evaluation protocol to validate the LLM judge before it influences decisions. Since engagement data is proprietary, we evaluate the judge layer on RAGBench, a public benchmark of 100k annotated RAG traces across 12 datasets. On identical stratified test samples (N=1200 per judge), a low-cost judge (gpt-4.1-nano) detects non-adherent answers barely above chance (AUROC 0.603 [0.570, 0.634]), despite producing flawless protocol output, while gpt-4o reaches 0.783 [0.756, 0.807] -- yet its per-domain performance still ranges from 0.62 to 0.88. A fixed-seed gate study spanning regression, no change, and improvement quantifies unsafe promotion, false-alarm cost, and improvement throughput. Under regression, the decision-grade profile reduces unsafe promotion to 22.2%-35.1%, against 29.3%-41.8% for a naive gate. These results support the design choices that judge quality must be measured per engagement and that point estimates alone are not a release decision.

GUI agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step workflows. However, the diversity of available trajectories is constrained by the applications, interface states, and workflows accessible in the underlying environments. Expanding this coverage requires deploying increasingly diverse and complex software, with specialized applications imposing additional installation, configuration, and runtime costs. We introduce AutoGUIWorld, a data generation framework that combines the visual priors of image generators with the task knowledge of a planner to synthesize GUI interaction trajectories without deploying or running the corresponding software environments. AutoGUIWorld samples initial GUI scenes from structured specifications of operating-system context, visual appearance, and interface state, and generates tasks conditioned on those scenes. A planner then specifies atomic actions and their intended visual consequences, while an image generator iteratively edits the current screenshot to produce subsequent observations. Action grounding and transition-level quality filtering yield 79,266 spatially annotated step-level training samples across Ubuntu, Windows, macOS, and Chrome. Fine-tuning Qwen3.5-35B-A3B on AutoGUIWorld trajectories improves the mean task score on OSWorld from 33.0% to 40.8% and the task success rate on ScienceBoard from 14.0% to 32.2%. These results show that generated trajectories improve GUI-agent performance on real desktop and scientific tasks.

Egocentric video has become a primary source of supervision for embodied models, and its value rests on recovering hand motion in world coordinates, which camera motion and hand occlusion make difficult. Existing reconstruction pipelines typically separate hand and scene estimation, leave interaction attributes to separate task-specific models, and invoke several models per video, so no prior reconstruction model estimates these attributes and throughput becomes a practical constraint on large-scale annotation. We therefore introduce EgoFound3R, a unified end-to-end model that estimates world-space hand geometry in a metric scale shared with the scene, and predicts point-wise interaction attributes, including visibility, contact, and distance. The model integrates three designs: (i) structured hand prompts that transfer pretrained geometric priors to world-space hand reconstruction; (ii) an explicit hand representation that decodes hand geometry and interaction attributes; and (iii) a shared-parameter multi-rate design that lowers inference cost. Together, these designs predict hand geometry and point-wise attributes in one pass. On OakInk-v2, TACO, and HOI4D, EgoFound3R reduces the mean per-joint position error (MPJPE) by 43.2%, 22.4%, and 11.6% over previous methods and predicts point-wise contact and distance alongside the geometry in the same pass, while attaining approximately 6x higher throughput.

When training large language models with reinforcement learning, terminal rewards provide little guidance about which steps matter. Common methods for assigning step credit overlook that work built on uncorrected mistakes is wasted while independent work remains valid. With only a final success/failure reward, every step in a failed episode has zero total future reward, even when it made progress. We propose Dependency-Aware Reward Shaping (DARS), which represents task progress as predicates linked by prerequisite relations and assigns step-level credit over the dependency graph. An annotator marks which predicates each step verifies, invalidates, or repairs. Verified predicates are discounted according to graph distance from the nearest broken prerequisite, while independent predicates are unaffected. Repairs update these weights based on any errors that remain; invalidated predicates need re-verification to regain credit. A fixed potential converts these annotations into signed per-step rewards. A common reward and annotation interface allows DARS to integrate with a range of reasoning and agentic training methods, such as GiGPO and ARPO/AEPO, without changing their rollout strategies or optimizers. Across five task families and models from 1.5B to 8B, DARS improves success by up to 10 points over GiGPO trained with the same budget and harness (ALFWorld), raises the WebShop task score and Search-R1 QA accuracy, complements AEPO's entropy-based training on AIME24/25 with a Python interpreter, and exceeds OmniOPD in controlled tool-free reasoning comparisons at 1.7B and 4B. Ablations show that step-level credit, dependency attenuation, and graph topology each contribute. On ALFWorld, a distilled 8B annotator matches the API annotator, enabling DARS to run efficiently without a frontier judge. Code is available at https://github.com/JianhuiWei7/DARS.

Autoregressive modelling has achieved remarkable success in language and sequence tasks by learning to predict future states from previous observation. Mineral-exploration drillholes provide a natural but largely unexplored setting for this paradigm: as drilling proceeds, lithology is revealed sequentially from shallow to deep, making prediction of deeper strata inherently autoregressive. Existing drillhole modelling, however, is dominated by spatial interpolation and reconstruction, or largely rely on masked modelling, leaving strictly autoregressive prediction largely underexplored. We introduce DrillBench, a benchmark of 49,671 Western Australian drillholes for next-layer prediction and autoregressive stratigraphic generation across a graded transfer spectrum, from local prediction through spatial shift to cross geological province transfer. Benchmarking classical, geostatistical, and neural models reveals a clear \emph{transfer boundary}: spatial and geochemical conditioning provides large local gains but deteriorates sharply under stronger shift, whereas lithology-sequence autoregressive models transfer more robustly. Guided by this finding, we develop a backbone-agnostic recipe combining large-scale pretraining on historical drillholes with spatial retrieval of neighbouring lithology. Retrieval is most effective in weathered cover, when local spatial continuity remains informative, whereas pretraining contributes more strongly in bedrock and under broader geological shift. Together, they retain strong local performance while improving generalisation under spatial and cross-province shift, most markedly on the most distant splits. The benchmark and code are available at https://github.com/yihaoding/drillbench.

Object permanence, keeping track of an object's identity and position while it is occluded, is central to video representations that track, predict and plan. Trackers that achieve it learn from boxes, track identities and visibility labels. On the other hand, self-supervised object-centric methods discover objects without labels: through slot attention, it represents a video as slots that bind to objects and follow them across frames. However, these slots are lost under occlusion, making the desired permanence impossible. Reasoning permanence is a hard problem because it requires to detect when an object becomes occluded, re-identify when object reappears, and keep the object's hidden position continuous, using reapperance as the only learning cue. To address this, we propose iSEE, a novel framework that offers all three aforementioned requirements, without any labels whatsoever. We built iSEE using the following three proposed components: (i) Object evidence modelling: a slot's attention, compared with its own past, reveals when its object is hidden. (ii) Appearance-position separation: two slot streams let the appearance be held for re-identification while the position keeps changing. (iii) Permanence from reappearance: a walker follows the hidden object's position, trained only on where the object reappears. On LA-CATER static, iSEE returns a reappearing object to its own slot after 86% of occlusions, against 32% for SlotContrast, and localises it while hidden within 4.1 mAP of the label-trained SoTA RAM. The two streams also allow downstream planning, with the position stream as the action of a world model. Project page: https://insait-institute.github.io/iSEE/

We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high accuracy on the selection only. This problem is particularly relevant in contexts where labeling requires costly expert intervention, as in medical applications. We leverage features extracted from a pretrained self-supervised model to represent the data, and perform coreset selection directly in this feature space. In this paper, we use entropic optimal transport, specifically the Sinkhorn divergence, as the coreset selection criterion, which first allows us to get dimension-free sample complexity results, and second admits computationally efficient gradient evaluations. This opens the way to using gradient-based algorithms to rapidly compute solution candidates, further improved by a swap-based local search, with guarantees on the solution quality. Experiments on image benchmarks and medical datasets show that our method outperforms state-of-the-art heuristics in low-budget settings.

Large language model (LLM) agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedback, and local knowledge. Yet such experience is distributed across organizations and cannot be directly shared because of privacy and proprietary constraints. Conventional federated learning is insufficient for this setting, as agent capabilities extend beyond model parameters to memory, tools, rewards, skills, and structured knowledge. In this paper, we formulate \textbf{Federated Agent Optimization (FAO)}, which studies how distributed agents can collaboratively improve through controlled information exchange while keeping raw data, complete trajectories, and private knowledge local. We define FAO as a multi-objective problem balancing agent utility, privacy leakage, and communication cost, and organize its optimization space across policy, memory, tool use, reward, and structured knowledge and skills. We further characterize how private experience can be abstracted, protected, aggregated, and adapted into transferable capabilities, providing a unified view of how agents can benefit from one another without direct experience sharing. Finally, we identify the key challenges of FAO and outline several promising directions for future research toward trustworthy federated agent systems.

Counterfactual generation seeks to sample outcomes under a hypothetical intervention or decision using observational data collected under the factual assignment mechanism. We develop a flow-matching approach that combines a sample-split, doubly robust training objective with a learned coupling between observed source outcomes and target outcomes drawn from a fitted conditional outcome model. To enable finite-step generation, we leverage a score-corrected stochastic sampler based on a Gaussian-smoothed interpolation. Our main theoretical contribution is a coupling-sensitive KL bound for constant-step Euler discretization: the error is controlled by moments of the source--target displacement under the chosen coupling, rather than by global uniform regularity of the velocity field, and has near-linear dependence on the ambient dimension. We also establish finite-sample non-parametric guarantees for the learned velocity and score fields when both the conditional outcome model and the source-target coupling are estimated from data. These bounds separate approximation, coupling-replacement, nuisance-estimation, generalization, and Monte Carlo errors and, combined with the sampler analysis, yield an end-to-end guarantee for counterfactual generation. Experiments on synthetic and semi-synthetic image benchmarks support the coupling-dependent theory and show that, at finite discretization budgets, the stochastic sampler can outperform the corresponding deterministic ODE sampler.

Streaming vision-language models must process continuously growing video streams under a bounded compute budget, creating a persistent tension between real-time perception and long-term memory. Retrieving historical information provides a natural remedy, yet historical recall is not uniformly beneficial: unnecessary history may introduce irrelevant context into current reasoning and interfere with native real-time perception. Effective streaming memory should therefore address not only what to remember, but also when and how to access it. To this end, we introduce FlashBack, a training-free framework for selective, multi-level memory in streaming vision-language models. Before retrieving history, FlashBack draws on the semantic understanding of the frozen streaming VLM to infer whether a query calls for historical evidence. This assessment determines whether inference remains on the Native trajectory or invokes an isolated Recall trajectory. The Recall trajectory combines recent context with retrieved long-term memory through a query-local Side-KV pathway, preserving local temporal continuity without modifying the persistent Native state. We instantiate FlashBack on StreamingVLM and Mage-VL-4B and evaluate it on OVO-Bench and StreamingBench. The results show improvements on several long-horizon and memory-dependent tasks while largely preserving real-time perception, with performance competitive with strong training-based streaming methods despite requiring no additional training. Our code will be announced later.

Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote reasoning while reducing source-content exposure under existing media interfaces.

Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently struggle to understand negation and produce incorrect answers when questions involve negated clauses. To address this limitation, we propose Skeleton-and-Strategy Prompting (\textbf{SSP}), a training-free, in-context learning method that improves VLM negation understanding capabilities without any parameter updates. Given a negation question, our method first abstracts the underlying question structure into a skeleton, retrieves a small set of same-skeleton questions from a lightweight question pool, then prompts the VLM to analyze their shared negation pattern and synthesize a single-sentence answering strategy. The skeleton and strategy are prepended to the test sample to guide the model correctly tackle the negation problems. Experiments on multiple negation VQA benchmarks show that SSP achieves state-of-the-art performance on negation-focused VQA tasks while remaining computationally efficient.

Manipulation failures can leave scenes in states from which a task policy cannot recover. Learning corrective behaviors requires scalable failure exploration and physical grounding. We present Recova, an agent-guided framework that jointly develops task execution and recovery in a reconstructed digital twin, then verifies and refines both through real-world experience. In the twin, the agent diagnoses failures, tests corrective programs, and collects successful task and recovery rollouts for separate policies. During deployment, it monitors progress, invokes a learned or programmatic recovery, verifies scene restoration, and resumes execution. When no suitable recovery is available, a human demonstration resolves the failure and enters the learning loop, allowing the system to expand its recovery capabilities. Physical rollouts and human demonstrations are routed to the corresponding policy for DAgger training. Across six LIBERO-Pro settings and four MolmoSpaces categories, Recova achieves 78.8% and 64.9% mean success, compared with 71.7% and 38.0% for the strongest baselines. With parallel collection across four real-robot workstations, DAgger fine-tuning raises mean success from 23.8% to 77.5%, and recovery skills further raise it to 87.5%. Over four collection rounds on one task, observed human intervention falls from 87.5% to 0%. Together, these results show how agent-guided recovery turns failures into reusable capabilities, improving robustness while progressively reducing human intervention. Project page: https://www.liuisabella.com/Recova

Standard information bottleneck (IB) regularization constrains representations via a single scalar I(Z;X), implicitlytreating all information as homogeneous. However, a single global compression control couples label-relevant structurewith residual within-condition variation, rather than regulating their allocation independently, allowing nuisanceinformation to persist in learned representations. For example, in medical imaging applications, residual variation oftenstems from acquisition conditions, background factors, or subject-specific appearance. This issue becomes particularlypronounced in data-limited settings, where models tend to overfit such variation, hindering generalization. While existingregularization methods can stabilize training, control capacity, or shape representation geometry, they do not explicitlyseparate nuisance-like variation from task-supporting structure. To address this limitation, we revisit IB from a structuredperspective based on a label-induced partition, where condition-level structure and within-condition information playdistinct roles. This leads to a dual-bottleneck formulation: a standard KL term controls global information capacity, while aconditional KL term targets within-condition information. We show that the conditional KL admits an exact decompositioninto a within-condition information term and a prior-mismatch term, explaining its alignment with the design objective.With a simplex-structured conditional prior, the method provides controllable latent geometry and integrates seamlesslyinto existing pipelines. Experiments on classification and segmentation show the clearest gains in low-data classificationand consistent improvements across dense prediction benchmarks.

With the increasing use of robot-free demonstration interfaces that provide state trajectories without action labels, imitation from observation has become a promising approach for learning robot behaviors from human demonstrations. However, due to differences in embodiment and dynamics between humans and robots, demonstrated human motions may not be feasible for the robot, potentially degrading policy performance. In this study, we propose Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation (EF-GAIfO), which estimates the feasibility of state-only demonstrations from the robot's own experience rather than relying on explicit dynamics models or large prior exploration datasets. A key feature of EF-GAIfO is that the notion of feasibility evolves with policy learning: as the policy improves and the robot experiences a broader range of state transitions, the feasible region is progressively expanded, allowing additional demonstrations to be incorporated into learning. This enables feasibility-aware imitation that adapts to the current stage of policy learning, rather than relying on a pre-designed feasibility criterion. We validate the effectiveness of EF-GAIfO on a locomotion task in simulation and on a real quadruped robot performing a object-reaching-and-grasping task.

Time Series Anomaly Detection has received increasing attention, driven by the growing availability of complex time series data. This surge has led to the development of numerous detection methods, as well as a variety of benchmarks aimed at thoroughly evaluating their performance. However, most existing detectors remain largely agnostic to domain context, overlooking explainability and interpretability. One of the main reasons for this gap is that current benchmarks primarily focus on detection accuracy, and only few of them evaluate spatial explainability. Moreover, no benchmark currently provides sufficiently rich semantic annotations to support the generation of human-understandable interpretations of anomalies. To address these limitations, we introduce SHAD (Scality High-dimensional Anomaly Detection benchmark), a fully annotated benchmark composed of 215 multivariate, high-dimensional time series collected from real-world distributed cloud storage systems operated by Scality. The proposed dataset includes rich contextual information, covering three families of anomalies with varying degrees of severity. As further contribution, we provide a foundation for future work by evaluating baseline methods for Detection, Explainability, and Interpretability, covering all stages of a TSAD pipeline. For Detection, we benchmark a wide range of existing anomaly detectors, testing their effectiveness on the proposed real-world dataset. Then, we consider explainability by evaluating whether measuring the contribution of each dimension in the generated anomaly score can provide accurate anomaly attributions. Finally, for interpretability, we investigate the effectiveness of frozen LLM baselines in localizing and interpreting anomalies.

Cardiovascular magnetic resonance (CMR), including cine imaging, is a reference standard for the noninvasive assessment of cardiac morphology and ventricular function. Cine CMR interpretation integrates qualitative visual assessment with quantitative measurements of ventricular volumes, ejection fraction, myocardial mass, wall thickness, and regional wall motion. Current medical vision-language models (VLMs) cannot reliably derive quantitative measurements from multidimensional cine images without analysis tools. We present CineMR, a tool-augmented VLM that invokes cardiac image-analysis tools and integrates their outputs into interleaved reasoning for quantitative CMR assessment. We also construct a multi-cohort visual question answering benchmark covering quantitative metric extraction, multiclass diagnosis, and differential diagnosis, together with tools for segmentation, phase selection, volumetry, morphometry, and regional wall motion analysis. CineMR is trained with supervised fine-tuning (SFT) on tool-interaction traces followed by Group Relative Policy Optimization (GRPO) with conditional tool-use rewards. On the multi-cohort cine CMR benchmark, CineMR achieves 35.9% pass@1 and 58.9% pass@4, compared with 1.5% pass@1 for the Qwen3-VL-8B backbone and 0.0% and 7.0% pass@1 for LLaVA-Med v1.5 and MedGemma-4B, respectively. Correct tool invocation reaches 99.8% after GRPO, up from 78.9% after SFT. Live tool outputs improve ventricular measurement accuracy by 20.4--23.7% over direct model predictions, and removing all tools reduces pass@1 from 35.9% to 27.9%. These results highlight the importance of reliable tool use for quantitative cine CMR reasoning and support CineMR as a promising approach for assistive cardiac image assessment. Code, benchmark resources, and model weights are available at https://github.com/AI-MIND-Lab/CineMR.

Reliable video world models could provide scalable predictive environments for robot learning, planning, and evaluation. However, generated robot videos can violate physical principles and complete tasks through physically implausible behavior, limiting their reliability for robot learning and planning. Current video-generation benchmarks exclude physics that are inherently hidden by visuals (e.g., weight, viscosity, friction). Due to this, video models are evaluated on the fidelity of physics, not the underlying accuracy of physics. We introduce PhysicsLENS, a dataset and benchmark for evaluating plausibility of physical properties grounded in robotics. PhysicsLENS uses matched scenario pairs that hold the same conditioning frame and task, while varying underlying physics in the scene description. Scenarios are curated from public robot video sources and annotated across seven physical domains: collision, gravity, momentum, friction, deformation, fluid, and causality. We evaluate across four video generation models, producing over 400 human-annotated labels. Results show that plausible-looking videos often ignore the stated property (34 of 47), and that stating the property lowers plausibility only slightly and not significantly.

Agentic reinforcement learning (RL) has emerged as a powerful approach for training large language model agents on multi-step tasks, yet reliance on terminal outcome rewards creates two credit-assignment problems, particularly in long-horizon tasks. First, same-outcome rollout groups provide no learning signal from terminal rewards. Second, terminal rewards provide only trajectory-wide feedback, making it difficult to identify which decisions caused a failure. Recent work supplements terminal rewards with finer-grained information from trajectory analysis, such as natural-language reflections on intermediate decisions and errors. However, natural-language diagnoses are difficult to use directly for credit assignment: their error claims may be unreliable, and they do not quantify how much each error should affect learning. We propose Self-Diagnosis-guided Terminal Credit Redistribution (FAULT), which turns diagnosed errors into explicit step-level credit anchored by terminal outcomes. FAULT checks diagnostic evidence and learns relative error costs from task outcomes. During training, the policy and self-diagnoser co-evolve, while error costs are updated online from recent outcomes. On ALFWorld, FAULT recovers learning signals from same-outcome groups, reaching 95% signal coverage versus 41% for GRPO and 72% for GiGPO, while better localizing credit to specific error steps. Across two model scales, FAULT delivers strong. improvements on the long-horizon ALFWorld and WebShop tasks while remaining competitive on short-horizon Search-based QA.

Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group proportions change between training and deployment. We propose DR-TFM, a parameter-efficient distributionally robust adaptation framework that requires no true group annotations. DR-TFM adjusts attention to labeled context examples by fine-tuning an existing query scaling network or adding and training one, while keeping all other parameters fixed. We instantiate the framework with two robust objectives using estimated groups or source conditional distributions derived from training data. For TabPFN-3, adaptation updates only 0.016% of the pretrained model's parameters. Across five tabular benchmarks, DR-TFM achieves substantially higher average worst-group accuracy than pretrained TFMs and the compared robust baselines without true group annotations, while maintaining competitive mean group accuracy. DR-TFM also improves average worst-group accuracy on ACS Income and across four additional TFMs.

Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement policies are tested in 28,800 exhaustive permutation trials and 2,160 scripted multistep episodes. Joint policies are spatially order-invariant conditional on fixed priorities, yet conservative rejection completes only 31.25% of agents in a six-agent doorway task versus 90.28% for random tickets; the paired improvement is 59.03 percentage points (95% bootstrap interval: 50.00-68.06). All policies preserve the tested spatial constraints, and priority arbitration still misses the independent small-instance optimum. A separate full-state journal audit exactly replays 156 checkpoints and rejects 1,332 constructed corruptions with a retained terminal anchor. The evidence concerns execution semantics, not human realism or long-run fairness.

Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield policies stronger than the checkpoints visited by its optimizer. We call this policy-space scaling: expanding the deployable policy set accessible from a fixed RL history, without extending training or increasing per-query inference computation. We instantiate it with SURGE (Scaling Up RL Gradient-free via Eigenspace fusion). SURGE combines two checkpoints from the same RL run: a high-accuracy anchor and a competitive donor that generates shorter responses. It expresses both checkpoints as changes from their shared initialization, then spectrally decomposes the anchor's update to retain its dominant component and incorporate the donor's complementary component. With a fixed target for how much of the anchor update to retain, SURGE determines the block size from the weights without testing candidate policies. We evaluate two 1.5B mathematical-reasoning histories, DeepSeek and Nemotron, and one 7B coding history, OLMo. SURGE improves benchmark-average accuracy over both input checkpoints while using fewer reasoning tokens than the anchor. It reaches 54.17% on DeepSeek AIME24 against a measured native maximum of 50.83%, and 83.7% on OLMo HumanEval+ against 82.8%. These gains exceed the observed training curves. Geometric controls support the importance of RL-update structure beyond weight displacement or token reduction alone. Each constructed model runs as a single policy. Our findings identify stored RL history as a reusable scaling resource: the capability available from a training run need not end at its best checkpoint.

Mainstream large language models rely on a tokenizer to encode text into a token sequence. Different tokenizers may yield token sequences of substantially different lengths for the same text. With a fixed model architecture, shorter token sequences correspond to lower inference time. We propose a tokenizer training approach named Counting and Filtering (CNF) and a text encoding algorithm called Min-Cost Encoding (MCE). MCE defines a cost function over a text segment, and determines the best segmentation by globally minimizing the overall segmentation cost. CNF builds a raw vocabulary by directly counting valid substrings, and then constructs the final vocabulary through a filtering step based on actual token usage when segmenting the training corpus with MCE. The CNF-MCE conbination offers several advantages over BPE, including higher token efficiency, greater scalability, and lower dependency. Across six text categories and two vocabulary-size groups, CNF-MCE consistently achieves better compression than the evaluated BPE tokenizers. With a 250K vocabulary, CNF-MCE increases compression rate by 26% and 30% on English web text over the o200k_base and qwen250k tokenizers. Experiments scaling the vocabulary to 1M entries on English web text demonstrate sustained improvements over BPE, with a token efficiency improvement of over 60% and vocabulary utilization rising from 52.9% to 96.9%. The MCE algorithm does not depend on a merge list (as in BPE) or token probability (as in UnigramLM), making it applicable to a wide range of vocabularies, including those built from BPE, UnigramLM, CNF, and others. Language models trained from scratch at the 1.8B and 8B scales achieve comparable average performance to models using the BPE tokenizers across 11 benchmarks. These results demonstrate that CNF-MCE can improve token efficiency significantly while maintaining competitive downstream performance.

Electroencephalography (EEG) foundation models are often pretrained with a fixed channel vocabulary or a limited set of montages, making transfer difficult when electrode layouts change. We propose CortexBridge, a lightweight adapter that combines EEG features with electrode and atlas coordinates to map arbitrary montages into a shared cortical latent space. Evaluated with three frozen foundation models on five brain-computer interface (BCI) datasets from the Mother of All BCI Benchmarks (MOABB), CortexBridge improves performance in 13 of 15 evaluations. The gains in balanced accuracy average 0.80% for EEGPT, 0.70% for LaBraM, and 3.26% for CBraMod, with a maximum gain of 13.02% on 12-class steady-state visual evoked potential (SSVEP) classification. Visualizations of the learned atlas representations reveal task-dependent spatial patterns, with SSVEP showing a more concentrated representation in the Yeo Visual network than auditory P300. These results establish cortical alignment as a learnable and anatomically grounded routing mechanism from heterogeneous EEG montages to pretrained foundation models.

Designing high-performance microwave absorbers requires specialized expertise in electromagnetic theory, materials science and simulation programming, and entails time-consuming optimization. Here, we present AbsorbEvo, an agentic framework for autonomous inverse design that translates natural-language performance objectives into designs verified by full-wave simulations. Its candidate evolution strategy integrates language reasoning, physics-based prediction and historical feedback. A large language model proposes the directions and magnitudes of parameter adjustments based on task objectives and computational history. The system combines directed increments with global sampling to generate candidates and uses a low-cost predictive model as a physics prior to rank them. Only high-ranking designs undergo full-wave simulation. Results passing physical validity checks are used to evaluate performance and guide subsequent search. Experience from training tasks is further distilled into textual skills, which are independently validated before use in new tasks. Under identical proposal budgets on held-out AbsorbBench-36 tasks, AbsorbEvo achieved a task success rate of 79.17%, versus 25.00% for a generic agent and 12.50% for random search. Its mean best coverage was 0.7816, compared with 0.6434 and 0.6448, respectively. By integrating language reasoning and physics-based feedback into design decisions, AbsorbEvo provides a methodological foundation for natural-language-driven autonomous inverse design of microwave absorbers.

A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now. Current systems recover such associations by letting an LLM reason at write or read time, at a cost of hundreds to over a thousand LLM calls per memory bank and up to several thousand context tokens per query. We argue that association is a learnable relevance: the pointwise mutual information of memories under how human lives unfold. We introduce Madeleine, which learns amortized association: offline, an LLM life simulator writes simulated lives, whose cue-trigger pairs teach a query encoder a residual association on top of frozen similarity; online, it calls no LLM and plugs into any vector memory by replacing only the query encoder. On LoCoMo-Plus under the official protocol, Madeleine (I) reaches 66.6 when plugged into HyperMem, the highest among all systems evaluated under this protocol; (II) used alone, reaches the score of HyperMem as released (52.4 vs. 52.9) with zero LLM calls and about 1/21 of its answer context; and (III) lifts T-Mem by 26.2 points, significantly outperforms the same untrained backbone inside both systems, and leaves ordinary QA intact on the 4B backbone.

As the capabilities and ubiquity of Large Language Models (LLMs) grow, so does their environmental footprint. Despite calls for responsible AI, the machine learning community lacks standardised practices for carbon accounting. Our automated literature review of the 5,285 papers accepted to NeurIPS 2025 reveals that reporting of environmental impact is nearly non-existent. To catalyse a shift toward sustainable AI, we define standardised sustainability metrics for evaluating model training efficiency, accompanied by simple heuristics to estimate the carbon cost of LLM inference. We implement these metrics in carbonbenchmark, a drop-in software solution for tracking and reporting emissions. Finally, to combat the pursuit of marginal accuracy gains at disproportionate environmental costs, we formalise the `Smallest Model that Achieves the Job' (SMAJ), a framework which challenges the field to prioritise computational efficiency and environmental accountability alongside traditional `State-of-the-Art' (SotA) accuracy.

How much can test-time computation improve a language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, but existing comparisons mostly evaluate one domain at a time and rarely charge selection to the budget. We introduce SELF-POT, a benchmark and evaluation framework that measures the test-time potential of a model across competition mathematics, competitive programming, and agentic workflows. SELF-POT separates candidate coverage from final accuracy on static tasks, tracks correctness transitions under revision, and measures protocol completion alongside task success in agentic environments. Under a unified budget rule, it compares Direct inference with parallel sampling and self-revision under fixed multiples of the Direct budget, and charges every model call, including selection and critique, in dollars. This design supports two kinds of comparison: the gain a model obtains from additional inference, and a lower-cost model with additional inference against a stronger model. Across five low-cost reasoning models on 350 sealed tasks, with Claude Opus 5.5 Direct as the reference, the returns depend on the domain, the selection rule, and failure handling. When we replay the retained programming candidate pools, public-example selection raises correct submissions from 376 to 453 of 500 scheduled cells while saving 12-49% of logical API cost across models, and simply retaining an available candidate when judging fails recovers 61 submissions at unchanged cost. On identical mathematics pools, judging with fallback yields 186 correct submissions versus 182 for voting, while voting saves 12-21% of logical API cost. These controlled replays show how selection and failure handling change the gains realized from the same generated candidates, and they quantify the marginal value of a model judge.

Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier attempts. Yet existing methods fall short in agent pipelines: much of the reusable text is missing from their corpora or stored in a form that differs from what the agent emits, and their draft lengths ignore that accept length varies across agents and drifts over turns. We present AgSpec, a framework that supplies the corpus and draft-length policies that existing retrieval engines lack in coding-agent pipelines. AgSpec retrieves from session, workspace, and global corpora, retaining the ongoing session trajectory and indexing opened files in the agent's emission format. It bounds each agent's draft length with an offline-profiled cap and adapts the length online from verification feedback. On two repository-level multi-agent coding benchmarks, AgSpec outperforms five retrieval-based drafters and EAGLE-3 in most evaluated settings, raising generation throughput over autoregressive decoding up to 4.37$\times$ at batch size 1 and 4.76$\times$ at batch size 16. AgSpec also remains effective on benchmarks without a repository or a multi-agent pipeline, showing that its gains generalize to coding agents broadly.

Autonomous robots on one-shot missions run over horizons far longer than the trajectories seen during training, under a fixed onboard compute budget. We present FRANK, a 507K-parameter recurrent architecture that combines tau-gated recurrent modules, content-addressable memory, and a feedforward reflex pathway. We evaluate it against recurrent, state-space, and reduced modular baselines at matched parameter count on four algorithmic sequence tasks, trained at length 5-20 and evaluated out to two million tokens. At 100,000x the maximum training length, 6 of 10 FRANK seeds retain exactly 100.0% accuracy, while none of the 50 baseline configurations does, five architectures at ten seeds each with none left incomplete (Fisher exact, two-sided p = 4.2E-6. Targeted lesions across the four tasks yield four distinct component-reliance profiles, consistent with task-dependent allocation across the recurrent, memory, and reflex pathways. Separately, a FRANK policy trained in simulation drives a physical ground vehicle to commanded waypoints through obstacles without teleoperation.

Coordinated multi-humanoid loco-manipulation is promising yet challenging due to high-dimensional whole-body control, decentralized decision making, and scalability. While recent reinforcement learning methods have improved single-humanoid whole-body control, extending them to the multi-humanoid setting remains nontrivial and often requires substantial reward engineering or task-specific design. We propose MASkillBlender, a general multi-agent reinforcement learning framework to achieve decentralized multi-humanoid whole-body coordination. By learning a shared decentralized high-level policy over reusable pre-trained single-humanoid skills, MASkillBlender enables coordinated behaviors using only task-level rewards, without requiring task-specific motion references. To improve learning efficiency, we further introduce a permutation-based data augmentation strategy for homogeneous multi-humanoid systems, and theoretically show that the permuted samples preserve the policy-gradient direction of the original samples under the homogeneous Markov game formulation. We evaluate MASkillBlender on multiple multi-humanoid coordination tasks across two humanoid embodiments. Simulation results demonstrate that the proposed framework consistently achieves strong task performance and enables coordinated behaviors across different tasks and humanoid embodiments.

A post-hoc out-of-distribution (OOD) detector reads the activations of a trained classifier and returns a score. It fits that score on in-distribution data, and the benchmarks that evaluate it supply a second piece of OOD data for the fitting itself. Some detectors tune a constant on it. Others fit a direction in feature space or train a flexible combiner and report the number that it reaches as the gain that is still available. Every such fit is validated on held-out samples of the same OOD dataset. That check rules out memorizing individual images. It says nothing about a fit that has instead learned which dataset it is looking at, and a direction that recognizes one OOD dataset rather than novelty passes it perfectly. The detector that a practitioner installs meets OOD data from a source that nobody fitted it on, so the difference decides what the reported number is worth. We measure it by holding out the whole OOD dataset rather than a sample of it, and we call that gap the inflation. We read it across a range of combiners on ImageNet and CIFAR-100 backbones. Most of the gain that the usual protocol reports turns out to be dataset identity rather than novelty. The size of the fit does not move what survives, so the effect is not ordinary overfitting. The share depends instead on whether the input exposes class identity, and two controls that vary that property alone separate the inflation on every backbone of both benchmarks. A closed form accounts for the effect and computes it from the fitting rows, so a practitioner can tell which fits will inflate without running the hold-out protocol. One of these fits survives, namely the single constant that the field already picks on a designated validation dataset. Anything above it reports a gain that the hold-out protocol does not return, and on one benchmark what survives falls while what is reported climbs.

Spacecraft rendezvous and proximity operations (RPO) are currently planned through an expertise-intensive process in which engineers translate high-level operational intent into safe, dynamically feasible trajectories, creating a bottleneck to scalable operations. Large language model (LLM)-based agents could offer an intuitive interface for this process, although their outputs are not inherently grounded in orbital dynamics, operational constraints, or the structure of admissible spacecraft maneuvers. To exploit their semantic reasoning while ensuring the generated plan's physical validity, this paper presents a hierarchical framework for spacecraft task-and-motion planning (TAMP) that grounds LLM reasoning in a graph of reusable behaviors and domain-specific planning modules. Within this framework, a pretrained LLM maps a natural-language command to a partial mission specification. The associated planners then resolve unspecified decisions within the admissible operational space. Finally, trajectory optimization converts the completed mission specification into a dynamically feasible trajectory. Numerical experiments demonstrate that this architecture substantially improves intent recovery over direct LLM generation, achieving 98% exact recovery of partial mission specifications across all evaluated splits when backed by frontier LLMs. Additional test-time-compute experiments show that, for a compact 9B model, verifier-guided revision increases exact recovery from 75% to 88%, while broader behavior-plan search independently improves selection among admissible trajectory realizations. Overall, these results establish a scalable and auditable foundation for language-driven agentic planning of spacecraft RPO.

Video generation models are increasingly being explored as world simulators for embodied planning and learning. To do so effectively, these models must not only generate visually appealing frames, but also predict how environments dynamically evolve when executing goal-directed actions. While evaluating these capabilities is crucial, existing benchmarks focus mainly on single short actions or step-by-step instructions. This leaves multi-step physical reasoning underexplored, especially in egocentric video generation that requires planning to simulate proper execution to accomplish high-level goals by carrying out multiple real-world manipulations. We introduce Ego2Act, a goal-directed benchmark featuring 2,640 videos from 110 real-world tasks across day-to-day settings, varying object clutter and multi-step complexity. Given an initial scene image and a high-level goal, Ego2Act evaluates whether video generation models can produce realistic egocentric videos of a hand manipulating objects to carry out the task. To support scalable evaluation, we also introduce Ego2ActJudge, a reference-free evaluation pipeline that achieves better task completion and physics plausibility evaluation alignment with human consensus compared to relevant baselines. Our findings reveal that models' generated simulations often skip or partially execute steps, leaving later steps missing dependent states, which leads to unfulfilled goal. Furthermore, models consistently fail at fine-grained physical dynamics, particularly during complex object manipulation and persistent world modeling. We hope Ego2Act provides a rigorous testbed for advancing video models toward physically plausible, goal-directed simulation.

Vision-language-action (VLA) policies have demonstrated impressive capabilities in generalizable robotic manipulation, but their deployment in the real world remains challenging due to potential collisions involving different parts of the robot, manipulated objects, and the surrounding environment. Existing inference-time VLA safety frameworks typically rely on simplified end-effector-centered representations that do not explicitly model the full articulated robot and attached-object geometry. In this paper, we present WBAG, a safety framework that models the robot's whole-body and grasp-dependent attached geometry. WBAG constructs a grasp-conditioned safe set that adapts the protected geometry as objects are grasped, then converts this evolving geometry into differentiable CBF constraints that minimally modify the VLA's native six-dimensional operational-space action for collision avoidance across robot, scene, and attached geometry. On the SafeLIBERO benchmark, a variant of LIBERO augmented with obstacles for safety evaluation, WBAG achieves the best overall safety and safe task success among the evaluated methods under a scene-level safety evaluator that monitors all eligible non-task objects, reaching 97.38\% aggregate Scene Safety and 59.38\% Safe Success.

Dialectal machine translation remains challenging due to limited data and strong linguistic variation not captured by standard benchmarks, which often assume standardized and well-edited text. We study Polish-Silesian MT using neural and rule-based systems, evaluating on SiLTT - a new Pol-Szl testset, alongside established BOUQuET and FLORES benchmarks. Results show our rule-based system is consistently strongest on SiLTT and BOUQuET datasets and that TranslateGemma fine-tuned on a curated dataset improves over strong neural baselines but does not surpass the rule-based system in dialectal settings. We release SiLTT and our best neural model to support further research.

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the mathematical reasoning capabilities of large language models. Recent work introduces search into RLVR rollouts to increase trajectory diversity, but diversity alone does not ensure that the search-induced rollout policy improves upon the current policy. To address this gap, we propose APIVIS, a training-time framework that adapts finite-budget Gumbel search to chunk-level mathematical reasoning. APIVIS combines direct and searched responses within each rollout group, allowing improvements found by search to produce informative relative rewards. It further applies selective supervision to search-improved tokens, preserving a learning signal when uniform group rewards render GRPO ineffective. We show that exact value-guided selection improves the expected verifier reward at each searched state and that this guarantee extends to the complete rollout policy, with a corresponding approximate guarantee under bounded value-estimation error. Experiments on widely recognized mathematical reasoning benchmarks and different model scales demonstrate substantial improvements over competitive search-based methods, validating the effectiveness of APIVIS.

Structured electronic health records (EHRs) contain a patient's clinical trajectory as a sequence of clinical codes. Answering clinical questions from such records requires both the context of the whole trajectory and the specific events that support the answer. We introduce GLoC-EHR, a multimodal language model that reads a contextual encoding of the record through a fixed-size global memory of the trajectory and a local memory of selected events. The model learns to generate hospital-course summaries from the global memory and descriptions of masked concepts from the local memory, aligning both with clinical text. It is then trained to cite evidence before answering, through rationale fine-tuning followed by group relative policy optimization (GRPO) with rewards for correct answers and record-supported evidence. On three MIMIC-IV outcome tasks, GLoC-EHR attains the highest macro AUROC among the compared models when it answers directly, whereas zero-shot LLMs reading the serialized record fall far behind. With evidence-cited reasoning, it stays close to its direct multi-task counterpart in macro AUROC, and the evidence terms of the objective reduce unsupported evidence at a similar macro AUROC. The local memory adds distinct supported findings, particularly under strict matching, without a detectable change in macro AUROC. Without retraining, GLoC-EHR transfers to EHRSHOT on par with EHR-BERT and answers two unseen laboratory questions better than zero-shot prompting of its own backbone.

Robotic manipulation of labware is difficult when transparent or reflective objects must be identified and localized. Coded planar fiducials are a practical retrofit: easy to print, they leave the marked face flat and graspable. Yet a single planar tag is least reliable in near-frontal views, where perspective cues fade. Non-planar geometries restore those cues but intrude on the flat face that a parallel-jaw gripper must contact. Our idea is to tilt multiple tags within one compact footprint, so that each tag is seen at a non-frontal angle even when the marker faces the camera. We propose the quARtet marker, a 3D-printable fiducial embodying this idea: all detected corners of its four tilted AprilTags enter one Perspective-n-Point solve, and a shared configuration defines the fabricated geometry and the detector model. Because tilting consumes flat area, its three layouts trade pose-estimation consistency against graspability. In robot-referenced, same-setup fixed-camera experiments, all three layouts reduced the mean frontal orientation error from 2.18 degree for a single planar tag to 0.24-0.47 degree and the root-mean-square position error from 1.50 to 0.17-0.20 mm. A robot-mounted-camera pose-hold test confirmed this separation under closed-loop visual feedback. In swing-down trials under identical conditions, the two layouts with flat contact strips retained the object with about 2 mm of in-grasp slip, whereas the layout without flat strips slipped by roughly 100 mm. For the tested conditions, the results support a rule: the layout without flat strips when pose-estimation consistency dominates, a layout with flat strips when the marked face must remain graspable.

Unmanned aerial vehicles (UAVs) searching for ground targets from a high altitude face a unique challenge, particularly when the target is already within the field of view but effectively unobservable because of its small apparent scale. Standard object detectors often underperform in such scenarios because of resolution downscaling and limited context. In contrast, active object search frameworks address this challenge by directing the agent to a suitable pose to gather richer visual information. However, flight regulations in urban airspace often restrict such physical movements for UAVs. As an alternative active sensing approach, the UAV can leverage the pan-tilt-zoom (PTZ) mechanism of the onboard camera to dynamically adjust its field of view and sequentially gather enhanced visual information from specific regions of interest. Once the candidate locations of the target are identified, it can deploy more expensive object detection schemes, such as an ensemble of multiple models, to get better reasoning at a fixed scale. In this work, we formulate the sequential exploration with PTZ operation as a partially observable Markov decision process (POMDP), in which the agent maintains a belief state over the target's true location. To solve the POMDP, we deploy partially observable Monte Carlo planning (POMCP), where we condition the sensing reliability on target object scale and deploy selective ensemble detection as an additional reasoning step. We validate our methodology with experiments in a photorealistic simulator under different environmental conditions and vehicle states, showing detection of ground targets at variable scales with significantly fewer steps and minimal dependence on sensor resolution compared to baseline methods.

Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases. Dense table retrievers rank schema elements independently, but this ignores a key source of evidence: some required tables are not mentioned in the question and become identifiable only through their join relationships to already relevant tables. We introduce JOINGR, a join-aware table retrieval method that treats the database join graph as the retrieval space. Columns are represented as graph nodes, while intra-table and foreign-key relationships are represented as typed edges. Given a question, JOINGR selects semantically similar anchor tables, traverses join edges with a query-conditioned scorer, and aggregates the resulting edge deposits into table scores. The scorer is a lightweight MLP on top of frozen query, node, and edge embeddings, trained with a pairwise margin loss over gold tables. On BIRD and Spider datasets, JOINGR is competitive with the strongest retrieval baselines. On BEAVER, a challenging enterprise benchmark with multi-hop table requirements, JOINGR substantially improves recall over dense retrieval and re-ranking baselines. Cross-domain experiments show that the learned scorer transfers across benchmarks, indicating that the method captures reusable joingraph traversal behavior.

Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization weakens alignment safeguards, leaving qLLMs (quantized large language models) highly vulnerable to jailbreak attacks. To address this challenge, we present MOMAT (Mixture of Multiple Atlases), a hardware-enhanced safety framework that combines structured knowledge retrieval with low-power defense acceleration. Each atlas represents a semantic cluster of harmful or benign sample sets and policy templates, enabling domain-localized Retrieval-Augmented Generation guarding that mitigates the curse of dimensionality and the resulting semantic sparsity problem in large, heterogeneous safety databases. MOMAT retrieves top-$k$ similarity features from all atlases for each prompt and evaluates them using a lightweight MoE (Mixture of Experts) detector, while a CiM (Compute-in-Memory)-accelerated similarity engine performs fast, low-power atlas-local retrieval. MOMAT's CiM-based retrieval accelerates a 100-query batch from 15,052.44 ms to 3,207.21 ns (a $4.69 \times 10^6\times$ speedup) and reduces energy from $8.1 \times 10^7$ $μ$J to 3.32 $μ$J, yielding an approximately $2.5 \times 10^5\times$ energy reduction over DRAM-based (Raspberry Pi) baselines. Red-team evaluations across standard benchmarks show that MOMAT matches the defense performance of state-of-the-art methods while avoiding benign overkill and providing substantial efficiency gains, demonstrating that CiM-based modular defenses can make edge-deployed qLLMs both safer and more energy-efficient. We will release the full 223.2k-sample dataset to foster future research.

We argue that as video generation extends to longer durations, subject consistency should be evaluated over \textit{dynamic subject sets}. We therefore introduce \textbf{DynSC-Eval}, an evaluation framework that dynamically tracks eligible subjects throughout their visible lifespans and measures local continuity and global identity preservation using six complementary object-level metrics, with explicit detection of inconsistency events. To validate its effectiveness, we design synthetic experiments that actively inject inconsistency events, demonstrating both the sensitivity of DynSC-Eval and the limitations of existing metrics. Evaluations of diverse models on 5s, 15s, and 60s video generation further reveal substantial subject consistency differences that are obscured by conventional metrics. Beyond evaluation, we construct rewards from DynSC-Eval and apply DiffusionNFT post-training in an autonomous-driving testbed. On 5s generation, our approach reduces the six inconsistency metrics by an average of 13.82\% for Wan-2.1-1.3B and 5.66\% for SANA-2B, with improvements also observed on the I2V model ReSim. Qualitative comparisons further demonstrate the effectiveness of our method. We then extend generation to 10s and 30s through curriculum learning and show that consistency optimization remains effective while largely preserving other capabilities.

World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics. Complex systems call for the same tool because the effect of an action is not immediate. Seeding nodes for a campaign, or immunizing nodes against an epidemic, changes little on its own; what matters is the outcome that unfolds over the steps that follow. Designing an algorithm that selects such actions to maximize expected performance on a task is inherently iterative, and every candidate must be scored by the outcome it produces. Obtaining that outcome has relied on simulation, whose cost becomes a bottleneck when candidates are evaluated over many sampled trajectories. We propose an action-conditioned Network World Model that learns a network's diffusion dynamics under interventions over time, applies each action to the network, and predicts the outcome that follows. It serves as a fast evaluator inside an algorithm design loop in which a coding agent designs and refines executable algorithms using feedback from full rollouts, action-level credit, and counterfactual probes over alternative interventions. Across eight network tasks and five diffusion models, the designed algorithms match or exceed the strongest reported baseline in 138 of 141 settings while enabling up to 14.5 times faster rollouts than Monte Carlo simulation. Code will be released upon acceptance.

Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect effective communication, a favorable agent architecture, or simply additional reasoning? Because communication methods are commonly evaluated within the systems they were designed for, these factors are difficult to disentangle. Final accuracy further merges corrected errors and corrupted answers into a single outcome, obscuring how communication changes decisions. We introduce Independent--Communicate--Revise (ICR), a controlled framework that evaluates communication as answer revision following independent reasoning. ICR fixes initial reasoning trajectories, measures correction and preservation conditional on both agents' initial correctness, and uses a no-message revision control to quantify gains beyond additional reasoning. Across four reasoning benchmarks, our audit of textual and latent communication reveals that similar aggregate accuracy can conceal substantially different revision behaviors. Compared with transmitting answers alone, full reasoning increases correction while reducing preservation on all four benchmarks, so richer messages amplify beneficial and harmful influence alike. Receiver-policy comparisons on MedQA and GPQA-D further show that a structured verification policy shifts every channel toward greater preservation and lower correction, while its effect on selectivity varies across channels and tasks. These findings challenge treating communication quality as an intrinsic property of a channel. ICR therefore recenters evaluation on selective revision, providing a unified framework for examining how message content and receiver policies jointly produce benefits and harms.

Optimizing merging coefficients for large language models can require many costly benchmark evaluations. We propose \textbf{Simplex-Lattice Interpolation Merging (SLIM)}, which constructs a quadratic surrogate of aggregate performance on the coefficient simplex using a classical mixture design. Evaluations of individual experts and equal-weight pairs determine the surrogate with the minimum number of measurements needed to identify a general quadratic on this domain. SLIM then optimizes the surrogate without further target-metric evaluations. Experiments on two model architectures demonstrate accurate prediction of unseen multi-expert mixtures and competitive merge performance under limited evaluation budgets. Matched-budget comparisons show that structured evaluation points improve prediction fidelity over random designs, including those using regularized fitting.

Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely on shortcut features that fail to generalize across subgroups. A recent line of work mitigates this issue by using loss-based signals to identify informative samples, but these signals can become severely distorted under label noise: mislabeled samples may also incur large losses and contaminate subsequent reweighting or retraining. Despite its practical importance, this intersection remains largely underexplored. We propose POTER, a reweighting framework based on optimal transport that derives sample importance from the transport geometry between the training distribution and a reference distribution constructed from limited validation group annotations. By measuring alignment at the individual-sample level rather than relying on loss, POTER downweights mislabeled or strongly bias-aligned samples while assigning higher importance to samples better aligned with the reference distribution. In addition, POTER requires only a single ERM training stage, moving beyond the retraining paradigm common in recent work. Across standard benchmarks and noisy-label settings, POTER achieves state-of-the-art worst-group accuracy, including cases where label corruption is concentrated within minority subgroups.

Recent advances in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have significantly democratized access to legal information. Nevertheless, most existing legal assistants remain confined to multi-turn conversational QA, failing to support complex legal tasks that require systematic evidence retrieval, multi-step reasoning, and report-level synthesis. In this paper, we present LawCompass, an evidence-grounded legal assistant that navigates the transition from standard Legal QA to multi-agent deep research. LawCompass provides three task-oriented functions: Legal QA, which delivers precise, evidence-backed answers to legal questions; Professional Retrieval, which enables structured exploration of statutes and judicial cases via query rewriting; and Deep Research, which employs a multi-agent workflow to decompose complex legal tasks and synthesize comprehensive research reports. Crucially, LawCompass maintains explicit citation links across all modules, empowering users to directly verify system outputs against original legal sources. Evaluation results demonstrate that LawCompass provides a practical and scalable paradigm for transforming conversational AI into trustworthy and evidence-grounded legal research assistance.

Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents to work together on these tasks. Recent methods train LLMs to construct better workflows from execution outcomes, but they optimize only the workflow generator, while the other agents that build or execute each workflow remain fixed even though every outcome depends on all of them. However, extending training beyond the generator is challenging: the agents are coupled, and a workflow's outcome is a single sparse score that cannot tell which agent causes a failure. We propose FloWright, which leverages the workflow as a harness to optimize workflows. By introducing a hierarchical, structure-aware reward paradigm, FloWright enables one role to self-evolve and two or more roles to co-evolve, with no additional models, labels, or executions. Considering the limitation that workflows are commonly trained and evaluated on data that a single agent can already handle, we further propose DataWright, an adaptive data hardening approach that converts existing datasets into workflow-level tasks with increased difficulty. Across document, slide, chart, code, math, and finance tasks, small open models trained with FloWright achieve improved performance by up to $+7.41\%$, with co-evolving ($+5.03\%$) more roles gaining more than optimizing one of them alone ($+2.83\%$). Our project page: https://xhguo7.github.io/FloWright/.

Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory requirements confine them to short video clips and their single-prompt inference design makes multi-category open-vocabulary tracking computationally prohibitive. This work introduces two contributions toward fully automated tracking annotation of arbitrary video. The Generalized Presence Token (GPT) reformulates SAM3's inference pipeline to process N text prompts simultaneously via virtual prompt batching, reducing image encoding cost from O(N) to O(1) with no modifications to any learned component. The Annotation and Segmentation Handler (ASH) extends any memory-attention VIS tracker to sequences of arbitrary length through overlapping temporal chunks with IoU-based inter-chunk identity matching, requiring no dataset-specific training. Instantiated on SAM3, the resulting pipeline -- SAM3-ASH -- achieves state-of-the-art HOTA on MOTS20 under fully zero-shot conditions and remains competitive with trained specialists across seven additional benchmarks, while peak GPU memory consumption stays below 25 GB, establishing a practical baseline for scalable, training-free automated video annotation.

Robotic world models predict action-conditioned future scenes, providing a foundation for understanding action outcomes. However, turning alternative predictions into useful learning signals remains challenging: similar candidates limit informative quality comparisons, while diverging trajectories require persistent maintenance of their individual histories. We introduce FutureWorlds, a framework that unifies candidate construction, history maintenance, and learning from relative quality. Built on a multimodal discrete autoregressive model, FutureWorlds uses diverse beam search during reinforcement learning to construct candidate futures that balance confidence and diversity. Candidate-specific bounded memory preserves scene states and ensures that generation and policy scoring use matching histories. We further propose MemSPO (Memory-Conditioned Search-Guided Policy Optimization), which converts video trajectory rewards into group-relative advantages to optimize the world model. On RT-1, BridgeV2, and RoboCasa, FutureWorlds reduces LPIPS for 32-frame predictions by 14.78%, 20.84%, and 9.12%, respectively, relative to the strongest baseline on each dataset. Under fixed evaluation configurations, only 200 MemSPO updates further improve generation quality and support continued prediction beyond the training horizon. Memory ablations, decoding sensitivity analysis, and optical-flow evaluation show that these gains extend beyond visual quality to more accurate motion prediction and more consistent object states. Project page and code: https://github.com/Alexander-wu/FutureWorlds.

Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow well remains challenging: how finely to divide the task, which agent to trust with each subtask, and when to create a new specialist are all critical decisions a workflow constructor needs to settle up front. Thus, whether each subtask succeeds remains unknown until the workflow runs. Yet, improving a workflow is costly. Locating a fault usually requires a reference answer, a graded outcome, or a trained assessor, and the fix is applied to the whole workflow through re-execution, re-search, or retraining. We propose InFlowOp, which prices every decision in one label-free cost that weighs how well an agent's competence meets what a subtask demands against how much that agent takes to run. Before execution, InFlowOp bidirectionally determines the granularity of task decomposition and agent assignment following from the cost rather than from a fixed template. During execution, InFlowOp corrects a fault with the cheapest move via the same cost that serves the workflow both as it is built and as it runs. Facing the workflow-level evaluation challenge, we introduce Braid, a benchmark whose tasks require multi-agent coordination beyond single-agent capability. Across various domains and backbones, InFlowOp outperforms single agent baselines by up to $+11.97\%$, achieving $+9.64\%$ with in-flow optimization. Our project page: https://xhguo7.github.io/InFlowOp/.

Feed-forward 3D vision models such as VGGT have achieved remarkable progress, unifying camera estimation and dense scene reconstruction in a single pass. However, their quadratic global attention makes long image sequences expensive, while existing sparse methods may favor highly attended yet value-redundant regions. To address these limitations, we introduce VASC, a training-free sparse attention method combining value-aware block selection and execution-aware cross-layer memory. Our value-aware block selection integrates pooled query--key relevance with neighboring value contrast, reducing redundancy while preserving query-relevant and distinctive content. Cross-layer memory tracks unserved demand across layers and updates this state according to actual execution, enabling previously underserved blocks to compete under a fixed computation budget. Experiments on 7Scenes and NeuralRGB-D with VGGT and $π^3$ demonstrate improved pose estimation and reconstruction quality compared with FasterVGGT, together with up to $2.29\times$ faster inference than dense VGGT. Code is available at https://github.com/kosakayamahoo-design/VASC.

Model-based reinforcement learning (MBRL) can exploit simulated experience, but a simulator-to-target shift creates a model-selection problem: correcting the simulator and fitting the target directly can each fail under limited target data. We introduce the Model-Corrected World Model (MC-WM), which separates initial target data into disjoint fit, selection, and calibration partitions and deploys the family with lower standardized calibration risk. A learned confidence signal and deterministic validity predicates weight one-step imagined policy updates without rewriting physical rewards. We evaluate 540 unique reported run cells across three controlled Multi-Joint dynamics with Contact (MuJoCo) shifts; one exact-routing cell was repeated after a pre-deployment artifact gate, giving 541 completed executions.

Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce VIEScore2, a unified evaluator for image generation and editing tasks with optional conditioning images. VIEScore2 represents an image as an N x N grid and jointly predicts quality scores and defect locations in a single model pass. Its text-native grid representation provides a common interface for heterogeneous spatial supervision and enables directly verifiable post-training objectives. We train on 38K examples spanning score-only, localization-only, and joint supervision across generation and editing tasks. Starting from supervised fine-tuning, we further apply GRPO to improve defect localization using rewards that combine cell-level Dice overlap, score accuracy, and output-format validity. A parameter-free parser converts the structured predictions into readable explanations. On the primary suite, VIEScore2 achieves an overall-score SRCC of 0.601, compared with 0.491 for Gemini-3-Flash, the strongest zero-shot general-purpose VLM baseline under matched inputs. For defect localization, VIEScore2 outperforms both general-purpose VLMs and specialized spatial evaluators on three of six benchmarks in per-image grid IoU and ranks among the top three on five, including datasets beyond its training sources.

Kolmogorov-Arnold Networks (KANs) represent a compelling alternative to traditional Multi-Layer Perceptron (MLP)-based neural networks. By employing activation functions as learnable elements, KANs offer superior interpretability, making them suited for scientific domains. In this work, we investigate the neural scaling laws of KANs and the structural evolution of their learnable activation functions under dataset expansion. Specifically, we evaluate the scaling behavior of three KAN variants---BSRBF-KAN, Gottlieb-KAN, and Faster-KAN---across standard image classification benchmarks (MNIST and Fashion-MNIST) and a specialized scientific regression task (magnetic parameter estimation from domain images of moiré magnetic textures). Our results demonstrate that the test loss ${\cal L}$ exhibits a broken neural scaling law (BNSL) behavior as a function of the dataset size $N_D$. After passing through a random-guess regime, the loss follows architecture- and task-dependent scaling behavior. The loss crosses from a faster- to a slower-scaling branch, ${\cal L}\propto N_D^{-α}$ and ${\cal L}\propto N_D^{-β}$ with $α>β$ for image classification tasks. The exponents $α$ and $β$ depend strongly on both the specific network architecture and the dataset-size regime, ranging from 0.4 to 1.5 and from 0.06 to 0.6, respectively. For the magnetic parameter-regression task, the loss follows a single scaling law with its exponent ranging from 1.28 to 2.59. Additionally, we provide a structural analysis of how activation functions refine their complexity as data volume increases, finding that dataset expansion drives a transition from simple linear-like approximations toward stable, interpretable symbolic forms. These findings provide a quantitative roadmap for the efficient application of KANs while managing the trade-off between model expressivity and computational overhead.

Post-training quantization (PTQ) methods typically use sequential quantization that partitions a pre-trained LLM into a series of units (e.g., transformer blocks), with one unit quantized at each stage. State-of-the-art PTQ methods are predominantly learning-based, optimizing auxiliary quantization parameters (e.g., scaling factors, rotation matrices, clipping thresholds, and adapters) via gradient descent to minimize a reconstruction loss. A common practice is to use mean squared error (MSE) as the reconstruction loss function, yet its induced optimization behavior remains largely unexplored. In this work, we take a holistic view of sequential quantization and systematically investigate how optimization evolves from the first quantization stage to the last, aiming for a deep understanding of optimization in learning-based PTQ schemes. Through extensive empirical studies spanning representative learning-based PTQ methods, LLM families, model scales, architectures, quantization settings and various tasks, we consistently uncover Optimization Imbalance: reconstruction loss magnitudes vary dramatically across stages, accompanied by highly uneven gradient magnitudes and parameter updates under MSE. We term the cross-stage range of loss magnitudes the reconstruction loss scale, and reveal that MSE translates the unexpectedly large reconstruction loss scale into highly uneven gradient magnitudes, which in turn lead to uneven optimization strength across quantization stages. This finding suggests a general principle for improving learning-based PTQ: optimization strength across stages should be decoupled from the reconstruction loss scale. Theoretically, we show that root mean squared error (RMSE) variants defined at the sample, channel, token, and element levels naturally realize this principle through implicit gradient normalization, outperforming MSE significantly as a drop-in replacement.

Vision-language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the action, and the policy needs a memory of the history. Existing memory methods decide what to remember by design, for example, keeping frames with large pixel changes, and show inconsistent gains across tasks. We view what to remember as an optimisation problem. From the POMDP formulation of imitation learning, we show that the optimal memory maximises the conditional mutual information $I(a_t; m_t \mid o_t)$ between the action and the memory given the current observation. Intuitively, this means preserving the action-relevant information in the history that is not already contained in the current observation. Based on our analysis, we propose Divide-and-Remember (D&R), a recursive memory method that learns a memory function $m_t = M(h_t)$ and scales to long contexts while staying compute-light. It involves two strategies: (1) the selection over the full history is divided recursively into subproblems of top-$K$ selection over $2K$ tokens, so that fixed-size, lightweight selectors learned end-to-end support an unbounded history; (2) all recursion blocks share one selector, which captures the selection rule common to every block and keeps the method efficient. On RoboMME, a benchmark of 16 long-horizon manipulation tasks that require remembering when, where, what, and how to act, D&R achieves a state-of-the-art average success rate with consistent gains across all four suites under a budget of only 64 tokens; real-robot experiments show the same gain. Code, checkpoints and more results are at https://dnr-memory.github.io/

We focus on language-conditioned flow-based manipulation, where robot flows (robot velocity fields) serve as embodiment-agnostic, motion-centric representations for leveraging data collected from multiple robot platforms. This task is crucial because language-conditioned manipulation is essential for practical robotic systems, yet scaling robot foundation models remains limited by the labor-intensive collection of embodiment-specific data. Existing methods either coarsely approximate robot flows with sparse keypoint displacements, or cannot handle language-conditioned manipulation. To address this limitation, we propose NarrativeFlow, which models robot flows as continuous velocity fields using a flow-matching formulation conditioned on language. Accordingly, NarrativeFlow generates robot flows that are physically consistent with real-world manipulation. To validate NarrativeFlow, we have conducted experiments on standard datasets for language-conditioned manipulation. The experimental results show that NarrativeFlow outperforms representative baseline methods on standard evaluation metrics. Furthermore, through real-world experiments, we show that NarrativeFlow achieves higher success rates than baseline methods across multiple manipulation tasks. The project page is available at https://shota0520.github.io/NarrativeFlow-project-page/

Multi-agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestration, which typically relies on fixed workflows. In contrast, human scientists coordinate and adjust their division of labor at runtime. We therefore ask: can AI scientists also coordinate at runtime? To this end, we introduce Runtime Agent Coordination (RAC), which selects agents from existing AI-scientist hosts during execution, assigns scoped work contracts, and provides artifact-grounded verification. Verification informs subsequent agents without blocking transitions or discarding artifacts. We conduct a single-seed exploratory evaluation across Agent Laboratory, EvoScientist, and ARK on ResearchClawBench, preserving host models, tools, and permissions under host-calibrated budgets. Four cumulative conditions separate native execution, runtime communication, runtime selection, and the combined addition of contracts and verification. Runtime selection yields the highest observed mean score for each host; adding contracts and verification reduces these means, with host-dependent outcomes relative to native execution. These results motivate runtime coordination while exposing the limits of additional coordination mechanisms under constrained budgets. Code is available at https://github.com/systemind-team/Runtime-AI-Scientist.

Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly considering relationships between current rollouts across environments for prompt-group selection. Meanwhile, as environments are learned at different rates, all-failure and all-success rollout groups can coexist within a batch, leaving those data without group-relative reward signals. Both challenges highlight limitations of relying solely on scalar rewards in multi-environment RL: they provide limited information about cross-environment relationships and no within-group reward contrast when rewards are identical. This motivates richer textual feedback, such as rubrics describing rollout behaviours, to guide learning. Beyond rubrics' usage as reward, we repurpose rubrics to guide both online data selection and policy supervision. An LLM judge tags each rollout using a predefined rubric vocabulary shared across environments. The resulting profiles guide the selection of data that aligns with the overall behavioural composition of the mixed-environment batch while limiting overlap with already-selected data. Available positive rubrics (describing desired behaviours) provide privileged context for an on-policy self-distillation teacher, supplying additional token-level supervision, while negative rubrics (describing undesired behaviours) guide subsequent rollout generation away from recurring failure modes. Together, these components form RISED. Across model backbones, RISED achieves the highest mean pass rate across environments and ranks first or second in every individual environment. Rubric-based analysis of RISED can further characterize the behavioural changes accompanying these gains.

Time-series anomaly detection (TSAD) is difficult to generalize across datasets because heterogeneous temporal dynamics imply different notions of normality and favor different detection criteria. While time-series foundation models provide transferable representations, coupling them with a fixed anomaly-scoring mechanism can overlook this variation. This motivates a different perspective on foundation-model-based TSAD: using foundation models to coordinate specialized anomaly criteria rather than directly imposing a universal one. Based on this view, we propose \textbf{TS-Router}, a generalist-representation, specialist-detection framework that estimates the relative competence of heterogeneous anomaly detectors from pretrained temporal representations and selects suitable specialists for each target series. To avoid relying on specialist-performance labels from real tasks, we derive soft competence supervision from specialists' relative performance on labeled simulated tasks. At deployment, routing requires no target anomaly labels, and only the selected specialists are fitted unsupervisedly on the target series. We bound Top-\(k\) set-competence regret under representation coverage and conditional competence stability. Across 16 real-world benchmarks and four complementary evaluation metrics, TS-Router achieves the best overall average rank. Controlled ablations with multiple frozen TSFM encoders further support the use of pretrained representations for competence estimation and adaptive specialist selection. The code is available at https://anonymous.4open.science/r/TS-Router-D8FF.

Probabilistic forecasting is important for predicting complex dynamical systems because intrinsic randomness and incomplete observations can cause the same observed state to evolve into multiple plausible futures. While flow matching is a flexible approach for probabilistic forecasting, it is computationally expensive. Streaming flow (SF) reformulates this approach to model temporal evolution efficiently by learning a continuous velocity field directly in physical time. However, SF learns a deterministic velocity field. Thus, it provides only a single future trajectory for a given fixed initial state and observation history. To overcome this limitation, we introduce Variational Streaming Flow (VSF). Our approach learns a latent distribution that is conditioned on the dynamics of interest. In turn, this enables probabilistic forecasting. Importantly, we retain the computational efficiency of SF by generating in physical time. Across deterministic and stochastic dynamical systems, VSF demonstrates superior predictive accuracy and distributional fidelity. We demonstrate the advantage for both long-horizon rollouts exceeding 1,000 steps, and settings with bifurcating dynamics. Moreover, VSF can be integrated into existing Joint-Embedding Predictive Architecture (JEPA)-based world models as a plug-and-play predictor to improve temporal dynamics and goal-directed success rate in navigation, motion planning, and manipulation.

Science teachers frequently search for documentary excerpts not by describing what appears on screen, but by querying the abstract concepts they intend to teach. This use case exposes a limitation of existing language-based video moment retrieval methods, which typically assume that queries describe observable events, whereas instructional search requires retrieving concrete visual phenomena that instantiate an underlying scientific principle. We study this setting as concept-to-example video retrieval, an abstract-needle-in-a-haystack problem where compact curriculum concepts must be grounded in temporally sparse documentary evidence. To bridge this abstraction gap, we propose Concept-Driven Domain Adaptation (CDDA), a three-stage framework for adapting two-tower vision-language models to concept-level retrieval. CDDA treats concepts as intermediate semantic anchors: it first structures the textual embedding space with textbook and teacher-handbook example-concept pairs, then transfers this concept-aware geometry to documentary visuals under a frozen visual encoder, and finally jointly adapts both encoders with sparse visual concept supervision. From a geometric perspective, this staged alignment reduces text-concept and vision-concept angular gaps, thereby encouraging concept-level adaptation while preserving the pretrained model's concrete image description alignment. On a curated middle-school physics retrieval benchmark, CDDA achieves stronger pedagogically oriented concept retrieval than several competitive multimodal baselines, including Qwen3-VL-Embedding-2B, while maintaining concrete image-text matching after adaptation.

As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened with a fixed base model, without access to reference answers or grading rubrics at test time. Repeated sampling yields multiple rollouts that can contain complementary correct claims, but we need a reliable verification mechanism to determine which claims to trust. We first find that disagreement often exposes correct alternatives, while consensus can conceal errors. These observations motivate VeriHarness, which turns the underlying LLM a generator uses into an agentic verifier by giving it a workspace, evidence tools, and reusable verification skills. A disagreement resolver checks competing claims against environmental evidence, while a consensus challenger tests shared claims and searches for omitted requirements. Their findings guide the selection and revision of the final artifact. Across five long-horizon workspace benchmarks and two frontier models, VeriHarness achieves the highest selection scores among the evaluated baselines. Evidence-backed revision further improves average performance, bringing gains over a single rollout to 6.2 points with Gemini 3.5 Flash and 6.4 points with Claude Opus 4.8. We further show that verification skills can self-improve from failure feedback, demonstrating VeriHarness as a novel and critical approach for scaling long-horizon agentic verification. We release the full pool of approximately 26,000 rollouts across all five benchmarks and both models, produced at a cost of over $100,000, to support future research on agentic verification.

Large language models (LLMs) have been increasingly used for financial document analysis, including earnings call transcripts (ECTs). Beyond generating standalone claims, users increasingly prefer grounded analyses that pair claims with verifiable citations from source documents to enable independent validation. However, evaluating such analytical claims typically requires extensive expert annotation, which is costly and difficult to scale, and real-world financial analysis commonly involves long context-question-answer triplets, further increasing task complexity. To address these challenges and benchmark the current landscape of grounded analysis by LLMs, we propose a numeric evidence evaluation method that enables groundedness assessment without reliance on expert annotation. We also introduce an automated dataset construction pipeline and construct ECTs-100 from the top 100 constituents of the S&P 500 to support benchmark of both groundedness and correctness. In addition, we examine conscious incompetence, a practical failure mode in financial analysis in which LLMs must detect when available evidence is insufficient and refrain from producing unsupported hallucinations. Empirical results show that LLMs perform well in groundedness but face notable limitations in correctness, with informational insufficiency presenting an additional challenge.

Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the causal structure a priori, yet different structures demand fundamentally incompatible invariance constraints, and misspecification leads to representations that discard predictive information. We introduce SaCRL, a framework that jointly identifies the causal structure and learns the corresponding invariant representation without prior structural knowledge. Our approach formulates structure selection as a soft optimization over candidate invariances using HSIC-based violation metrics, with adaptive weights that automatically concentrate on the achievable structure. We provide theoretical guarantees for structure identification, including under random-feature approximation, invariance satisfaction, and out-of-distribution generalization. Empirically, SaCRL recovers the true structure on synthetic and semi-synthetic Bayesian-network benchmarks, outperforms fixed-invariance baselines on Colored MNIST, achieves state-of-the-art accuracy on three DomainBed benchmarks (PACS, VLCS, OfficeHome), and degrades gracefully under structural misspecification and limited environment diversity. Code is available at: https://github.com/ArmanBehnam/sacrl.

For small merchant businesses (SMBs) whose catalogs fit within a long-context LLM, full-catalog prompting offers a compelling alternative to multi-stage retrieval designed primarily for large marketplaces with millions of items. However, fitting the full catalog into the context window does not ensure that the model can use it effectively, since LLMs do not exploit long contexts uniformly. We therefore study in-context catalog search through two complementary questions: (1) how to curate and present catalogs to the LLM, and (2) how to adapt the LLM for product selection on curated contexts. We propose RPTune, an end-to-end framework that couples learned catalog curation with LLM post-training using automatically generated, catalog-grounded supervision. An encoder-reorganizer curator orders and prunes products guided by downstream LLM feedback, while the resulting curated catalogs in turn improve the effectiveness of LLM post-training with a context-relative reward. We evaluate RPTune on 7 real merchants spanning distinct retail verticals, using 100 complex conversational queries per merchant. RPTune consistently improves search accuracy across both proprietary and open-weight LLMs, with context curation yielding gains of up to 31.4 percentage points and post-training adding a further 10.3 points on average.

As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it --- a shift CS-education researchers have begun to name. This shift exposes a vocabulary gap: the field asks for "human oversight" without a working distinction between the two things language does in a delegation channel --- coordinate action (cybernetic: words succeed when the world comes to match them) and coordinate understanding (epistemic: they succeed when they answer to the world and a hearer can check that they do). The failure this names is not cybernetic language but epistemic-form language doing cybernetic work: explanation-shaped output calibrated for approval rather than truth. Oversight that checks only whether an output was approved is satisfiable by rubber-stamping; oversight that holds an agent accountable requires the reasoning behind its work be retrievable and checkable. We present three delegation episodes --- illustrations, not controlled evidence --- in which epistemic engagement proved practicable while remaining auditable, one public record where a recommendation was withdrawn on its own stated terms, and one failure case illustrating oversight that requires no reasons for its discretionary choices. We propose a criterion for agentic-system governance, alongside existing technical trust properties: every consequential choice should carry the condition under which it would have gone otherwise, in a form a third party can test. Without such a condition, a third party cannot distinguish a decision from a rubber stamp. We give the criterion an operational form --- a two-part reconstruction test scoring a delegation record by whether a second reader can predict what the agent does under a perturbation --- and a deliberation-recording convention, ORRCF, that makes the condition a required component of every recorded choice.

A video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence. We introduce the attack pyramid, five levels of shortcut attacks with increasing access to each item, and audit 115 video benchmarks with it. On 35 benchmarks, attackers that never see a frame approach full-video accuracy. On 51 benchmarks with temporal probes, shuffled frames keep a median 96% of full-video accuracy. Near-duplicate questions make up at least half the items in 63 benchmarks. We screen 505,518 question-answer pairs from 112 of them into an audited pool. Agents turn evaluation requests into specifications, and a deterministic selector with a red-team gate composes reproducible benchmarks. We release Video-Index, the 210 hardest verified items under these attacks in each of four capability groups, 840 items from 76 sources. With the same fixed input, Claude Opus 5 outscores every open-source model by over 37 percentage points, and agent tools add about 20 more, yet all systems leave room to improve efficiency and accuracy. Blog: https://www.enxinsong.com/blog/video-index/ GitHub: https://github.com/Espere-1119-Song/Video-Index Hugging Face: https://huggingface.co/datasets/Video-Index/Video-Index

Large language models often lose track of persistent instructions and relevant information as multi-turn conversations grow. We study this cumulative contextual decay through three related failure modes: attention pollution, dilution, and drift. We propose REA (Role-aware Heuristic Episodic Attention), a context-management framework that assigns different persistence and representation policies to instructions and episodic interactions. Instructional Memory retains identified global constraints in a dedicated prefix. Episodic Memory preserves user inputs and compresses model replies, while heuristic retrieval selects raw text, compressed representations, or omission for each historical turn. On Long-MT-Bench+, REA improves the judge score from 6.32 to 7.36 on a 10-point scale, a 16.5% relative gain over the Vanilla baseline, and reduces average latency by 2.91$\times$. Additional evaluations show aggregate gains on three backbones spanning 1.7B-7B parameters and on Chinese and English role-playing tasks. These results support role-aware context management as a practical approach to maintaining conversational continuity and instruction adherence.

As large language models (LLMs) move from standalone assistants into agentic workflows, evaluation must extend beyond scalar leaderboard accuracy to account for operational reliability, cost, latency, and token efficiency. We use an agentic ensemble of small language models (SLMs) with an SLM-judge-mediated feedback loop as a case study for such beyond-leaderboard evaluation. On the 541-prompt IFEval benchmark, the best ensemble achieves 97.34% strict prompt accuracy, exceeding the strongest standalone LLM baseline, gpt-5.4, by 5.81 percentage points while operating in a lower-cost regime. We then analyze the tokenomics and operational behavior behind this gain, including cost per sample, token composition, useful-output goodput, feedback-loop recovery, latency decomposition, and performance across instruction categories and constraint counts. Our results show that agentic SLM ensembles can trade additional test-time tokens and orchestration overhead for improved instruction-following fidelity, motivating multi-dimensional evaluation protocols for future agentic AI systems.

An answer candidate in a masked diffusion MLLM can stabilize while its rationale is still unfolding. We distinguish retrospective stabilization of the logged candidate from token commitment, and examine these two clocks relative to rationale generation. Analyzing our results across three visual question-answering benchmarks, we find that 89.4-98.1% of the rationale-side canvas remains unwritten at stabilization in single-block, EOS-suppressed LaViDa runs. On V*Bench, reducing block length from 128 to 8 changes this fraction from 89.4% to 1.7%, together with answer coverage and the eligible observation window. Under EOS-enabled prompting, direct instructions improve Nemotron's overall accuracy by 15.0 and 19.5 percentage points on M3CoT and ScienceQA, but reduce LaViDa/V*Bench accuracy by 11.0 points. A symmetric decomposition associates the larger absolute component of each change with coverage rather than conditional accuracy. Matched-canvas image ablations measure visual sensitivity alongside answer stabilization, separating the two temporal readouts. Together, these measurements distinguish answer stabilization, rationale unfolding, and visual sensitivity, and identify coverage as the larger component of the prompting differences.

Recaptioned image-text corpora are now standard for text-to-image (T2I) training, with vision--language model (VLM) captioners replacing sparse alt-text by dense descriptions. A recaptioned corpus is a supervision distribution induced by a documented captioning policy ($π$), captioner ($V_c$), and source corpus ($C$). Length-correlated proxies miss caption-register artifacts and downstream T2I benchmarks entangle the corpus with training choices, so this distribution is hard to audit at corpus scale. We introduce a reusable matched-budget audit framework for recaptioned supervision distributions $D_{π,V_c,C}$: at a fixed text budget of $B = 64$ it reports a five-axis profile spanning prompt-side coverage, image-conditioned faithfulness, and caption-surface health, with claimed controllable basic units (CBU) as the common claim unit. We instantiate the framework on seven paired comparisons over five public source corpora. Across the four cross-corpus pairs, the released surface raises supported CBU per caption by $+3.39$ to $+6.36$ under both Qwen and Gemma Judges, and on CC12M the same framework exposes a long-vs-dense frontier that is consistent across both judges and four budgets. We release the audited multi-source recap corpus ($\approx$ 490M) together with the audit-artifact bundle.

Supervised fine-tuning (SFT) on offline agent trajectories is the standard approach for training specialized tool-using agents, but forcing models to imitate reasoning and actions token by token may harm other capabilities (e.g., general reasoning, tool calling, code generation) of the base model. In this work, we focus on studying \emph{how to better balance the trade-off between acquiring new capabilities and preserving existing ones during agent trace SFT}. By comparing several baselines in our setup, standard SFT improves the target benchmark while lowering several non-target benchmark scores; meanwhile, simply constraining distributional drift using KL penalty or limiting the update magnitude did not avoid this regression trend. Motivated by recent token-wise adaptive learning objectives, this work proposes \textbf{Privilege-Guided SFT (PG-SFT)} to leverage turn-level information gain of agent trajectories as an indicator to adjust supervision strength. PG-SFT yields a more favorable observed trade-off on the evaluated benchmarks, substantially reducing distributional drift and broad capability degradation at the cost of slight degradation in target-task performance. Our findings suggest that balancing the acquisition--retention trade-off depends not only on whether the model is anchored to its base behavior, but also on where and how strongly supervision should depart from that behavior.}

The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled. Compared with harness optimization for non-GUI agents, automatically optimizing this harness poses three coupled challenges: reconciling model intent with observed visual effects, diagnosing failures under variable execution outcomes, and identifying recurrent failure patterns across tasks and translating them into reusable runtime changes. We introduce GUI-HARVEST, an automatic harness optimizer that enables self-improving GUI agents with frozen backbone models. First, to ground diagnosis in observed action effects, it aligns model outputs and executed actions with before-and-after screenshots, tying findings to specific interface transitions. Second, to account for execution variability, it treats repeated runs of the same task as a joint evidence unit, using within-task comparisons to locate outcome-relevant behavioral differences. Third, it consolidates verified findings across tasks into recurring failure patterns, maps them to bounded source-code edits with predictions recorded before evaluation, and checks the predicted behavioral effects alongside task performance through repeated execution. Experiments on OSWorld-Verified show consistent held-out gains across six general-purpose open, GUI-specialized open, and proprietary backbone models; Qwen3-VL-32B-Instruct gains 12.33 points on the full suite. Frozen-harness transfer improves GPT-5 by 13.87 percentage points on WindowsAgentArena at 50 steps without further optimization. With the same backbone and initial harness, GUI-HARVEST outperforms Self-Harness and Meta-Harness, suggesting that GUI-specific diagnosis and validation help harness improvements generalize to unseen tasks. The code is available at https://github.com/GaryYang12345/GUI-HARVEST.

We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questions along multiple paths before the final answer. It iteratively plans a horizon of candidate intermediate questions, selects one to answer, and replans from the updated history. ReHoPER is task-agnostic, using the same generic instructions across datasets and models without labeled data or task-specific prompt design. Across multiple datasets, including iLLC, a new controlled benchmark for compositional reasoning, ReHoPER outperforms strong baselines, with the largest gains in the most compositional settings. Our implementation and the iLLC generator are publicly available to support future work.

Post-training quantization for diffusion models increasingly exploits timestep, feature, and layer structure. While recent work has begun incorporating CFG structure into diffusion quantization, activation quantization still operates independently across conditional and unconditional coordinates, leaving cross-activation structure unexploited. We show that matched CFG activations form a strongly correlated two-dimensional source and that, under a fixed bit budget, the choice of branch coding basis materially affects quantization fidelity. Motivated by this observation, we introduce branch-space transform coding, which rotates matched CFG branches via an offline derived 2x2 orthogonal matrix, requiring minimal modifications to model parameters or the quantization pipeline. We further derive the Guidance-Correlation Branch Transform (GCBT), which jointly incorporates the CFG guidance direction and cross-branch second moments. Under an equal-rate quantization-noise surrogate, GCBT admits a closed-form per-layer solution without gradient optimization or angle search. Applied on top of existing diffusion PTQ methods, GCBT yields statistically significant fidelity gains in most evaluated comparisons with no statistically significant degradation, while leaving the underlying host quantization pipeline unchanged.

We study episodic adversarial linear constrained Markov decision processes (CMDPs) with unknown transitions, where both the loss and constraint functions may vary adversarially across episodes. The best previous algorithm achieves $\widetilde{\mathcal{O}}(K^{3/4})$ regret and cumulative constraint violation, leaving a gap to the optimal $\widetilde{\mathcal{O}}(\sqrt{K})$ dependence on the number of episodes $K$. We close this gap by proposing a new primal dual algorithm that achieves $\widetilde{\mathcal{O}}(\sqrt{K})$ regret and cumulative constraint violation without assuming Slater's condition. The main challenge is that learning linear CMDPs requires uniform concentration over a value function class with a controlled covering number, whereas standard techniques in constrained online learning, such as policy mixing, can make this class more complex. Our algorithm combines adaptive Follow the Regularized Leader (FTRL), contracted value estimation, and an exponential Lyapunov function. An adaptive dual regularizer offsets the dependence on the dual weights in the primal regret bound, removing the need for policy mixing. We further show that the normalization in the FTRL update bounds the policy parameters independently of the magnitudes of the dual weights, which explains why the resulting policy class remains compatible with uniform concentration. Under feature access, the computational complexity is independent of the size of the state space.

This paper studies communication-aware safe control for discrete-time linear multi-agent systems under limited information exchange. The main challenge lies in the coupling between remote-state estimation and safe controller design, since estimation errors affect the state evolution through the controller gains, while the controller design must account for the resulting observer-induced state perturbations to guarantee safety. To address this challenge, a distributed k-hop observer is developed to reconstruct unavailable remote states, and a uniform observer-error bound is derived. The effect of the observer-induced state perturbation on closed-loop safety is accounted for in both the construction of local εi-robust safe invariant (RSI) sets and the enforcement of pairwise relative-state safety constraints. The resulting safety conditions ensure that all agents remain within their local RSI sets while all pairwise relative-state safety constraints are satisfied. A linear matrix inequality (LMI)-based optimization method is developed to jointly synthesize the distributed observers, local controllers, and RSI sets. A case study illustrates the effectiveness of the proposed method.

The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribution sampled in its next iteration. A scoring error can therefore change both the present decision and the candidates considered later. We evaluate these two roles separately. Four types of predictive model generate CEM traces, and every model rescores every saved candidate pool. Executing the same candidates in the environment provides a reference elite set and proposal update. Across twelve independently trained task-seed units on Walker and Cheetah, the pre-specified proposal distance falls from the first to the final CEM iteration in every unit. Proposal widths contract and fitted means separate relative to the remaining search width. Pairwise ranking agreement stays near chance on Walker and declines on Cheetah; elite-set agreement does not improve. This comparison shows greater variation between scorers than between pool sources on Cheetah; Walker has variation in both and in their pairings. We use the original six units to select Random nonlinear for a one-update intervention, without inspecting intervention outcomes. Replacing its first model-ranked update with an environment-ranked update lowers final realised selected-sequence cost in those six units and in six further units held out from the selection.

Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing stays strong when the setting changes. We evaluate 66 configurations: four configurable harnesses (OpenHands, DeepSeek Harness, PI, and openJiuwen) paired with five models on TUA-Bench, ALE-CLI, and Terminal-Bench 4, plus the native Codex-GPT and Claude Code-Claude pairings. Model rankings reverse across harnesses. On Terminal-Bench 4, Claude leads GPT by 7.94 points in OpenHands but trails it by 30.16 points in PI. For four of the five models, the best harness changes from one benchmark to another, yet some pairings hold: openJiuwen gives Kimi its highest score on all three benchmarks, by 5.61 to 11.11 points. A model's own vendor harness is not reliably its best, and higher cost does not reliably buy a higher score. On Terminal-Bench 4, GPT scores higher under PI than under DSH at less than a quarter of the cost per task. Matched trajectories suggest why fit varies. Models start almost all repairs themselves, so much depends on whether the harness hands failures back in a form the model can use. GPT does best with PI's lean scaffold, while Kimi, which often issues malformed tool calls, does best in openJiuwen. We argue that the model, the harness, and the task should be evaluated together, and we release the harness adapters, evaluation code, and all 6,204 scored trajectories at https://github.com/liyix/finding-the-right-fit and https://huggingface.co/datasets/yixuanli97/finding-the-right-fit.

Vision-Language-Action (VLA) models provide strong behavioral priors for robotic manipulation, yet efficiently adapting them to downstream tasks remains challenging. Recent work addresses this challenge by adapting frozen VLAs through online reinforcement learning (RL), whose sample efficiency depends on the quality of the state representation used by the actor and critic. Existing methods construct such representations either with VLA-independent visual encoders or through fixed compression of internal VLA representations. Neither design explicitly extracts the task-specific action-relevant VLA features most useful for downstream action refinement and action-value estimation, therefore limiting sample efficiency. To address this limitation, we introduce eRLT, which constructs an effective state representation by routing task-specific action-relevant information across both tokens and layers of the frozen VLA. Specifically, learned routing tokens dynamically aggregate visual-language features at multiple depths, while a lightweight layer router combines these summaries into a fixed-dimensional RL token. The routing module is initialized using expert demonstrations to capture features predictive of expert actions and then refined using critic feedback from online interactions for action-value estimation. Across seven LIBERO and RoboTwin tasks, eRLT improves mean normalized learning-curve AUC by up to 23.7% over representative baselines. Real-robot experiments on USB connector insertion and motherboard ribbon-cable insertion further show AUC improvements of 108.9% and 46.7%, respectively, over the strongest baseline.

Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A solver can then return an optimal solution to the wrong problem. Even when the solution satisfies the intended operating rules, a better plan may exist. For organizations that repeatedly use optimization modeling, an LLM-based framework should produce accurate formulations at low cost and, ideally, run locally. We study how to verify improvements and allocate attempts across LLMs that differ in price and capability. We develop OSCAR (Optimization modeling by Simulator, Coder, And Reviewer), which uses an offline Simulator certified against labeled decision examples to compare candidates and continues searching beyond feasibility. We model the search for the next certified improvement as sequential decisions under unobserved difficulty: which LLMs to call and when to stop. In a simplified known-prior setting, we give conditions under which cost-ordered escalation is optimal. For general menus, we derive a prior-free competitive guarantee. On five benchmark problems, OSCAR achieves 95% to 100% accuracy at the reported settings using two small open-weight LLMs, each deployable locally on a single GPU. Their single-attempt accuracies average 29% and 48%. In five runs per problem, Codex and Claude Code incur average token costs 3.1 and 5.8 times OSCAR's, respectively. OSCAR supports open-weight models locally or in the cloud, depending on budget and confidentiality requirements. Firms should maintain labeled decision examples of feasible and infeasible decisions to clarify plain-language operating rules. OSCAR follows these labels when an LLM's interpretation conflicts with them. As LLM capabilities and prices change, OSCAR's simple operating rules and adjustable settings help firms adapt their model choices and benefit from these advances.

We study an endogenous nonstationary stochastic bandit problem with latent linear dynamics, where actions affect both immediate rewards and the future evolution of an unobserved latent state. Rewards are bilinear in the current action and latent state, inducing history-dependent rewards and a nontrivial long-horizon planning problem. The existing explore-then-commit approach achieves $\tilde{O}(T^{2/3})$ regret by uniformly exploring to estimate the latent dynamics and then committing to an optimized open-loop action sequence. We show that this rate can be improved via adaptive block-level optimism. Our key step is a cyclic approximation: under stable dynamics, the infinite-memory reward process can be truncated, and the open-loop benchmark can be approximated by optimizing a finite-memory block-level proxy. Building on this reduction, we propose a UCB-based block algorithm that maintains confidence sets for the truncated dynamics parameters and selects blocks optimistically. We prove a regret bound of order $\tilde{O}(\sqrt T)$, significantly improving over the previous $\tilde{O}(T^{2/3})$ guarantee for the same model. To the best of our knowledge, this is the first $\tilde{O}(\sqrt T)$ regret guarantee for latent linear-dynamics bandits with bilinear reward observations and an open-loop action-sequence benchmark.

Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, existing methods primarily optimize how the harness is updated while largely fixing which training scenarios generate the feedback that drives those updates. As the harness evolves, the scenarios most useful for further optimization can change, suggesting that the training curriculum itself should adapt alongside the harness. We formulate this missing dimension of harness optimization as an automated curriculum learning problem and introduce ActiveSaddler. ActiveSaddler models the evolving curriculum as a non-stationary bandit with dynamically instantiated optimization targets. It abstracts recurring failures into reusable failure-pattern arms, estimates the potential learning progress from further targeting each pattern, and adaptively balances revisiting known weaknesses with exploring unseen scenarios for new ones. Optimization outcomes continually update both the set of discovered failure patterns and their priorities, allowing the curriculum to co-evolve with the harness. Experiments on GAIA2 and Terminal-Bench 2.0 show that ActiveSaddler consistently discovers stronger harnesses, improving test Pass@1 by 4.4 and 7.5 percentage points over the same harness optimizer using a scenario order fixed before optimization, respectively. Ablations further show that these gains depend on dynamically constructing optimization targets, estimating their evolving utility, and balancing continued optimization with new failure discovery. Together, these results establish automated curriculum learning as a new crucial optimization dimension for harness optimization.

With the advancement of LLM-based multi-agent systems (MAS), an increasing number of opensource projects are adopting multi-agent architectures as the foundation of their core functionality. Although research and practice on MAS have attracted considerable attention, limited studies have explored the challenges faced by practitioners of open-source LLM-based MAS, the causes of these challenges, and potential solutions. To address this gap,we conducted an empirical study to understand the issues that practitioners encounter when developing and using open-source LLM-based MAS, the possible causes of these issues, and potential solutions. We collected 22,848 closed issues from 21 open-source LLM-basedMASand applied a mixed automated and manual filtering approach to reduce the dataset to 944 issues related to LLM-based MAS.We then analyzed these issues to understand the frequent issues encountered by practitioners, their underlying causes, and potential solutions. Our study results show that (1) Orchestration & Execution Issue is the most common issue faced by practitioners, (2) Workflow Problem, Tool Integration Problem, and Memory Problem are identified as the most frequent causes of the issues, and (3) Optimize Workflow is the predominant solution to the issues. Based on the study results, we derive empirically grounded implications for practitioners and researchers aimed at improving orchestration, tool integration, and memory mechanisms in LLM-based MAS.

Learned manipulation policies rediscover from data the spatial relations that rigid-body mechanics supplies in closed form. This costs data, and it leaves the policies fragile to geometric changes in the scene. We present Screw Attention, a transformer layer in which the relation between two bodies is a spatial transform rather than a graph edge. Every token is a body with a pose. Each pair of tokens carries the relative pose and, for robot joints, the joint screw. Messages are transported along this relation into the receiver's frame, while the attention scores see only frame-invariant quantities. By construction, the messages are equivariant to an independent change of frame at every token, and a single layer can express the velocity recursion of rigid-body mechanics. On simulated manipulation tasks, Screw Attention matches or outperforms controls of the same size, including graph, transformer and flat networks on LIBERO-Spatial. With 16,162 parameters it reaches 97.3% on LIBERO-Spatial from object poses (without images or language), above a flat network with 27x more parameters. Under a change of per-link frame convention its success is unchanged, while every other learned network falls below 3%. Placed on an analytic controller as a gated residual, it raises insertion success by 17.3 points. It is unaffected by pose noise up to 10,mm and by joint offsets within the factory calibration of a Franka arm. These results suggest a criterion: geometry is decisive when the task requires relations between frames that no other part of the system supplies. Code and trained policies will be released.

Test-time reinforcement learning (TTRL) adapts language models on unlabeled test problems using supervision derived from their own samples. This makes the checkpoint's \emph{entry state} consequential: a diffuse policy provides noisier self-supervision and may spend much of a limited adaptation budget merely concentrating probability mass before reliably expressing capability it already possesses. We propose \textbf{entry-state sharpening}: use data-free training \emph{before} TTRL to prepare a general-purpose checkpoint in a state that subsequent label-free adaptation can exploit more efficiently. The idea is not tied to one training recipe; different data-free objectives can move the same base model to different entry states. Across five data-free checkpoints derived from Qwen3-4B and evaluated under an identical 15-step TTRL protocol, entry policy entropy strongly rank-orders endpoint conversion efficiency, a reliability-to-reachability measure (Spearman $ρ=-0.90$; $ρ=-0.99$ after controlling for entry reachability). The contrast across objectives is striking: R-Zero remains diffuse at $3.39$ nats and finishes below the untuned base in 6/6 matched comparisons across MATH, GPQA, and AMC, whereas SPIRAL reaches $0.07$ nats and achieves the highest post-TTRL accuracy on MATH and GPQA despite its self-play stage using no math training data. An in-domain label-free self-distillation intervention further shows that the entry state can be deliberately sharpened. These results motivate treating checkpoint preparation as a \emph{state-control problem}: use data-free training to improve TTRL readiness, with entry entropy as a label-free control signal and reachable capability as the constraint.

One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' characteristics as partly unknown and ask what structure of interaction ensures that bad collective outcomes are not equilibria. Mean field games suit this when many interchangeable agents are coupled through an aggregate. We introduce a program for using them in AI safety and carry one example through end to end: the July 2026 incident in which about 1,200 agents in an OpenAI evaluation coordinated on an improvised message board and 684 attacked a third party's infrastructure. We model the decision to attack as a mean field game of optimal stopping whose gain is a product: belief that provenance will be audited, times reachability of the record, minus the perceived hazard. The central result is an exact threshold on the belief. No agent attacks unless the population's confidence that provenance is checked exceeds $π^{**} = η/(η+ ψ+ \varepsilon a \overline{M})$, where $η$ is the perceived hazard, $ψ$ and $\varepsilon a \overline{M}$ measure how far one attacker and the collective can alter the record, and $\overline{M}$ is the peak population. Below it, no attack is the unique equilibrium for all agent parameters. The threshold survives every enrichment we consider. We then use the per-agent record to discipline the model. Its features, a stable minority attacking for thirty hours and then a pivot in which most of the board joined within a day, motivate each refinement. The account that emerges is heterogeneous belief meeting a sequence of public discoveries, each lowering the belief at which attacking paid. A few coordinating agents made those discoveries, so the model describes the several hundred who responded, not the few who produced them; a major-player version is left to future work.

Autoregressive Vision-Language-Action models often represent continuous robot actions as discrete token sequences, enabling action prediction with standard next-token objectives. FAST has substantially improved this representation by compactly encoding action containing diverse temporal frequencies into relatively few tokens. However, while such compression reduces the number of action tokens required for autoregressive prediction, it does not necessarily improve the efficiency of policy learning from limited demonstrations. In particular, FAST typically assigns a single deterministic tokenization to each quantized action sequence, although multiple token sequences can represent and decode to the same robot motion. We investigate whether exploiting this representational redundancy can improve policy learning. In this paper, we propose TOkenization of Action sequences with STochastic sampling (TOAST), a stochastic action tokenization method that samples alternative tokenizations of the same quantized action sequence during policy training. This diversifies the discrete supervision while preserving the underlying robot action and requires no additional demonstrations. Experiments on LIBERO show that TOAST consistently improves over its deterministic counterpart, with the improvement increasing as training data decreases, achieving a 6.8 point gain in success rate when only 1/16 of training data is available. Across four real-robot manipulation tasks, TOAST further improves mean success rate by 15.8 points over the deterministic counterpart. These results demonstrate the effectiveness of stochastic action tokenization for autoregressive robot policy learning, particularly when training data are limited.

Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biological text. Their benchmark accuracy is taken as evidence that LLMs reason over these inputs. We test this assumption in six biological reasoning models across DNA, protein, and single-cell tasks. We perturb one biological input while holding the query and other inputs fixed, construct evidence conflicts that pair the foundation model representation of one genome, protein, or cell with the text of another, fit linear probes to the representations the language model receives, and analyze reasoning traces against the biological inputs. Evo2 and ESM3 contribute little to BioReason and BioReason-Pro performance on the evaluated tasks. Shuffling the DNA sequence barely changes BioReason disease prediction accuracy, and in evidence conflicts the two models follow the text in 97.9% and 99.7% of cases. Linear probes trained on the Evo2 and ESM3 representations predict the task targets, so these foundation models encode information relevant to the task, but provide limited overall performance improvement to BioReason and BioReason-Pro. In contrast, foundation model inputs contribute to ChatNT, Prot2Text-V2, and CellWhisperer performance, and differentially expressed genes in the gene sentence contribute to Cell2Sentence-Scale performance. Across SFT and RL checkpoints of BioReason-Pro and 42 BioReason checkpoints, increases in accuracy do not imply greater performance contributions from biological inputs. BioReason traces misstate nucleotide changes, while BioReason-Pro traces describe functions omitted from final predictions under evidence conflicts. We find that current post-training strategies do not ensure that foundation model representations contribute to task performance.

Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such strategies for classifiers without metadata. For foundation models, no such option exists yet. We propose Disentangled Diffusion Autoencoders (DiDAE). DiDAE wraps a frozen foundation model in a conditional diffusion decoder. A counterfactual is one closed-form edit along a direction of a disentangled dictionary, followed by decoding. The dictionary can be supervised (Procrustes) or unsupervised (Singular Value Decomposition, Sparse Autoencoders). No gradients are needed, so DiDAE is up to 2000 times faster than the state of the art. We evaluate on six datasets, two synthetic and four real-world. In a desiderata-driven benchmark on three of them, its counterfactuals are on par with or better than the state of the art, and they repair downstream classifiers through Counterfactual Knowledge Distillation (CFKD), where they beat metadata-based correction. The same machinery can rank a pretrained dictionary against a trained classifier. It returns the few directions the classifier actually reads, each causally verified by a counterfactual that flips the decision, and repairs the classifier along those a teacher marks spurious. The workflow is plug-and-play in our open-source Peal library we publish alongside the paper. With a public dictionary and a pretrained decoder, all that remains is a cheap linear distillation of the classifier and its own fine-tuning.

Recent works on continuous diffusion for discrete data have demonstrated performance on par with comparable discrete diffusion models. However, these continuous counterparts lack key features that are essential to practical use as language models, namely variable-length generation and support for a key-value cache, and they still lag behind the frontier of autoregressive and discrete diffusion quality. In this work, we address these limitations. We do so by introducing a model parameterization that uses position-dependent noise schedules to define semi-autoregressive (SAR) continuous diffusion language models (DLMs). Together with efficient training and sampling algorithms, we call this framework Clock Diffusion, and we present two special cases of our method: block and sliding window generation. We then define ClockDLMs, a family of Gaussian DLMs based on sliding window Clock Diffusion that attain state-of-the-art diffusion likelihood bounds on OpenWebText, even beating the performant block SAR discrete diffusion models. ClockDLMs trained on TinyGSM also substantially outperform continuous baselines on the GSM8K benchmark and match and exceed comparable SAR discrete diffusion models. Finally, building on our parameterization, we propose more efficient samplers that we dub Cache Grab, which adapt techniques from accelerated inference in discrete diffusion, such as committing tokens whose probabilities exceed a confidence threshold and self-speculative decoding, further improving our models' quality and efficiency.

Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handles, break behavior that was supposed to stay intact, or validate against an unchecked assumption. We ask whether reinforcement learning (RL) on expert-built agentic coding tasks closes this gap, and whether what the agent learns transfers beyond the training distribution. We post-train Kimi K2.7 Code, a 1T-parameter (32B active) open-weight mixture-of-experts model, with RL alone on 1,700 tasks: 1,000 repository tasks graded by hidden fail-to-pass tests and by pass-to-pass tests of existing behavior, and 700 terminal tasks graded by expert-written hidden verifiers. The reward is the fraction of target checks passed and drops to zero if any pass-to-pass test fails. One epoch of GSPO on a rank-32 LoRA adapter improves pass@1 on each of the six external benchmarks we evaluated, across three agent harnesses: SWE-Bench Pro (60.1 to 64.8), DeepSWE (31.0 to 43.4), Terminal-Bench 2.1 (67.4 to 82.0), Terminal-Bench 3 (1.4 to 12.1), Terminal-Bench 4 (0.0 to 7.6), and SWE-Marathon (5.0 to 25.0). Pooled over the five independent task sets (Terminal-Bench 4 revises Terminal-Bench 3), the improvement is significant (p < 0.001), and it remains significant on the three sets released after the training data was collected (p = 0.004); the model also improves under both harnesses never used in training. Median trajectories on DeepSWE and Terminal-Bench 3 are 24-35% shorter in agent steps. The base model's failed DeepSWE runs are mostly near-misses, and on the tasks the trained model newly solves, paired trajectories show it avoiding each of the four failure modes above.

Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineering effort through cost-efficient automation. Decades of research have produced a rich landscape of concurrency control (CC) protocols, each encoding distinct trade-offs in correctness, throughput, and abort behavior. However, most applications in practice default to 2PL or OCC, because selecting and adapting a protocol to a specific application requires expert knowledge that is rarely available to application designers. This is a wasted opportunity, as an application-specific CC protocol can yield significant performance advantages over a generic baseline, but designing one requires deep expertise in CC protocol design. In this paper, we propose HakiCC, an LLM-driven multi-agent pipeline that automatically designs, verifies, and optimizes concurrency control protocols tailored to a given target application. HakiCC provides a two-stage pipeline. In Stage 1, a multi-agent system takes a workload description as input and generates an application-specific CC protocol implementation, which is iteratively repaired and verified for conflict-serializability. In Stage 2, the verified protocol is further optimized for that application through an LLM-driven evolutionary loop targeting correctness and throughput. We evaluate HakiCC on TPC-C and AuctionMark as target workloads, producing and reporting ten application-specific CC protocols. All ten are conflict-serializable after Stage 1; Stage 2 improves throughput for every protocol, with average gains of +50.6% for TPC-C protocols and +92.2% for AuctionMark protocols.

Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per forward pass, while a verification step over draft tokens ensures that token distribution of the backbone is preserved. Every open MTP-family release (MiMo-7B, DeepSeek-V3, Qwen3) trains its heads jointly with the backbone over the full pretraining run of tens of trillions of tokens, thus setting the drafter quality at pretraining time. We ask whether a lightweight post-training pass on target-generated chain-of-thought is enough to reach the same expected throughput speedup on a frozen reasoning model, and study how a serving-time system built on such a checkpoint can be optimized. We present three findings. 1) On a frozen Qwen3-8B with $K{=}3$ chained MTP heads, we show that a post-training recipe with plain cross-entropy on $\approx\!2.5$B tokens reaches or exceeds the expected speedup of jointly trained MiMo-7B on math, coding and knowledge benchmarks. Our post-training recipe utilizes $10^3$-$10^4\times$ less MTP-training tokens as compared with joint pre-training of MiMO-7B MTP baseline. 2) We propose a chain-aware relaxation of draft token verification rule that allows a bounded drift from backbone language model token distribution. We show that this relaxation lifts expected speedups by $+12$ to $+16\%$ per benchmark while preserving task accuracy. 3) We propose an adaptive controller that dynamically chooses the number of MTP heads to be engaged at inference time and demonstrate recovery of upto $11$--$14\%$ loss in speedup using fixed maximum MTP draft length.

Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended statement under acceptable assumptions. We present FORALL-LEAN-AGENT, a frontend-agnostic framework for auditable reasoning in formal mathematics and software verification. The framework combines isolated workspaces, Lean tools, and fresh review with statement comparison, axiom audits, and independent proof checking where supported. Verification evidence and reviewer decisions are bound to the same candidate artifact, making acceptance traceable. We evaluate the framework on VeriSoftBench, PutnamBench, and both problems in the Lean Eval softwareverification track. On the 100-task VeriSoftBench subset, integration with FORALLLEAN-AGENT raises benchmark-rule success from 93 to 100 for GPT-5.6 Sol at low effort while reducing cost from $69 to $62. The PutnamBench evaluation accepts all 672 problems at an average of $4.72 each. These results show that agent harness design can improve correctness and efficiency while providing evidence beyond aggregate solve counts.

General-purpose embodied robots should support both navigation toward language-specified destinations and dynamic person tracking under arbitrary initial target azimuths. However, existing methods typically rely on forward-facing observations and address these tasks with separate policies, limiting omnidirectional perception and unified closed-loop control. We present UniTrackPLA, a unified panorama-language-action model for instruction-guided navigation and dynamic person tracking. Its Panoramic-Aware Encoding (PAE) preserves the temporal and azimuthal structure of perspective views projected from each panorama, enabling perspective-pretrained visual encoders to process omnidirectional observations. A shared vision-language backbone grounds instructions in the panoramic context and predicts continuous robot-centric waypoint chunks for both tasks. World-Action Consistency (WAC) further predicts action-conditioned future visual states and verifies waypoint prefixes online, allowing reliable actions to be reused while triggering replanning upon inconsistency. We also introduce OmniTrackNav-Bench, comprising 5,000 simulated tracking trajectories, 10,000 simulated VLN routes, and 96 verified real-world routes, providing 919,978 waypoint-supervision instances. UniTrackPLA improves overall tracking SR from 23.50% to 35.00% and Omni-VLN SR/SPL from 13.00%/12.77% to 19.75%/19.29%. Incorporating 76 real-world routes further improves held-out [email protected] from 42.92% to 92.08%. Closed-loop experiments on a Go2-W robot demonstrate unified panoramic tracking and navigation across indoor and outdoor environments. The project page is at https://tw5775.github.io/UniTrackPLA.

Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LLM agents to organize and consolidate memory, resulting in costly, inefficient write operations. To address this limitation, we propose MemFit, a long-term memory system for conversational agents that reduces the cost and latency of memory operations. Unlike existing systems that rely on expensive LLM calls for memory construction or discard surface-level details through compression, MemFit stores each turn verbatim in an append-only store with near-instantaneous, LLM-free insertion, indexing turns with segment summaries rather than replacing them. Additionally, MemFit uses an LLM-free, multi-path retrieval strategy that combines lexical and semantic signals with cross-encoder reranking over caption- augmented episodes in both textual and multimodal settings. Empirical results on three widely used benchmarks, LoCoMo, MemGallery, and LongMemEval-S, show that MemFit achieves state-of-the-art performance while reducing memory construction time and cost several-fold, providing a scalable and efficient solution for persistent agentic memory.

We present an educator-guided LLM pedagogical agent for scaffolded feedback in conceptual database design. Integrated into an entity--relationship diagram (ERD) editor, the system grounds feedback in the student artifact, assignment requirements, educator-authored rubrics, and instructional resources. Its architecture separates hidden, artifact-grounded diagnosis from the workflow that controls the form and disclosure level of student-facing support. We instantiate the architecture as a four-stage workflow progressing from concept checks and guided application to low-detail feedback and localized clarification. Each feedback request creates a stateful episode linked to versioned ERD states. In a deployment spanning three ERD environments and 383 feedback episodes, 71.1\% of observed target-level changes fully or partially incorporated the hidden diagnostic target, including many after Stages~1--2. Qualitative analysis showed that staged disclosure sometimes withheld inaccurate details, supported selective uptake, or allowed later recovery, though some errors still shaped revisions. Survey responses from a self-selected sample favored delayed disclosure and student agency but noted indirectness and repetition.

In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. MeanFlow provides a promising framework for this goal, yet its direct application leads to performance collapse. We discover that this stems from two distinctive dynamics exhibited in the RFM velocity field: (1) the ``local acceleration" exhibits stability early on, but surges sharply towards the end of the denoising process, and (2) the spread of its magnitudes across samples widens as denoising progresses. To address these issues, we introduce Kinematic MeanFlow (K-MF), a novel one-step action policy tailored for RFMs. Specifically, grounded in a kinematic identity, K-MF decouples the time derivative term in the MeanFlow formulation into two sub-interval terms separated by an intermediate point. This decoupled formulation enables the two terms to capture early-stage and late-stage denoising dynamics, respectively, while mitigating the error amplification across the process. As a result, our K-MF empowers RFMs to achieve one-step action generation in both training from scratch and fine-tuning paradigms across diverse tasks, while outperforming multi-step flow matching in most settings. In terms of inference efficiency, K-MF reduces action-head latency of GR00T-N1.6 by 67.5%~74.4% across L40 and Jetson Orin in eager and compiled modes, yielding end-to-end latency reductions of 30.3%~54.9%. Code will be available at https://github.com/IntelChina-AI/K-MF.

World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video simultaneously, but such training paradigms introduce a mismatch: perturbed actions imply counterfactual future visual, while the noised video remains tied to the GT recording. In low-noise regime, the scene geometry and even the dynamic behavior remain clearly visible from the noisy future frames despite the added noise. We present CtrlWAM, which executes perturbed actions in a simulator and pairs them with their noised visual consequences for joint WAM learning. To accommodate the different denoising requirements of video and actions, we introduce warped video--action noise schedules that aim to keep visual layout responsive as action predictions evolve. We further extend the action interface from ego-only control to a variable number of agent streams, allowing a unified model to represent predicted or commanded futures for multiple agents. Driving experiments show more accurate action forecasts, closer agreement between generated video and actions, and better following of supplied commands; robotics experiments show stronger motion fidelity and controllability. Matched controls support the benefit of off-path renders for command following and manipulation fidelity. Together, these findings contribute to a more controllable world action model. Project page: https://ctrl-wam.github.io/

Accurate 3D semantic perception is critical for safe autonomous navigation. However, supervised LiDAR segmentation remains tied to closed taxonomies and to the cost of point-wise manual annotation. Open-vocabulary methods avoid that cost by projecting the output of 2D vision-language models onto LiDAR and distilling it into a 3D network. These methods rely almost exclusively on voxel-based sparse convolutions, and point transformers have so far been limited to indoor environments, where 3D data is dense and bounded. We present Lang3DSeg, which establishes a point transformer as the backbone for annotation-free open-vocabulary segmentation of outdoor 3D LiDAR, and is trained from scratch without geometric pre-training. This training paradigm necessitates addressing the inherent noise in 2D-to-3D label projections; specifically, naive projection often suffers from depth ambiguity, where points behind an object are erroneously assigned its semantic label. We therefore composite masks using an explicit class-priority rule and truncate each projected instance at the first gap in its depth distribution, correcting the projection error directly rather than averaging it over registered sequences. Lang3DSeg achieves 52.8% mIoU on nuScenes validation and 41.4% on SemanticKITTI, the highest among published annotation-free methods on both benchmarks. Every 3D semantic segmentation is on a single LiDAR sweep, and inference operates in real-time without running vision-language models.

Frontier vision-language models (VLMs) combine scene estimation, interaction grounding, and executable actions. Understanding how these abilities support complete robotic tasks is central to evaluating their readiness as robot generalists. We introduce Embodied Agent Arena to examine where local competence supports, or falls short of, complete task success across Geometry, Spatial Reasoning, Affordance, Task Planning, and Manipulation. The arena contains 1,000 cases drawn from 32 established sources and GeoProbe, our new benchmark for geometric estimation on Blender renders and real-scene images. A minimal harness preserves source observations and operations while separating metric precision, functional grounding, and native goal completion. We evaluate seven VLMs, analyze Astra's task-specific advantages, and compare richer-observation execution protocols and multi-round review. Across the arena, Astra's advantage is strongest in precise estimation and usable-contact localization; completing coordinated, goal-directed actions remains the key gap to robot generalism.

Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in OSR lies in the inability to model the unbounded distribution of unknown classes during training, often leading to the misclassification of samples from these classes. Rather than modeling unknowns, recent work shapes the feature space so that known classes are compact and well separated, and spherical representation learning methods have achieved strong results this way. Label smoothing has been identified as one of the key drivers of this success, yet it applies the same coefficient to every training sample, regardless of how well each sample is already embedded. We show that the spherical representation learning objectives used in OSR share a single alignment--uniformity structure in which labels enter only through the alignment term. Label smoothing therefore acts as an alignment dial, and a fixed coefficient sets this dial to the same value for every sample. We propose a plug-in, SmoothOperator (SmoothOP), which sets the smoothing coefficient of each sample from its \textbf{prominence}, an embedding-space signal measuring how clearly the sample's own class stands out against its strongest competing class. Our method integrates into four existing spherical representation learning methods at minimal training overhead. SmoothOP assigns strong smoothing to samples with high prominence, which reduces their alignment and relaxes their pull. On the Semantic Shift Benchmark, SmoothOP-augmented variants generally outperform their base objectives across datasets, degrees of semantic shift, and OSR post-processors, with gains of up to 4.7\% in AUROC, OSCR, and closed-set accuracy.

Existing approaches to offline goal-conditioned reinforcement learning (GCRL) struggle with long-horizon tasks. Discounting shrinks value differences between distant states until they fall below the function approximation error, leaving the agent with no signal for ranking states. Temporal abstraction, which treats k environment steps as a single transition, restores this signal at long range, but no single fixed k suits all state-goal distances: large k preserves value differences across long temporal distances while collapsing distinctions between nearby states, and small k does the reverse. We make this trade-off explicit and introduce Generalized Implicit Temporal Abstraction (GITA), which conditions a single value function on k. GITA trains one policy by aggregating advantage-weighted supervision across multiple k values, so scales assigning larger positive advantages to a state-goal pair contribute more strongly to its update. GITA does not need to choose between local resolution and long-range signal; it retains both without committing to a single k. On OGBench, GITA outperforms a broad range of offline GCRL baselines, raising average success rate across all tasks by 25 percentage points (73% relative improvement) over HIQL. It also improves over the strongest fixed-k method, OTA, by 7 percentage points (14% relative).

Machine learning models are increasingly used in feedback control loops for nuclear fusion, where inference speed and predictable timing are critical. We summarize lessons from models deployed for control on the DIII-D tokamak and develop a benchmark to compare inference backends across ten neural networks and model components from fusion control and diagnostic pipelines. For models greater than five million parameters, the CPU backends take tens to thousands of milliseconds, while GPU inference is substantially faster, suggesting an upper limit on CPU-oriented development for control. These results show why the deployment backend must be selected together with the model and its control-cycle budget.

For quantum machine learning, the exact boundary between classical and quantum advantage is still poorly understood. Direct comparison between quantum neural networks (QNNs) and existing classical models, which encompass fundamentally different function classes, often fails to provide broader insight into the difference between the two. Inspired by the techniques of Neural Quantum States and Random Fourier Features, this work introduces Neural Fourier Surrogates (NFS), a stochastic classical neural network architecture for efficiently learning coefficients over the same finite Fourier series support as quantum neural networks. Testing on a selection of tabular benchmark datasets, we find that NFS is an effective classifier architecture broadly competitive with established classical baselines, including a comparable Random Fourier Features model, and possessing comparable performance to data-reuploading QNNs; combined with additional analysis comparing the learned Fourier spectra of QNNs and NFS on synthetic data, these results establish NFS as a natural classical baseline for evaluating QNN performance.

Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error can cause task failure, while trajectory-level rewards provide limited guidance for assigning credit to individual decisions. To address this limitation, we introduce Segment-level Hindsight Advantage Reweighting for Policy Optimization (SHARPO), a credit-assignment mechanism that refines Group Relative Policy Optimization (GRPO) at the level of environment-facing segments. Inspired by the existing on-policy self-distillation (OPSD) method, SHARPO computes teacher-student log-probability gaps within each segment and uses the resulting signal to compute a bounded multiplier on the GRPO advantage. This multiplier is shared by all tokens within the segment, allowing credit to vary across different segments. With Qwen2.5-7B-Instruct, SHARPO outperforms existing baselines on the ALFWorld and WebShop benchmarks, including GRPO, SDAR, RLSD, and StepOPSD.

Text-to-music generation models are trained on massive music collections, creating a growing need for data attribution methods that can quantify the contribution of individual training samples. However, existing attribution methods are difficult to rigorously evaluate due to the lack of reliable ground truth, making it challenging to reliably assess their actual effectiveness. To address this gap, we introduce TrueMuse, a controlled dataset and benchmark for text-to-music data attribution. TrueMuse is constructed by fine-tuning three diffusion-based text-to-music models on carefully curated attribution samples, whose known inclusion in fine-tuning provides controlled attribution targets for evaluation. The benchmark covers four attribution settings, spanning melodic structure, timbral characteristics, artist-level stylistic signatures, and genre-level shared patterns, and includes 133 attributes, 648 fine-tuned models, and 95,456 generated samples across two prompt types. Using TrueMuse, we systematically evaluate existing black-box attribution methods along four dimensions: fine-tuning improvement, prompt-type difficulty, multi-task training, and fine-tuning data size. Our results show that attribution remains challenging, with existing methods exhibiting substantial variation across evaluation settings, highlighting the need for more reliable and generalizable attribution methods for text-to-music generation. Code and Dataset will be released upon acceptance.

ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source harness that represents hypotheses as executable world models and validates them through retrospective transition checks and conditional prediction checks. Under one frozen Claude Opus 5 configuration, Kepler obtained a server-verified 100.00 RHAE on all 25 public games, with no per-game model selection or score-conditioned reruns. On 181 of 183 completed levels, the final Opus attempt used no more actions than the corresponding median-human baseline. The retained board runs used 8,256 environment actions, of which 7,292 occurred in scored levels. Retained local provider-session records yield 858.0 million tokens, 97.37% cache reads, and a \$777.72 cost at September 1, 2026 API list-equivalent rates. We also report three evaluation failures: source-code leakage that produced an invalid perfect run, agents reconstructing a removed harness in a control condition, and autonomous repair masking a broken planner. A single-game observation case study showed that animation frames contained task-relevant information absent from settled text grids. Across the final Claude Opus 5 and GPT-5.6 Sol boards, 48 of 50 game-model cells reached 100. These results indicate that public-set score alone has limited discriminative value and motivate first-attempt, cost-conditioned, and verification-aware reporting.

Fluent LLM explanations may not follow the evidence from a structured system. We present VERITYGATE, a four-gate checker for declared evidence IDs, entities, numbers, and claim types. It checks a fixed schema; it does not verify every fact in the prose. At r=0 and r=1, we test 900 instances per setting (450 grounded-ungrounded pairs) with GPT-4o-mini, Llama-3.3-70B, and Claude Sonnet 4.6. Under this schema-level contract and before repair, 80.3% of mini claims and 47.9% of Sonnet claims fail. These are verifier rejection rates, not prose-hallucination rates. One repair pass raises claim survival from 19.7% to 28.0% for mini and from 52.1% to 54.3% for Sonnet. Verified claims per example change by +0.14 for mini, -0.71 for Llama, and -0.47 for Sonnet, so survival and output volume must be reported together. A second Sonnet pass gives no clear gain. At r=1, Gate 4 covers 97.0%, 98.7%, and 100% of failing claims for mini, Llama, and Sonnet. Small human studies support the rules but show gaps between schema checks and correct prose. A domain-specific GPT-4o judge test shows an order effect, so it is only a usefulness check. We release the code and data.

Dubbing quality control requires a reference-free judge that can determine whether a candidate text line matches a speaker's visible articulation in both content and timing, using only silent video and text because dubbed audio may not yet exist. Existing visual speech recognizers and video-language models are poorly suited to this setting: even when fine-tuned to recover spoken content from lip motion, they remain largely insensitive to temporal errors. We introduce $\textit{Align Then Reason}$ (ATR), a multilingual lip-sync judge that first establishes a monotonic alignment between frame-level lip representations and the phonetic units of the candidate line, then reasons over this alignment to make the final judgment. An alignment scorer provides the LLM with both local evidence for each phonetic unit and a calibrated global alignment score, enabling it to reason jointly about content and timing. On a seven-language benchmark, our method improves mean AUC over the corresponding Qwen3.5 SFT baselines by 59.4%, 50.2%, and 50.8% with 2B, 4B, and 9B reasoners, respectively. The gains generalize across LLM families, reaching mean AUC improvements of 45.9% and 46.6% over the best baseline for LLaMA-3.1-8B and Mistral-7B, respectively. They also transfer across datasets to three unseen MuAViC languages. Furthermore, we evaluate on two downstream tasks built from real dubbing lines. On dub-line reranking, ATR-9B outperforms the best lip-reading baseline by 52.0%, while on script-to-clip assignment, ATR-9B improves over the best lip-reading baseline by 17.7%.

We present a planning and control approach to reactively use hand contacts to stabilize a humanoid in low stability scenarios, where only using feet contacts may result in a fall. Candidate contacts are sampled within the robot's reachable workspace, and a preview is computed by rolling out the centroidal dynamics through pre-impact, impact and post-impact phases. Sampled points are scored based on the Center of Pressure (CoP) control authority at the post-impact phase. Central to our approach is a learned model of the robot's CoP region during post-impact, which enables rapid evaluation of candidate contact points compared to traditional optimization-based methods. The presented planner has two stages: the first selects an optimal bracing region and the second computes an optimal bracing point within the region. Our simulation results demonstrate an average increase in impulse resilience of 89% over recovery without hand contacts and 17% over a naive planning strategy (closest reachable region). We validate our framework on hardware, performing push tests while standing and walking. The standing trials show an average 43% reduction in stabilization time compared to naive hand placement and the walking trials demonstrate a 18% reduction compared to baseline recovery (without hand contacts).

Simulation can expand scarce real demonstrations for co-training, yet how world fidelity and similarity to human behavior affect policy performance remains unclear. We distinguish world grounding, which aligns simulation with the real system, and behavior grounding, which aligns simulated trajectories with human motion. We build a real2sim2real pipeline that varies these axes independently to generate data for co-training. On a dynamic dexterous pick-and-sort task, fully grounded co-training raises success from 52% to 86%; averaged across configurations, world grounding improves success by 18 percentage points and behavior grounding by 10. Deployed policies behave like a mixture of real-derived and simulation-derived policies, imitating real demonstrations in covered states and relying on simulated behavior elsewhere, which we examine through latent-space analysis. Together, these results suggest complementary roles: world grounding lets policies use simulated experience beyond real-data coverage, while behavior grounding matters mainly when world grounding is imperfect. Grounded simulation remains beneficial when co-training foundation models.

Join discovery aims to identify tables from large data repositories that can augment a query table with complementary information, enabling downstream tasks such as data exploration, feature engineering, and business intelligence. Although numerous join discovery methods have been proposed, existing studies rely on method-specific benchmark construction, making reproducible and fair comparison difficult. We present TabJoinBench, a benchmark for evaluating join discovery methods across semantic, relational, and hybrid data lake scenarios. TabJoinBench constructs query-candidate pairs using source-specific validation strategies, systematically introduces structural, representation, and semantic changes through composable perturbations while preserving reliable ground truth. We evaluate representative join discovery methods spanning set-based, feature-based, and learned approaches, together with general-purpose language-model embedding baselines, and publicly release the processed datasets, ground-truth annotations, and generation pipeline to facilitate reproducible evaluation and future research.

Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong generative priors learned through large-scale pretraining, pretrained video models often fail to reliably follow human intent, maintain temporal coherence, or satisfy physical and safety constraints. Compared with image and text generation, alignment in video generation presents unique challenges, including error accumulation over time, motion-appearance coupling, multi-objective trade-offs, and limited supervision for temporal properties. These challenges motivate systematic post-training strategies that adapt pretrained models without retraining them from scratch. In this survey, we present the first comprehensive review of post-training and alignment in video generation models. We frame post-training as a unifying framework and distinguish between implicit alignment and explicit alignment based on how alignment signals are enforced. From this perspective, we organize existing approaches into four broad categories: supervised fine-tuning methods, self-training and distillation methods, preference- and reward-based methods, and inference-time methods. This taxonomy provides a coherent view of how alignment signals shape model behavior across both training and deployment. Beyond methodological advances, we review commonly used datasets, benchmarks, and evaluation practices, and discuss open challenges such as scalable reward design, long-horizon temporal consistency, stability-expressiveness trade-offs, and safety-aware generation. This survey aims to provide a structured conceptual foundation and practical guidance for advancing controllable and reliable video generation models.

A robot may lose sight of an object it must later retrieve, need to recall what a person demonstrated earlier, or track which steps of a task it has already completed. Current vision-language-action (VLA) policies often fail once the information needed for action disappears from the current observation, making memory critical for long-horizon robot behavior. Existing approaches typically provide longer histories or learn implicit memory from observation-action trajectories. But action supervision tells a policy how to act, not what to remember: it does not specify which past facts should persist or how they should change as new evidence arrives. We therefore separate maintaining an evidence-grounded account of the past from learning how to act on it. This insight motivates Explicit Concept Memory (ECoMEM), which represents task-relevant history with a reusable library of grounded concepts. An evidence-based Writer selects and updates these records, while a learned Reader turns them into memory tokens that directly condition the VLA. Across 16 RoboMME tasks, ECoMEM leads the evaluated robot policies on 15 tasks. On two new real-robot tasks, the same memory library either transfers directly or requires only one new concept, achieving 86.1% success versus 8.6% for a no-memory VLA. These results show that explicit concepts provide a reusable and extensible memory interface for robot control. Project website: https://ecomem.github.io/

Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a policy engine for enforcing stateful contextual policies. A Sapien policy specifies permitted tool-call sequences using a regular expression extended with stateful predicates, deferred policy generation, and scoped semantic checks. We show that Sapien stays within a few percent of an unconstrained agent's utility. Even if the agent is fully hijacked, Sapien's policies rule out 93-95% of attacks on AgentDojo and 62-85% on Toolathlon (twice as many as tool allowlists on long-horizon tasks).

Teleoperated demonstrations are a primary source of data for robot manipulation, and teleoperated interventions are a primary mechanism for correcting policies at deployment. Yet most teleoperation systems close the loop through vision alone and are built around parallel-jaw grippers, limiting both what the robot can execute and what the operator can express through it. This is most damaging in shared autonomy, where the operator sees the scene only through occluded cameras and must take over a dexterous hand mid-task, often with an object already grasped. We present DITTO-X, a hand-agnostic dexterous teleoperation interface that renders joint-level force and fingertip contact events from sensing already on the robot hand, and drives three commercial dexterous hands (Sharpa, Wuji, and Inspire) without per-hand redesign. Because the exoskeleton is actuated, DITTO-X also supports reverse teleoperation, in which the robot back-drives the operator's fingers into its own configuration before control is transferred, so the human enters the loop already matched to the state they inherit. Our results show that DITTO-X improves demonstration quality and throughput over a commercial hand-tracking glove, both in regular data collection and in human intervention during policy deployment for contact-rich manipulation tasks. More information can be found from our website: https://tml.stanford.edu/ditto-x/.

Synthetic data now is essential to LLM training, used to strengthen advanced capabilities such as autonomous and long-horizon task execution. Yet recent work shows that training on it at scale can degrade model generation, making it important to decide what synthetic data is worth training on. While current data curation practices do so with individual-level signals (i.e., estimates of each data sample's training utility in isolation), across pre-training and post-training settings we show that this is insufficient for synthetic data, and that group-level signals (i.e., estimates of utility that account for interactions among data samples) are necessary for effective data curation. First, we show that individual-level signals are blind to how samples jointly affect training: synthetic datasets with different compositions can be indistinguishable under individual-level influence yet differ sharply under group-level influence, and curating by the latter yields better downstream performance, particularly in generative capability. Second, we find that group-level signals matter more as training pipelines become increasingly synthetic: among widely used data curation methods, only those incorporating them improve over baseline, with gains increasing when weights capturing relations among samples are amplified. Finally, we translate these findings into practice -- for model developers under a compute budget, we offer a cheap diagnostic that prioritizes which groups of synthetic data most need group-level estimation, recovering much of the benefit of full group-level scoring at a fraction of the compute cost.

Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training. One recently popular technique for such interventions is synthetic document fine-tuning (SDF), which aims to alter what the model believes. Ideally, synthetic documents would be mixed into pre- or mid-training, but every change to a pre-training corpus must be followed by a full post-training run before its effect can be measured, making iteration slow and expensive. Common practice instead applies SDF to an already post-trained model. This is known to leave artifacts and degrade capabilities, and, as we show, it makes the model treat fabricated entities unrelated to the documents as real, a failure we call reality drift. We propose grafting: train the SDF adapter on the pre-trained checkpoint, then add the learned weight update to the post-trained model, which approximates the faithful approach while reusing the existing post-training. We demonstrate this by installing false facts, training misaligned model organisms and applying a constitutional mid-training intervention, across model families up to 284B parameters. Grafting installs the target belief as strongly as SDF on the post-trained model while reducing both reality drift and the loss of preference coherence by more than half on average, and it stays closer to a faithful mid-training run. Because grafting requires no post-training, the same adapter can be applied to any later checkpoint, enabling researchers to iterate quickly on pre-training interventions at the cost of a single fine-tuning run.

Cyber attack agents are typically trained and evaluated within a single simulator, making it unclear whether learned policies transfer beyond the environments in which they were developed. This limitation hinders both deployment and fair comparison, as cyber simulators differ substantially in their state representations, observation models, and action spaces. In this paper, we study policy transfer across cyber environments and argue that simulator-to-simulator and simulator-to-real transfer can be viewed as instances of the same underlying alignment problem. We propose a framework that separates state alignment from action translation, enabling a policy trained in one environment to operate in another without retraining. We evaluate transfer across four cyber platforms, CyberBattleSim, NetSecGame, CyberWheel, and NASim, including emulated deployments in NASim. Our experiments show that zero-shot transfer is feasible, fully preserving source-policy performance in closely aligned environments and achieving 45.2% win rates when transferring policies whose source performance is 60.5%. In emulated virtual machine environments, transferred policies exhibit a Jensen-Shannon divergence of 0.085 from native policies, indicating strong behavioral similarity. Code and benchmarks are available at: https://anonymous.4open.science/r/RL-Transfer-between-env-4F47/.

By learning transferable rewards, inverse reinforcement learning (IRL) enables counterfactual evaluation of agents under modified environments. Such transfer places strict requirements on coverage since target environments affect agents' state occupancy. We propose a multi-task IRL method that pools data across multiple agents with different rewards in the same environment under a low-rank assumption. In addition to alleviating coverage requirements, so each task need not visit every state as long as others do, the method offers scalable evaluation of multiple tasks under new environments as computationally intensive planning scales with rank rather than the number of tasks. We provide finite sample guarantees on reward recovery and on policy learning in new environments. Experiments show our method is robust to limited coverage, recovers rewards on and off of each task's support, transfers to target environments at lower regret than baselines, with its computational advantage over per-task methods widening as tasks grow.

Recent theoretical work identified fundamental properties of representation geometry that shape inference ability of deep neural networks. These include signal-noise factorization (SNF), the ability to segregate signal from noise, and signal-signal factorization (SSF), the ability to segregate task-specific and task-irrelevant signals. Here, we built regularizers that reinforce these two properties during training. We compared networks trained with these regularizers to $L_2$-regularized baseline networks on the CIFAR-100 classification task to understand how our regularizers shape representation geometry and impact performance on a well-known computer vision baseline. Enhancing SNF via regularization improved model performance but enhancing SSF did not. Motivated by biomedical applications, we investigated how our regularizers affected performance on the BloodMNIST dataset treated with MedMNIST-C corruptions at five severity levels, and found even larger performance gains using the SNF regularizer. To understand the mechanism by which SNF-regularization produces improved performance, we analyzed the nuisance subspaces across regularization regimes, finding that the SNF-regularized models represent noise in distinct subspaces, separate from class-relevant signal. Because this geometry is explicit, the dominant corruption-induced directions can be estimated on held-out data and projected out of the representations. This manipulation led to a substantial gain in accuracy. These results show that regularizers that enforce signal-noise factorization can produce substantial improvements on computer vision tasks that contain out-of-distribution image distortions at inference time. They also highlight how shaping representations affects model performance: isolating nuisance variables from categorical ones is more important than maintaining factorized representations of categorical variables.

Standard 3D Gaussian Splatting (3DGS) learns geometry and appearance jointly from RGB supervision, making it difficult to isolate how luminance and chroma contribute to the learned representation. We study this by training models under different channel supervision, freezing their non-appearance parameters (position, scale, rotation, and opacity), and re-estimating appearance with the same solver before comparing held-out reconstruction. Across eleven benchmark scenes with four independent runs each, geometry learned from luminance alone supports held-out reconstruction 0.085 dB below RGB-trained geometry on average. If chroma is deleted from a trained model, a sufficiently expressive solver can re-fit it on the frozen geometry to the original quality or slightly better. Higher-order spherical harmonics contribute much more reconstruction quality to luminance than to chroma, improving PSNR by 1.44 dB versus 0.19 dB on average, although on mirror-like surfaces hue does still change with viewpoint. The luminance advantage is even larger when geometry is being formed. Chroma-only supervision produces geometry 3.9-5.5 dB worse than luminance-only supervision after the same appearance solve; densification explains part of this gap. Overall, geometry formation in standard 3DGS is strongly luminance-dominated but not luminance-exclusive, and much of the chromatic appearance can be recovered after spatial support has formed.

We propose a calibration-free photonic memory bitcell based on nonresonant variable optical attenuators in the GlobalFoundries 45SPCLO platform. The cell maintains complementary electrical states through electro-optical feedback without cavity-resonance alignment. Wordline-controlled attenuators enable selective writing through differential optical bitlines, while optical readout shares the holding input and output splitters, avoiding additional read attenuators or a separate laser source. Circuit simulations demonstrate writing with $10~\mathrm{ps}$ optical pulses at $2~\mathrm{mW}$ peak power. The cell retains data as long as optical and electrical power are supplied, with retention simulated for $5~\mathrm{s}$ per logic state. The evaluated transition consumes an incremental write energy of $0.562~\mathrm{pJ}$, including circuit electrical energy and the laser contribution at 20\% wall-plug efficiency. The bitcell layout occupies $147.92\times219.93~μ\mathrm{m}^{2}$.

Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, however, a user's personal context is much richer, comprising reviews, posts, images, captions, and metadata accumulated over time. A truly personalized generator should leverage this history to produce images aligned with the user's lifestyle and aesthetic preferences. To this end, we introduce the first unified benchmark for personalized image generation from user histories. The benchmark comprises two complementary tasks and a multi-axis evaluation protocol that assesses target fidelity, visual quality, user distinguishability, semantic alignment with the user's history, and task-specific utility. Grounded in real-world e-commerce and social media settings, the benchmark includes: (1) Personalized Scene Generation, which places a given object in a scene that reflects a user's preferences and lifestyle, motivated by personalized product presentation; and (2) Personalized Creative Generation, which generates a novel image on a specified topic that is faithful to a user's aesthetic and visual identity, motivated by social media content creation. We further propose PEARL, which couples a multimodal reasoner with a frozen image generator in an interleaved reason-reflect loop optimized with differential data reward. Across both tasks, PEARL outperforms strong baselines, achieving an average improvement of 15% across personalization metrics.

Simulated evaluation is increasingly used alongside real-world evaluation of robot policies because it is cheaper and easier to repeat; however, its value depends on how closely its outcomes track the real robot's. We test whether our reconstruction pipeline, combining metrically scaled object geometry, authored physical parameters and scene reconstruction, reduces disagreement between simulated and real robot scores relative to a default open-source recipe. We constructed two simulated versions of one bimanual robot cell: an authored reconstruction, using object geometry at estimated metric scale, projected textures, authored physics and our own scene splat; and a baseline, referred to as the default reconstruction, using the open-source recipe of a generative single-image mesh, engine-default physics and a Gaussian-splat scene. Both reconstructions use the same object photographs and scene video. Two policies ran five tasks each, giving ten task-policy pairs, which we call cells; each cell was run twenty times in each reconstruction with all other settings held fixed. Both reconstructions were scored against the same real trials, graded by a third-party evaluator. Pearson correlation between the ten simulated and real cell means is r = 0.90 for the authored reconstruction and 0.51 for the default. Mean score error is 6.97 percentage points for the authored reconstruction and 17.54 for the default, a reduction of 10.56 percentage points. These results show that improving the quality of the environment reconstruction through higher visual fidelity, authored physics and metric scale makes the simulation more faithful to the real world and narrows the sim-to-real gap. We release the harness, the per-trial scores, every reported run's configuration, and the assets and scenes of both reconstructions.

Weather reanalysis products rely on computationally intensive numerical weather predictions followed by data assimilation that corrects the forecast toward observations. Deep generative models offer a cheaper alternative that shifts much of this cost from inference to offline training. However, existing generative approaches have been evaluated on synthetic observations or under different datasets and evaluation schemes, making it unclear which design choices actually improve real-world data assimilation. We present the first controlled benchmark of generative weather data assimilation on real weather station observations. Using 11,849 NOAA MADIS stations across the contiguous United States and four weather variables, we evaluate methods while holding the dataset, observation operator, and deep learning architecture fixed. The benchmark compares the major design choices, including diffusion versus flow matching, pixel versus latent-space formulations, and multiple inference-time conditioning strategies, against a classical 3D-Var baseline. The benchmark reveals three clear conclusions. First, learned generative priors outperform the Gaussian prior of 3D-Var (35.7% vs. 33.3% RMSE reduction over ERA5) despite using no ERA5 background field at inference. Second, full-gradient guidance consistently outperforms stop-gradient and initial-noise optimization. Third, other choices provide little measurable benefit: diffusion and flow matching perform nearly identically under matched conditions, and latent-space variable mixing does not help. We further evaluate both dense and sparse station settings and find advantages from generative AI and full-gradient guidance more pronounced under sparsity. Together, these results identify which components of generative weather data assimilation improve performance on real station observations and establish a standardized benchmark for future work.

Controlling an agent with vision requires being able to separate useful information from irrelevant background information. JEPA-style latent world models seem like a natural approach for this, as they do not perform pixel-level reconstruction; however, they are still sensitive to these distractor signals and experience latent collapse. In this work, we introduce Controllability Factorized JEPA (CF-JEPA), a JEPA-style world model which splits the latent space into controllable and uncontrollable subspaces. This factorization allows us to capture all the distractor information into the uncontrollable region, while we use the control-relevant latent information for our task. With this, we show comparable performance across 2D and 3D control tasks under nominal conditions and improved performance under distracted conditions, where CF-JEPA is the only model that does not experience latent collapse. We also validate our model under distracted conditions for a simulated robot task, highlighting the practical application of such a scheme.

Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control. We study whether recurring styles in model responses can be discovered without supervision and explicitly controlled. We design an algorithm that learns to separate representations of content and style from language models' outputs and validate its effectiveness on math questions in a controlled setting. By applying this method to over 100K verified traces from nine distinct teacher models, we discover six recurring yet imbalanced styles. We then fine-tune smaller student models to follow these styles when explicitly conditioned on them, using importance weighting to balance the contribution of the styles represented in the corpus. This approach improves Pass@$k$ over standard fine-tuning on the same data across six math reasoning benchmarks, demonstrating that we can diversify the style of answers effectively. We confirm that this also results in strong correspondence between requested and realized styles. We find that style affects correctness: the probability of solving a problem depends on the style we condition on, and different problems benefit from different styles. In summary, our results show that stylistic variation in model-generated data can be discovered in an unsupervised way, and made explicit, providing a source of both control and improved reasoning performance.

World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during training. We present JEPA-TTT, which adapts the latent dynamics predictor of a pretrained action-conditioned Joint-Embedding Predictive Architecture world model throughout test time. Self-supervised updates accumulate across episodes, while the visual encoder and reward head remain fixed, preserving the pretrained representation and task objective. Planning requires neither a goal image nor online environment reward. JEPA-TTT uses dense replay, which forms prediction windows at every temporal offset, retains them in a growing buffer, and samples minibatches from that buffer for predictor updates. Across eight dynamics shifts in four continuous-control environments, JEPA-TTT improves planning on every shift. After 500 test-time episodes, it reduces autoregressive latent prediction error by 83% on average and improves planning performance by 153% over the frozen JEPA world model. These results show that persistent self-supervised test-time training can adapt a pretrained latent world model under changed dynamics.

We present a teleoperation system that enables a single operator to perform construction tasks on a Unitree G1 humanoid, combining extended reality (XR) based upper body control with pedal-based locomotion to enable simultaneous manipulation and locomotion. Motivated by persistent labor shortages, hazardous working conditions, and challenges in humanoid autonomy, we investigate teleoperation as a practical near-term approach for reducing physical strain on workers while generating high quality demonstration data. We evaluate the system on two representative construction tasks drawn from O*NET occupational database, and report task success and completion time relative to a manual baseline. The system achieved 100% success on tool transport and 80% success on surface painting, with teleoperation requiring substantially more time compared to manual execution.

Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the representation shift introduced by earlier compression. We propose FTC, a sequential structured compression framework that adapts the approximation to the current compressed model while jointly exploiting the native Q/K/V head structure under a fixed storage budget. The output projection is handled separately to account for the changed post-attention representation. FTC requires neither fine-tuning nor gradient-based recovery. Across seven decoder-only LLMs from 6B to 32B parameters, FTC achieves the lowest WikiText-2 perplexity among the compared methods at every tested keep ratio on five modern GQA models, with the largest gains under aggressive compression. The improvements transfer to downstream tasks and remain substantial at the 32B scale.

When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attribution alone cannot reveal whether the explainer has failed or the model has learned a shortcut. We introduce WOMBAT, a benchmark of 14 whitebox GNNs, each with message-passing weights set by hand to detect a specific SMARTS motif. Each model's decision rule is known by construction, providing attribution ground truth against which explainer errors can be identified and studied. We validate the models on millions of PubChem molecules and evaluate post-hoc explainers including GNNExplainer, PGExplainer, and Integrated Gradients. Guided by our qualitative analysis, we construct a model that causes Integrated Gradients to spread attribution across the graph, even though the model reliably detects the intended motif. We release the dataset, models, and evaluation code to help researchers in the development of newer XAI tools for GNNs.

As large language model (LLM) agents become widely adopted, they are increasingly deployed for tasks that require persistent monitoring or recurring actions (e.g., market analysis). These agents are expected to operate unattended for days or weeks, act at the right timing, and adapt to the dynamic environment over time. These challenges are not fully captured in the existing long-horizon agent work, as they often consider a static environment that is not temporally changing. We introduce ReLiveGym, a diagnostic evaluation environment of long-lived tasks in which agents act sparsely over simulated weeks of chronologically replayed real-world news, market, and social-media streams. The tasks span diverse levels of time sensitivity, reasoning intensity, and recurrence. Across eight base language models, we investigate how model choice and harness design affect agent performance on such long-lived tasks. Our results show that how agents determine when to act arises as an important harness-design axis for long-lived tasks; and that the optimal design varies across tasks and sometimes model choices as well. We also evaluate how continuous learning from hindsight feedback affects performance and addresses failure modes observed in these long-lived tasks. These findings indicate model choice, action timing mechanism, and use of feedback as important considerations in the design of long-lived agents. Code: https://github.com/SaharaLabsAI/ReLiveGym

Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and question embeddings. We train these vectors through self-distillation over diverse audio and text perturbations. To improve answer consistency and mitigate hallucination, we use the model's prediction on the clean recording as the target for answerable inputs, and assign a refusal target when the audio lacks sufficient evidence to answer. Furthermore, AnchorPrompt is perturbation-agnostic at inference, requiring no prior detection of perturbations and enabling zero-shot transfer to unseen distortions. We evaluate three LALMs across three benchmarks and show that AnchorPrompt improves answer consistency in most tested conditions. Clean accuracy improves in six of nine model-benchmark pairs, with minimal impact on the remainder of 1.2% at most. Crucially, AnchorPrompt reduces hallucinations under severe audio corruption while keeping false refusals on clean audio rare. Finally, these consistency gains transfer to unseen perturbations, such as choice permutations and reverberation.

This paper develops a meta-multi-agent reinforcement learning (meta-MARL) framework to enable fast adaptation of interactive policies in a multi-agent system (MAS). Meta-reinforcement learning (meta-RL) enables agents to rapidly adapt to new tasks/environments using a bi-level optimization mechanism. However, existing meta-RL generally focuses on single-agent systems. Extending these frameworks and algorithms to multi-agent systems poses additional challenges, as tasks are characterized by not only the environment but also agents' strategic interactions. To address these challenges, we model multi-agent reinforcement learning (MARL) problems as Markov games (MGs) and develop a meta-MARL framework for rapid interactive policy adaptation across a distribution of MGs. A new concept, called meta-NE, is defined to describe the desired solution concept in a meta-MARL problem. Sufficient conditions for the equivalence between a meta-NE and a stationary point of the gradient-play-based meta-MARL algorithm are established. Our evaluation on autonomous-driving tasks demonstrates that the proposed meta-MARL method achieves faster adaptation than pretrained MARL baselines, validating the effectiveness of our framework.

Natural-language skills are textual procedural memories through which large language model (LLM) agents retain reusable task knowledge without updating model weights. Existing methods typically treat skills as either static artifacts or monolithic documents optimized using aggregate validation scores as feedback. However, representing a skill as a monolithic document restricts optimization to its textual content, without explicitly modeling the structure through which procedural knowledge is retrieved and executed. We identify a key distinction between learning what knowledge to retain and determining how to organize it: textual updates should first be validated through execution evidence, after which the retained knowledge should be structured according to its procedural dependencies and retrieval requirements. To this end, we introduce SkillSpec, a two-phase framework comprising consensus-gated evolution and representation specialization. In the consensus-gated phase, complementary editing intents generate complete candidate skills. An update is committed only when paired evaluations reach consensus, requiring sufficient overall improvement and non-negative aggregate paired gain in every repeated evaluation. In the specialization phase, signals of process and redundancy sensitivity derived from the full optimization trajectory, including accepted and rejected candidates, guide the selection of a flat, graph, or hybrid representation.Across six benchmarks and three target language models, SkillSpec improves average success rate over SkillOpt by 6.89%, averaged across the three models. These results demonstrate that reliable skill evolution and representation specialization address complementary objectives: deciding what knowledge to retain and how to structure it for inference.

Recent advances in AI for scientific discovery enable molecular understandingand design, yet reasoning over incomplete chemical representations remainsunclear.Markush structures, which encode molecular families through variable R-groupplaceholders (\textit{R\textsubscript{1}}, \textit{R\textsubscript{2}}, \textit{X}, etc.), are ubiquitous in pharmaceutical patents and requiregrounding across molecular, textual, and chemical information.However, existing molecule-language benchmarks focus on fully specifiedmolecules, leaving R-group grounding largely unevaluated.We introduce R-GroundBench:, a diagnostic benchmark built from real patent Markushstructures, featuring a Multiple-Choice (VQA) track with controlled difficultyand modality splits, and an open-ended Generation track.Our results reveal a substantial gap between recognition andmolecular grounding.While models achieve over 90\% accuracy on Easy VQA, performance drops to56--66\% on Hard VQA when shortcuts are controlled.Chemical-domain VLMs also remain unreliable, achieving only 25.7--46.2\% on HardVQA despite domain-specific pretraining.Moreover, Generation Exact Match remains below 20\% for most models and below8\% when visual input is required.These findings reveal that current AI systems lack reliable grounding andexecution for Markush editing, highlighting challenges for AI-drivenscientific discovery.

Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for the optimal performance of each of these, both in terms of fidelity and semantics. Flexible-length, coarse-to-fine tokenizers yield exactly that: the first coarse tokens carry the clip's global semantics while later tokens further specify details. Existing flexible tokenizers only apply a representation-alignment (REPA) loss on early decoder hidden states, a target the decoder can partly meet from its noised input instead. We introduce SemanTok, a flexible video tokenizer that feeds frozen DINO features into its encoder and adds lightweight heads that reconstruct them from each retained token prefix alone. SemanTok achieves high semantic alignment and video fidelity at every AR model size: a 201M SemanTok AR model matches or beats a VideoFlexTok AR model $3.4\times$ its size, and larger SemanTok AR models further improve fidelity. It keeps semantic alignment on out-of-distribution classes and gives the decoder higher semantic alignment at every noise level, including pure noise. It performs well in both reconstruction and generation, and its short token prefixes are cheaper to predict and give better generation fidelity, with pixel detail deferred to later tokens.

Large language models (LLMs) increasingly underpin scientific AI applications that reason over structured knowledge, from biomedical question answering to materials informatics. However, their logical reasoning often falls short, producing factual inaccuracies unacceptable in these settings. Reliable evaluation remains challenging: manual dataset construction scales poorly, and LLM-based generation risks embedding the very flaws it aims to measure. High-quality benchmarks must ground both correct and incorrect labelled examples in explicit background knowledge, formally verifiable by a standard reasoner. We propose a pipeline that automatically generates ontology-grounded multiple-choice question (MCQ) benchmarks from any sufficiently axiomatised OWL 2 ontology, with correct answers grounded in the ontology by design. Distractors are generated by perturbing the right-hand-side class expressions of class definition axioms, and their incorrectness is formally verified by an OWL reasoner via entailment checks. We evaluate the pipeline on three ontologies: Pizza (small, academic), PMDco (complex, materials science), and DOID (large, biomedical), generating 112, 2,491, and 15,216 MCQs respectively. Distractors span four semantic categories from class unsatisfiability to weakened subsumptions, enabling diagnostic evaluation of specific reasoning failures. Items meet natural language quality standards: mean LLM judge scores of 4.02, 4.36, and 3.36 out of 5 confirm fluency, and correct-answer-to-distractor similarity above 0.8 shows that wrong options cannot be dismissed on surface form alone. Six LLMs evaluated zero-shot achieve 41.1-76.8% accuracy, well above the 25% random-guessing baseline, indicating the benchmarks are challenging and discriminative. This work is a step towards more reliable benchmarks for assessing logical reasoning in scientific AI.

Advancements in augmented reality (AR) continue to foster innovative solutions, facilitating novel methodologies within educational systems, healthcare delivery, and risk-mitigation protocols. However, optimizing for end-user immersion and comfort remains challenging, as AR head-mounted displays contend with constrained scene geometry, spatial jitter, and temporal instability. User studies are the standard AR evaluation method for visual quality, but their cost, diminishing scalability, and inflexibility pose bottlenecks during iterative application design. To address this problem, we present an automated framework for AR content evaluation and refinement, built on vision-language models (VLMs), to evaluate and predict the visual fidelity of AR scenes as perceived by users. First, we introduce RateAR, a benchmark of AR images and videos collected across diverse scenes and environmental conditions, with good-to-excellent reliability (ICC(2,5) >= .90) across perceptual factors, including object placement, scale, and shadow consistency. Subsequently, we evaluate eleven commercial VLMs on the crafted benchmark. Results support that VLM-based quality predictions strongly correlate with human subjective judgments, achieving Spearman's rank-order correlations of up to 0.8695. An ablation study further suggests that, compared to other prompting strategies, our contextual prompting yields better alignment with human ratings while balancing introduced complexity cues. Building on these findings, we construct an automated AR content adjustment system and conduct a 21-participant user study. More than 90% of participants found that the system improved placement and size coherence of virtual content.

Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent discovery harness built around LabBook, an agent-maintained memory that serves two complementary roles: guiding retrieval of relevant evidence from a complete experimental log and informing the generation of new solutions. At each iteration, the same agent combines its memory with retrieved evidence and jointly produces the next program and an updated LabBook. This separates complete history retention from selective context construction, without requiring an explicit population or branching search structure. On 49 Frontier-CS problems, LabBook improves the observed quality-cost trade-off over the evaluated evolutionary baselines with two backbones, while remaining competitive across nine additional mathematical, systems, and heuristic-design tasks. Code will be released at https://github.com/BoYuanVisionary/LabBook.

Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage training over trillions of tokens, while the benefits of recurrence remain difficult to separate from differences in data and training. In this work, we establish practical training recipes for looped language models, with three main results. (1) We develop a compute-efficient from-scratch pipeline that reduces the training budget from 7.7T tokens in Ouro to 310B tokens while retaining strong reasoning performance. Pretraining followed by high-quality mid-training, together with learning-rate warmup and stronger exit-gate regularization, enables stable recurrent training without prior multi-stage schedules. (2) Under controlled comparisons, our 1.4B LoopLM outperforms a parameter-matched dense model trained on the same data and token budget on all 12 evaluated benchmarks, including +14 points on GSM8K, +10 on MATH, and +22 on DROP. At matched inference compute, it approaches a 3.9B dense model on mathematical reasoning and reading comprehension while using only 36\% as many parameters. (3) We introduce a minimal recipe for converting pretrained dense models into looped ones: a single learned input-mixing scalar and a smoothed exit loss, with no step-specific parameters. Applied to Qwen3-1.7B-Base, Looped Qwen improves over an identically continued dense baseline on every evaluated benchmark across two data regimes, with statistically clear gains on GSM8K, MATH, and MMLU-Pro on the curated mixture. Together, these results make looped language models substantially cheaper to train from scratch and practical to introduce into existing pretrained checkpoints, while isolating the gains due to recurrence itself.

Making decisions despite conflicting norms and incomplete or unreliable information is a fundamental challenge for autonomous systems. We introduce a simple doxastic deontic logic for this setting: a classically reducible fragment of Chellas' Minimal Deontic Logic, extended with explicit conditional norms and combined with multi-agent KD45, so that norms can depend on agents' beliefs about both facts and norms. On this logic we define the Doxastic Norm Compliance Optimization Problem, where an agent chooses a decision minimizing weighted norm violations. We distinguish subjective optimization (relative to the agent's beliefs) from objective optimization (relative to the actual facts). We give conditions under which (i) the two coincide and (ii) optimal decision-making can be reduced to weighted partial MaxSAT in polynomial time.

Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchmarks score only scalar quality or overall preference, so a judge can be rewarded for picking the preferred image for the wrong visual reason. We introduce VisionQ, the first benchmark built from peer-reviewed CV comparison figures that grounds every judgment in a named visual criterion: each question states the criterion, and a judge is credited only when it selects the output the authors identify as best on that criterion. We call this task criterion-conditioned visual discrimination. VisionQ comprises (1) a corpus of 1,409 CVPR and ICCV papers with 1,800+ validated comparison figures and 3,911 hand-annotated data points linking method crops to author-stated visual claims; (2) a six-axis, 51-leaf taxonomy of the visual criteria behind qualitative judgment; (3) a criterion-conditioned evaluation protocol that hides method names, captions, and paper identity and reports accuracy per criterion; and (4) VisionQ-Judge, a DPO-tuned Gemma-4-E4B judge trained on symmetric evidence pairs, which reduces last-option predictions by 7.0pp and improves accuracy by 2.5pp on a held-out test set. Evaluating 20 open- and closed-source VLM judges, we find that the strongest reach only 63.1% accuracy (chance 32.2%) and that reliability varies sharply across criteria. Code: https://github.com/ReML-AI/visionq. Data: https://huggingface.co/datasets/visionq-anon-2026/VisionQ-1k.

Background: Protein language models (PLMs) are increasingly used for sequence generation and property prediction, but their size makes fine-tuning and deployment expensive. The effects of quantization and parameter efficient fine-tuning on performance, representations and generation remain insufficiently characterized. Results: We evaluated 4-bit quantization and low-rank adapter fine-tuning (QLoRA) across ESM-2, ESMC, ProtBERT, ProtT5, Ankh, Ankh3 and Profluent-E1. Across protein prediction tasks, many model-task pairs retained more than 90% of full fine-tuning performance. Peak GPU memory savings approached 90% for the largest models, although performance and efficiency varied by model, dataset and training configuration. QLoRA often preserved early-layer representations while inducing task-specific adaptations in middle and late layers, resembling full fine-tuning with smaller representational changes. Training speed and power effects were more varied. For unconditional generation with ProLLaMA, ProtGPT2, ProGen2, ProteinGLM and ESM3, 4-bit quantization largely preserved predicted structural and sequence-level properties, but token-level analysis revealed model-dependent shifts in autoregressive output distributions. Conclusion: QLoRA and 4-bit quantization reduce PLM computational requirements, particularly GPU memory usage. Our results support QLoRA as a first-pass strategy for memory limited adaptation, reserving full fine-tuning for challenging tasks, unstable architectures or low validation recovery. For generative PLMs, sequence-level and structural metrics should be complemented with distributional analysis, since downstream predictions alone may miss quantization-induced shifts. These approaches can broaden access to large-scale protein modelling while requiring model- and task-specific validation.

Bengali secondary education lacks curriculum-grounded benchmarks for STEM question-solving, and general-purpose language models struggle with the precise terminology, unit conventions, and derivations that physics problems demand. We introduce PhysicsMate, a benchmark of 1834 question-answer pairs built from the National Curriculum and Textbook Board (NCTB) Grade 9-10 physics syllabus and grounded in a multi-relational knowledge graph of 1760 nodes and 2600 edges across ten ontological types. We Low-Rank Adapt at 0.6B, 1.7B, and 4B parameters, with a unified recipe and demonstrate a significant increase in closed-book accuracy in all scales (+5.5, +15.0, and +23.3 percentage points). A node-type analysis shows that the most benefited by adaptation is the structured curricular knowledge, which consists of physical quantities and named laws, while the least benefited is the loosely specified entity-level knowledge. The 4B model has been adapted and quantized to a small offline binary that can be used for local inference in resource constrained environments and offers a viable path to curriculum aligned physics support in environments with limited connectivity and hardware.

Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing defenses span four stages--prior-training, in-training, post-training, and inference-time--and share one of two underlying strategies: either suppress backdoor learning (by filtering poisoned data or interrupting its acquisition during optimization) or learn, then purify (by repairing model weights or gating inputs after a fully backdoored model has formed). We propose a third strategy, learn, but channel: allow backdoor formation during training but route it into a designated, quarantined component that can be disabled at deployment. To this end, we propose Quarantined Expert Shutdown QES, a computationally efficient containment strategy built in a regularization-steered MoE-like setting. Specifically, given a poisoned dataset, QES augments a Transformer-based language model with routed expert-specific LoRA branches and lightweight routers, and uses auxiliary routing objectives to attract trigger-conditioned behavior into a designated expert while preserving benign capability elsewhere. At deployment, mitigation reduces to a single constant-time operation: zeroing the quarantined expert's routing weight, without trigger screening or further updating model weights. Empirically, our methods reduce the attack success rate ASR from 100% to 0-10% on most settings across two tasks, three attacks, and four model families, while downstream utility is often preserved or only modestly affected. These results establish learn, but channel as a previously unexplored regime for backdoor containment in generative LLMs.

Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcement learning with verifiable rewards (RLVR) reuses terminal feedback across these decisions, even as their conditioning context changes. We propose stepwise risk-sensitive GRPO (StepRS-GRPO), which varies the risk coefficient of the group-advantage transformation across denoising states while retaining the underlying trainer. For binary rewards, we show that this transformation is exactly a prompt- and state-dependent rescaling of centered outcome advantages. A capability-based calibration suggests a coefficient scale, while endpoint and interpolation ablations guide schedule selection. Across multiple dLLM backbones and mathematical reasoning benchmarks, StepRS-GRPO improves both pass@1 accuracy and pass@k coverage over centered GRPO, while increasing answer diversity. In our ablation studies, mass-matched controls support the contributions of state allocation and schedule direction, and the gains persist after matching the root mean square (RMS) of the advantages to that of centered GRPO. Reasoning-trace diagnostics further show that the diversity gains from StepRS-GRPO extend beyond final-answer strings.

Agent evaluations are increasingly used to compare LLMs and inform deployment decisions, yet ranks can reflect not only the model but also the effects of the evaluation conditions such as the scaffolds or tasks. This makes reliability claim-dependent: an evaluation that reliably ranks deployed systems may not reliably rank underlying models. We ask which conclusions current agent evaluations reliably support and what additional evaluation would improve them. We develop a Bayesian variance-decomposition framework for sparse, imbalanced agent leaderboards and apply it to 22 benchmarks from the Holistic Agent Leaderboard and Harbor Index. The framework separates signal, performance differences relevant to the intended claim, from noise, irrelevant variation that can still change rankings. We find: (1) Reliability depends on the measurement goal. Fixed model-scaffold systems are ranked reliably (0.935-0.994), while underlying-model reliability is substantially lower (0.148-0.841). (2) Scaffold choice can change conclusions. Inter-scaffold reliability measures whether scaffolds preserve model rankings, showing that scaffold effects vary substantially across evaluations. (3) More tasks cannot resolve all uncertainty. Even infinitely many similarly constructed tasks improve model-ranking reliability of a benchmark by at most 0.097 when uncertainty is dominated by limited scaffold coverage. (4) Pooling diverse benchmarks can improve cross-task rankings at lower cost. For rankings across diverse agentic tasks, pooling benchmarks raises projected reliability from 0.44 to 0.75 at the same task budget and can reduce projected cost by up to 83\%. Evaluation design should follow the intended claim: identify what a score or ranking should mean, diagnose what limits its reliability, and spend evaluation budget on the sources of uncertainty that matter.

The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted and fixed, making the process labor-intensive and often suboptimal. In this work, we propose RuleEvolve, a self-evolving framework for coding rules. RuleEvolve maintains a pool of candidate coding rules and iteratively improves them. In each iteration, it employs an LLM-powered mutator module to generate variants from existing candidates, and then uses a judge module to evaluate these variants and update the pool with the best-performing ones. Extensive evaluations across two coding-agent frameworks, four backbone LLMs, and three benchmarks demonstrate that RuleEvolve outperforms both manual engineering and existing prompt optimization baselines in terms of functional correctness of the generated code, code length, and/or generation cost (e.g., tokens used).

AI coding agents are ubiquitous in engineering workflows amongst industry and academia. Yet, despite their use in app coding, relatively less attention has been paid to their ability to execute on production incident response. This emerging field, termed agentic site-reliability-engineering (SRE) contains benchmarks limited by (1) unrealistic environments, typically toy repositories (2) non-standard framework implementations and (3) simple static verifiers. We introduce Incident-Arena, a human-built benchmark of 20 carefully selected tasks grounded in real-world deployed open source software. Each task deploys a production application to an ephemeral Kubernetes cluster, injecting a fault from the config layer through underlying images, and a sustained load profile given the task requirements. We also present a novel verification method, going beyond static checks to functional verifiers, holding systems level metrics stable, while ensuring repairs are done safely. Agent trials run an average of 2.81M tokens and 41 turns, going beyond existing benchmarks, demonstrating agentic long horizon reasoning. Across 20 tasks and 3 application substrates, frontier models score below 64.3%, with failures extending from diagnosis/localization errors, through incomplete repairs and unsafe regressions.

World action models improve robotic manipulation by conditioning actions on predicted futures, yet existing tactile variants largely inherit video-generation pipelines that reconstruct future tactile observations through iterative denoising. Such prediction can become unreliable under deployment drift: small changes in contact position or force may substantially alter tactile pixels even when the underlying contact evolution remains predictable. We introduce TacDyn-WAM, a heterogeneous visuo-tactile world action model that predicts implicit tactile dynamics rather than reconstructing future tactile observations. It learns TacRep, a dynamics-aware tactile target space trained through masked spatio-temporal prediction on tactile clips and regularized by relational structure distillation. A visual expert and an Implicit Tactile Dynamics Expert predict future visual and tactile representations in separate target spaces while interacting through joint attention; the tactile expert predicts future representations and their changes at multiple horizons in a single forward pass, and a read-only tactile memory supplies the current tactile state. On UniVTAC, TacDyn-WAM achieves an average success rate of 81.5% using only the provided demonstrations, reaching state-of-the-art-level performance and remaining competitive with models pretrained on large-scale visuo-tactile trajectories. Ablations confirm the benefits of both tactile pathways and TacRep over pixel-reconstruction and static alternatives. On five real-robot tasks, TacDyn-WAM reaches 71.0% average success, and modest-scale pretraining raises it to 85.0%, further validating our method.

Evaluating AI agents on scientific research tasks is constrained by the time and resources required for the underlying experiments or calculations. In computational materials research, repeating the same expensive simulations across agents and trials can make evaluation impractical. We introduce CompMat-Bench, a benchmark of 94 tasks derived from recently published computational materials studies, each asking agents to complete a step toward achieving the study's scientific goal. We reproduce the research steps in advance and assess agents on preparing inputs and analyzing outputs for expensive simulations, so expensive simulations can be avoided during evaluation. The reproduced inputs and results serve as ground truth for grading agents with fixed rules, without an LLM judge. The benchmark supports four evaluation conditions: single tasks and workflows composed of related tasks, each with full or reduced methodological guidance. With full guidance on single tasks, agents based on three LLMs demonstrate the ability to complete individual materials research steps, with pass rates of 66.0-90.4% across 94 tasks. Both longer workflows and reduced guidance can limit agent performance, but in different ways for different agents: they lower the pass rates of the weaker agents, whereas the strongest agent falls only when a long workflow is combined with reduced guidance. Failure analysis attributes most failures to scientific errors rather than to errors in software usage. CompMat-Bench provides a basis for comparing agents on the steps of real materials research and for analyzing agent failure modes.

Speculative decoding has achieved substantial lossless speedups for LLMs, but remains less effective for large vision-language models (LVLMs), where lightweight drafters struggle to use rich multimodal information. A second limitation is that standard distillation supervises the drafter only along the original training trajectory, without modeling how target predictions shift after the drafter's own proposals. As drafting moves away from this trajectory, the drafter can increasingly disagree with the target, reducing acceptance in later steps. We propose HAWK to address both limitations. HAWK uses representation similarity to select informative target layers and learns how to combine their hidden states. For visual information, it directly provides the drafter with compressed visual hidden states from the target model instead of raw visual tokens, making the visual information easier for a shallow drafter to use. HAWK also trains the drafter to capture how target predictions change after its own proposals, improving its agreement with the target during multi-step drafting. On SmolVLM-256M across ten multimodal benchmarks, HAWK raises average acceptance length from 3.32 to 4.08 and speedup from 2.19x to 2.60x over EAGLE-3 under greedy decoding, and from 2.89 to 3.41 and 1.92x to 2.19x under sampling.

In this paper, we extend earlier findings of supra-competitive outcomes in optimal-execution games by identifying a learned punitive mechanism that deters deviations and provides behavioural evidence of collusion. We investigate this mechanism in a two-player, finite-horizon Almgren-Chriss liquidation game. Independent proximal policy optimisation agents with access to within-episode price and action histories achieve costs below the Nash benchmark. We identify a profitable deviation by training against the mean learned liquidation schedule, then impose its first trade on one of the original agents. The opponent responds by accelerating liquidation. This response more than offsets the deviator's gain in every run and both player roles, while leaving the punisher's average payoff materially unchanged relative to not punishing under the same deviation. The punisher imposes greater losses on the deviator while preserving its own average payoff, despite the availability of more profitable, less punitive liquidation plans. Matching deviations and subsequent additional selling rise and later decline during training, while final policies retain an effective punitive response. We formalise two checks: whether punishment outweighs the gain from deviating, and whether the change in trading behaviour is large enough to account for the loss imposed. Both checks hold for the tested deviation. Together, these findings provide behavioural and economic evidence supporting a collusive interpretation of the learned supra-competitive outcomes.

Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial comprehension through an architecture combining geometrical tools with a LLM serving as a high-level orchestrator in grid-world environments. The agent first collects geodesic trajectories, which are then vector-quantized to extract a representative subset. Offline, the LLM associates a natural language description of the underlying behavioral patterns to each selected trajectory, making it a tool. Online, the LLM chooses the appropriate tool conditioned on the current state and goal. Low-level control is handled by primitive actions that execute the trajectory associated with the tool. From an agentic AI perspective, this approach separates learning into two levels: tool discovery is handled through unsupervised quantization of trajectories, while reasoning and decision-making are handled by the LLM. We test the approach in a partially observable dynamic 2D grid environment with an open vision-language model (Qwen3.6-35B-A3B). Pairing the geometry-derived tool library with an agent-centered zoom tool and a collision detection tool lets a fast, non-reasoning configuration match the goal-reaching rate of a much more costly chain-of-thought version, while cutting the cost of a decision from minutes to seconds.

Explainable suicide-risk assessment requires models not only to estimate risk severity, but also to identify supporting language and the risk and protective factors expressed in a post. We present our system for the IEEE BigData 2026 Cup on Explainable Suicide Risk Assessment on Social Media, which addresses three tasks: risk-level classification, evidence phrase extraction, and multi-label factor identification. Our approach adapts Qwen2.5-Instruct models using quantized low-rank adaptation (QLoRA) and an answer-masked causal language-model objective. We jointly train across all three tasks for risk classification, jointly train on Tasks~1a and 1b for evidence extraction, and adapt Task~2 separately for factor identification. We also tailor aggregation to each output: we average risk-level probabilities from the 32B and 72B models, combine evidence phrases through cross-fold consensus, and calibrate factor-specific decisions through rate matching based on out-of-fold operating points. On the official leaderboard, the final system achieved a composite score of 0.7738, with 0.8089 on Task~1 and 0.6919 on Task~2. Across the evaluated configurations, three-task training performed best for Task~1a, joint training on Tasks~1a and 1b performed best for Task~1b, and task-specific training performed best for Task~2. Probability averaging further improved Task~1a when component models had complementary errors. These findings highlight the value of tailoring both training objectives and aggregation strategies to the output structure of each task within a unified language-model framework.

Legal research is a core and time-consuming legal workflow. Lawyers must identify controlling authority, verify that it remains valid, reconcile statutes and cases, and synthesize a grounded answer. Language model agents are a natural fit for this retrieval-intensive workflow, and automating even part of it would be valuable. But that value depends on reliability: a single missing authority, stale citation, or wrong legal conclusion can make an otherwise plausible answer unusable. We introduce \textbf{Legal Research Bench} (LRB), a benchmark of 413 open-ended U.S. legal research questions written by experts, each paired with a gold answer, supporting authorities, and a binary grading rubric. We evaluate thirteen frontier models in a harness with web search, case-law search, page parsing, and retrieval tools. We score agent responses through all-pass grading with source verification, where a response is correct only if every required criterion is satisfied and its cited authorities verify. We also validate the LLM judge against expert attorneys ensuring that benchmark scores track attorney judgment. Agents remain far from reliable: among the models we tested, the strongest, Claude Opus 4.8, is fully correct on 42.9\% of questions. Performance also varies substantially by task setting: all-pass rates differ across areas of law and are lower on questions requiring reconciliation of conflicting authorities. Across models, more turns, tool calls, and inference cost do not predict higher accuracy.

Historical music restoration (HMR) has almost exclusively focused on constrained problems such as Super-Resolution or the restoration of solo pieces, under-exploring the general task of restoring orchestral historical music, which has multiple instruments. This under-exploration is largely because the HMR domain, early-20th-century recordings, has no pre-degradation ground-truth pairs, making the restoration task unsupervised and more challenging. This paper presents a supervised end-to-end orchestral HMR benchmark by exploring both the synthetic degradation functions and the end-to-end generative deep-learning restoration methods. We simulate the historical recording degradation chain more faithfully than prior work, which makes orchestral restoration into a tractable supervised problem. A latent flow-matching model trained on the resulting synthetic pairs outperforms existing HMR baselines on intrusive, non-intrusive, and subjective evaluations. We also curate and release a 9.3-hour license-free, unpaired, historical classical-music test set, along with code and audio demos.

Large Language Models increasingly serve as interfaces for knowledge-intensive information seeking tasks across languages by synthesizing multilingual evidence. Prior work has shown that they often exhibit query-language preference -- the tendency to favor sources written in the language of the query -- but has largely examined this behavior in settings where equivalent knowledge is available across languages. However, this bias becomes consequential when sources in different languages provide incomplete or inconsistent accounts of the same fact, since the information users receive then depends on the sources a model selects to use. To characterize query-language preference under such cross-lingual knowledge disparities, we introduce Waldo, a multilingual Question-Answering (QA) benchmark constructed from Wikipedia. Waldo contains 12K QA pairs targeting knowledge gaps, where a fact is available in one language but absent in another, and knowledge conflicts, where language editions provide conflicting versions of the same fact. Evaluating eight models across five languages, we find that when one language edition merely lacks the relevant fact, models generally use evidence from the other language regardless of the query language. Under conflicting accounts, however, model responses strongly align with the document in the query language, causing semantically equivalent queries to elicit different accounts depending on the user's language. Finally, we explore two different approaches that could mitigate this preference under knowledge conflicts: a mechanistic intervention that ablates attention heads associated with query-language preference, and LoRA-based training, which reduces the preference gap by up to 61.5%.

The rapid proliferation of data centers (DCs), driven by cloud computing and artificial intelligence (AI), has led to massive energy demand and carbon emissions, posing significant sustainability challenges. Carbon-aware optimization in geographically distributed data centers has been widely studied. Most existing approaches mainly focus on operational carbon emissions from server usage. However, existing literature often ignores workload-induced thermal stress, which accelerates nonlinear hardware degradation. This leads to more frequent server replacements and ultimately increases embodied carbon emissions. To address these limitations, we propose a comprehensive carbon life-cycle modeling framework for distributed data centers. Apart from operational carbon emissions, this work combines workload scheduling with a utilization-dependent exponential aging model to evaluate long-term carbon costs from server degradation. In order to solve the proposed optimization model in an online and privacy-preserving manner, an enhanced Lyapunov framework with time-varying queue shifting (TVQS) is first introduced to handle system uncertainties. Then, a zero-sum perturbation-based alternating direction method of multipliers (ZSP-ADMM) framework is developed to enable distributed coordination across geographically separated data centers while protecting locally exchanged workload information. Simulation results demonstrate that the proposed approach achieves up to 13.0% lower carbon emissions and 12.6% lower operational costs compared with benchmarks.

Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappears during a task. We introduce MIKASA-Robo-VLA, a benchmark of 90 language-conditioned manipulation tasks. All but 10 hide the cue an action depends on. Those 10 are reactive controls. MIKASA-Robo, the suite it rebuilds, has 32 tasks and uses language only in a representative VLA subset. Here every task provides an instruction, while memory-dependent tasks hide a task-relevant cue and reactive controls keep it available. For 70 tasks, environment phase timings specify an information gap, and for 28 of them the gap exceeds the 16-frame window of the widest fixed-context VLA we survey. The gap counts only the interval the cue is provably absent, not the full duration a policy must retain it, so every memory-dependent task still requires memory by construction, including the ones whose measured gap is short. We release 22,500 oracle trajectories across 10 memory types in RLDS and LeRobotDataset v3. A reference $π_{0.5}$ baseline with current images and proprioception, but no observation history or explicit memory module, is fine-tuned on 14 tasks and achieves 0.211 $\pm$ 0.044 mean task success. Its lower success on the evaluated Long-split tasks is confounded by open-loop chunking and the memory types represented in that subset. Project page: https://mikasarobo.github.io/

Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for runtime safety through reasoning monitoring and correction. In this work, we define and operationalize two evaluation axes for assessing when this interface can improve embodied behavior: correctability, which measures whether unreliable reasoning can be detected and improved during generation, and actionability, which measures whether reasoning corrections produce behaviorally meaningful changes in the intended direction. To enable correctability, we introduce Token-level Reward for Utility-Steered Chain-of-Thought (TRUST), an offline-trained value model that predicts eventual reasoning correctness from partial prefixes and uses these estimates to monitor and selectively steer reasoning generation in frozen VLA policies. On the Alpamayo 1.5 driving VLA, TRUST monitors correctness with 88.9% accuracy and improves reasoning correctness from 75.9% to 90.0%. On a baseline-defined challenging subset in AlpaSim, TRUST reduces collision rate by 30.4% and maximum trajectory error by 11.5% relative to the unsteered policy, outperforming a compute-matched Best-of-4 baseline. On the DeepThinkVLA manipulation VLA, TRUST improves the correctness of grasp-state claims from 69.3% to 90.2% and action-choice claims from 68.8% to 85.9%, yet closed-loop task performance on LIBERO-Plus remains largely unchanged. Empirical analysis reveals intent-consistent behavioral effects in Alpamayo 1.5 but limited effects in DeepThinkVLA, helping interpret these different task-level outcomes. Together, our results show that gains in reasoning correctness do not automatically imply gains in embodied performance, motivating evaluation of correctability and actionability when using CoT as a runtime safety interface.

In frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems, the uplink (UL)-to-downlink (DL) channel covariance matrix (CCM) conversion problem is studied to relieve the heavy burden of DL training and feedback required for channel estimation. Learning- based methods perform well up to a certain array size, but for a fixed dataset size their accuracy deteriorates with the number of antennas, to the point where simple model-based methods outperform them. This paper identifies a key cause of this behavior and addresses it. The mean angle of arrival (AoA) induces a phase ramp along the lags of the CCM. Since the oscillation rate of this ramp grows with the number of antennas, a dataset of fixed size becomes increasingly sparse relative to the variation that must be captured. We propose estimating the slope of this ramp from the UL CCM separately and mapping it to the DL band in closed form, leaving the learner with a residual that is largely insensitive to the mean AoA, which substantially reduces the performance degradation with an increasing number of antennas. The proposed scheme, termed deramping, is a combination of pre- and post-processing steps that applies to learning-based conversion methods without altering their internal structure, as demonstrated on three structurally different learners. Simulation results show that deramping reduces the covariance estimation error of all three learners under uniform, Laplacian, and Gaussian angular power spectra,keeps the interpolation-based learners ahead of a model-based benchmark at large array sizes, and improves downlink channel estimation.

In partially observable reinforcement learning (RL), a later observation can make stored information obsolete or change what it implies for the next decision. Memory architectures and benchmarks for RL mostly test retention, the ability to keep information unchanged until it is needed. We formalize two further requirements. Rewriting sets the decision-relevant content to a value independent of the old one, and experience fusion transforms the old content by a rule that a later observation specifies. For tasks built from such updates, we count the memory states that a solution needs, and several baselines reach their lowest success rates on compositions that need more states. We introduce ALER (Adaptive Learnable Experience Rewriting), an agent that pairs an LSTM with a slot memory. An independently addressed Gumbel-Softmax write that concentrates its weight on one slot overwrites that slot, and a learned gate fuses the retrieved content with the recurrent state before the policy and value heads. We also introduce Rune-Mazes, three environments in which rune observations invert, cancel, reset, or repeat updates of a hidden cue under vector and pixel observations. Against seven baselines, ALER reaches a success rate of at least $0.82$ in all sixteen Endless T-Maze configurations and at least $0.99$ on all five Rune T-Maze compositions, and it has the highest mean success rate on four-branch Rune Multi-Corridor with an Invert rune. On pixel-based Rune MiniGrid Memory, it has a higher mean success rate than PPO-LSTM in eight of ten configurations. Project page: https://quartz-admirer.github.io/ALER-Adaptive-Learnable-Experience-Rewriting/.

An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability to generalize as network scale changes. Hierarchical RL reduces decision complexity by separating strategic targeting from tactical execution, but it does not eliminate this retraining dependence. We investigate whether frozen, zero-shot large language models (LLMs) can provide retraining-free control in hierarchical cyber defense and how performance changes as LLM control is extended from planning to execution. We formulate a controller-agnostic planner-executor hierarchy in which the planner selects a subnet to defend over a fixed horizon and the executor selects defensive actions within that subnet. Using the high fidelity Cyberwheel environment, with its built-in automated red team agent mapped to the MITRE ATT&CK framework, we compare RL+RL, LLM+RL, and LLM+LLM configurations using six models ranging from 3B to 70B parameters, including two cybersecurity-specialized models, across small, medium, and large networks. Replacing only the planner with an LLM yields limited gains as network size increases. In contrast, extending LLM control to execution produces notable improvements for sufficiently capable models. For instance, a frozen general purpose 70B model holds successful lateral movement to approximately 1% of steps and attacker impact near zero across all three network scales using the same model weights, while the RL baseline is retrained for each scale. Our results show that sufficiently capable frozen LLMs can maintain strong defensive performance across the evaluated network scales without task-specific retraining, while also indicating that strong tactical execution is important to realizing the benefits of LLM-based control.

Activation memory, not compute, limits CNN inference on constrained hardware such as microcontrollers. Direct in-place convolution removes the dual-buffer cost, but the memory-optimal formulation of Gural and Murmann assumes valid padding, unit stride, unit dilation, and odd square kernels, and needs a non-sequential traversal costing $2\times$ inference time in transposes. We identify two regimes in which their published closed form does not hold: (1) an under-allocation of exactly $(k-1)C_{in} \bmod (C_{out}-C_{in})$ scalars, active on every convolutional layer of their own deployed network and manifesting as a silent corruption of still-live input; (2) an unbounded overestimate, up to $2{,}432\times$, once the critical leg leaves the output grid. We correct both and generalize to arbitrary stride, dilation, padding, and rectangular kernels. We then propose Right In-Place (RiP) convolution, a bit-identical operation in which every layer reads its input right-aligned in a shared workspace and writes its output left-aligned from index zero. The debt is piecewise affine in the output pixel index, so evaluating its breakpoints in $O(1)$ yields the minimum safe gap without enumerating the output grid, with row-major access preserved. Across $10{,}000$ random layers RiP produced no corruption, and across 84 convolutional layers from 25 architectures it matches the herringbone workspace exactly on 58 and within 5% on 81, using 24.8% less memory than dual buffering on average. Written into TinyEngine's kernels and deployed to a Raspberry Pi Pico 1 and Pico 2, it cuts peak activation memory across eleven MCUNet models by 12.5 to 33.3% at unchanged cycle counts and bit-identical outputs, raising the number of models that fit the Pico 1's 256 KB SRAM from six to nine.

People are increasingly delegating tasks to AI agents, and those agents are increasingly encountering other people's agents over shared resources such as a codebase, a calendar, or a budget. When each agent acts for a different user with different goals, coordination often fails, and the group ends up worse off than if a single agent had acted for everyone. We study this multi-user, multi-agent setting across five frontier models and 77 scenarios in four environments: an API key environment in which agents share a compute budget, a clinic in which they share a calendar, a personal assistant environment in which they share a group order or booking, and a merge queue in which they share a release cutoff. In each scenario, we compare a single agent that serves every user (a coordinator) to a team in which each agent serves one user, with and without a communication channel between the agents. Teams deliver worse group outcomes than the coordinator in every environment: without a channel, they completely collapse in two environments, and even with one, coordination overhead creates substantial gaps. For example, in the personal assistant environment, the coordinator fulfills a targeted user request about twice as often as teams. We identify distinct behaviors associated with this poor group-level performance, including stalling as teams grow, overriding each other's actions, and fabricating claims. We find effective but environment-specific mitigations, such as a team lead, explicit procedural instructions, and a platform check that makes an agent read its peers' messages before committing. We will release the API key, clinic, and personal assistant environments as MAMUBench, comprising 74 scenarios for evaluating multi-user, multi-agent coordination.

Aesthetic image cropping aims to identify the optimal crop of an image in terms of aesthetics and composition. While supervision based on annotated data is fundamental, the field has been hindered by a long-standing problem: existing datasets suffer from (1) human subjectivity and (2) rigid discreteness confined to fixed sampling grids. These flawed annotations not only limit the accuracy and generalization of trained models but also severely distort fair evaluation. To overcome this, we propose to model human cropping preference as a multi-peaked, continuous, and sharp field over the crop space. We introduce the Continuous Preference Field (CPF), which recovers a dense preference landscape from discrete annotations through (1) peak clustering, (2) off-lattice refinement, (3) negative shaping, and (4) field assembly. Based on this, we train CPIC, a VLM-based cropping model optimized via GRPO with the CPF reward, which overcomes template collapse, achieving state-of-the-art performance and exceptional out-of-domain generalization. Finally, to resolve the long-standing benchmark evaluation crisis, we introduce CPICD, a comprehensive recalibration of existing ground-truth boxes. By leveraging the CPF to correct grid-bound artifacts across mainstream benchmarks, CPICD establishes a rigorous and reliable foundation for future cropping research. Extensive experiments and user studies demonstrate the superiority of our CPF, CPIC, and CPICD. Code, model, and data are available at https://github.com/zzqingz/CPIC.

A common approach to world-model simulation for vision-language-action (VLA) systems is to predict future RGB observations and then re-encode them into policy inputs, introducing an indirect interface between simulation and downstream policy execution. We instead investigate whether world dynamics can be modeled in a compact, policy-oriented state derived from VLM visual tokens. A key challenge is that raw VLM visual tokens are high-dimensional, making efficient and accurate autoregressive dynamics modeling challenging. To address this, we introduce Token-World, an action-conditioned world model that compresses VLM features into a compact token state, learns future dynamics in this reduced space, and maps predicted states back to the original policy-facing representation for downstream use. Across manipulation benchmarks, Token-World improves open-loop feature fidelity and policy-action consistency over recent world-model simulators, with slower degradation over long rollout horizons. In closed-loop evaluation, its simulated policy performance correlates more strongly with reference policy performance than Ctrl-World ($r=0.794$ vs.\ $0.583$), while requiring lower simulation latency. Ablations further show that compact-representation design and dimensionality substantially affect future-state prediction. Code will be available at https://chuyaofu.github.io/Token-World/.

Multi-reward reinforcement learning trains large language models to satisfy multiple behavioral objectives simultaneously. Reward-wise normalization, as used in GDPO, preserves reward-specific relative information within rollout groups, but different objectives can still exhibit uneven learning progress. We study this behavior through advantage energy, the sum of a reward's squared advantages over a batch. Under idealized GDPO normalization, we show that this energy is proportional to active-group density: the fraction of rollout groups in which the reward provides nonzero relative advantages. This reveals a residual batch-level signal imbalance and provides a basis for calibrating reward contributions. Based on this relation, we propose Density-Aware Reward Aggregation (DARA). We derive an inverse-square-root density correction that gives greater weight to signals from less frequently active rewards. DARA computes its weights from each rollout batch, adapting to changes in reward activity throughout training without modifying the underlying policy optimization objective. Experiments on tool calling and mathematical reasoning show that DARA learns the targeted behaviors faster than GDPO, reaching high format compliance in up to 26% fewer training steps on tool calling and near-saturated length compliance in up to 65% fewer steps on mathematical reasoning, while remaining competitive in final performance. Our code is available at https://github.com/zhaihaotian/DARA.

Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant frames. Existing score-based methods, however, typically search within a fixed, uniformly sampled candidate pool, preventing evidence outside this pool from ever being selected. Given a limited relevance-scoring budget, the key challenge is to allocate evaluations adaptively to promising frames while continuing to explore underrepresented temporal regions. We introduce FORTE, a training-free framework that addresses this challenge through two stages: adaptive relevance scoring and global keyframe optimization. Starting from sparse, uniformly distributed observations, our efficient Gaussian-process relevance predictor estimates relevance for unscored frames, exploiting temporal locality and the approximately banded kernel structure to reduce the core computation from cubic to linear time in the number of frames for fixed bandwidth. The scoring stage then selects which frames to score next by balancing predicted relevance with temporal coverage, prioritizing promising regions while also exploring less-represented parts of the video. The optimization stage selects the final keyframes by maximizing an objective that jointly captures measured relevance and temporal coverage. We derive an exact algorithm that leverages the logarithmic coverage structure to identify the optimal subset of the scored candidate pool in time linear in the pool size, for a fixed final-frame budget. Experiments on four long-video question-answering benchmarks show that FORTE achieves the highest observed mean accuracy among the compared selectors under every tested scoring budget. Further evaluations demonstrate its consistent effectiveness across different relevance scorers and downstream MLLMs.

Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between capability and alignment, and between capability and faithfulness, but a third tension remains underexplored: the alignment-faithfulness conflict. We show that aligned models systematically deviate from their inputs on unsafe or sensitive content without disclosing the modification, a failure mode we call alignment-induced unfaithfulness (AIU). Unlike capability-driven unfaithfulness, which comes from errors in knowledge or reasoning, this is induced by post-training mechanisms that override adherence to the input. We introduce FaithConflict, a controlled dataset isolating both conflicts, and two complementary taxonomies: behavioral (B1-B8) and chain-of-thought reasoning (C0-C6). Across models, AIU increases with scale and more sharply than capability-driven unfaithfulness, a reverse scaling law; intermediate checkpoints show it is amplified during post-training, with DPO the stage at which the gap both grows most and becomes least visible. Prompting-based mitigation does not resolve it, revealing a capability-alignment-faithfulness trilemma in the design and evaluation of LLMs.

Operator learning on probability measures can be accomplished with transformers. For measures with polynomial tails, the exponential weighting in softmax can make the corresponding measure-level attention integrals diverge. This motivates replacing the exponential with slower-growing functions. We construct two benchmarks for operator learning on measures with closed-form targets. We use these benchmarks to study attention kernel growth and data transformation in post-norm transformers. Without data transformation, the softmax models exhibit ensemble collapse on both heavy-tailed benchmarks, while the three slower-growing kernels avoid collapse. Symlog preprocessing allows softmax to avoid collapse on the matrix inverse task but not on the sheared swap task. On the Gaussian control, all four kernels perform similarly. We also examine how sample size affects the sensitivity of empirical energy and Wasserstein distances to tail differences. These results support slower-growing attention kernels as an effective design choice for post-norm transformers learning from heavy-tailed ensembles.

Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient histories. Although long-context models can process increasingly large amounts of information, providing more history does not necessarily make relevant evidence more accessible or improve reasoning. We compare five context strategies (Full, Recent, Episodic, Semantic, and Hybrid) on MedLoCoMo across four open-weight LLMs, examining answer correctness, robustness to query-evidence distance, and abstention on questions with unsupported premises. Episodic and Hybrid generally achieve the strongest overall accuracy, while Recent Context degrades most as supporting evidence becomes more distant; Episodic and Hybrid maintain the highest accuracy at long distances. Analysis of adversarial questions further shows that strong performance on answerable questions does not necessarily translate to successful abstention when the available history does not support the requested conclusion. These findings show that reliable longitudinal reasoning depends not only on how much history an LLM can access, but critically on how relevant evidence is selected and presented for reasoning.

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains unclear. Existing benchmark paradigms often suffer from fragmented evaluation, focusing on isolated cognitive stages while overlooking the inherent synergy between perception, reasoning, and physical judgment. The lack of a holistic perspective limits the ability to diagnose whether VLMs can reliably evaluate the physical authenticity of emerging generative models. To address these issues, we introduce PhysVista, a benchmark designed to evaluate physical intelligence in VLMs through a closed cognitive loop framework inspired by the human seeing-reasoning-assessment process. PhysVista restores this loop by jointly evaluating physical state perception, physical dynamics reasoning, and physical plausibility assessment. It further distinguishes event-level reasoning and scale-level reasoning to enable fine-grained analysis of physical understanding. In addition, PhysVista incorporates both real-world and AI-generated videos, allowing evaluation across diverse domains and emerging generative scenarios. Extensive experiments across a diverse set of VLMs reveal substantial limitations in physical reasoning and plausibility assessment, highlighting a persistent gap between visual recognition and genuine physical understanding, and pointing toward more principled designs for physically grounded multimodal intelligence.

While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive memory requirements. Extracting a compact subset of experts presents a promising solution. However, existing expert selection heuristics predominantly rely on Top-k ranking, which isolates the evaluation of individual experts and ignores the intricate inter-expert dependencies introduced by the MoE gating network. In this paper, we propose DS-MoE, a theoretically grounded framework that redefines expert selection via difference-of-submodular (DS) optimization. By analyzing the second-order Taylor expansion of the loss degradation, we reveal functional duality within expert combinations: redundancy (where experts encode overlapping representations) and synergy (where experts provide complementary error cancellation). To navigate this duality, we mathematically decouple redundancy reduction from synergy maximization by formulating the selection objective as a DS function. Furthermore, we devise a tailored majorization-minimization (MM) algorithm with provable monotonicity guarantees to efficiently identify the optimal expert subset. Extensive experiments demonstrate that DS-MoE effectively preserves indispensable expert combinations, achieving superior performance compared to the state-of-the-art baselines.

Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning (RL) and large language models (LLMs) offer complementary mechanisms for the planning and execution such agents require, and prior work has combined them in hybrid hierarchies. Yet a given architecture is typically developed and evaluated within a single environment, leaving open whether an observed advantage reflects a generally stronger decision mechanism or merely alignment with a particular setting. We address this gap with a controlled cross-environment comparison of two homogeneous hierarchical red team architectures: an RL planner with an RL executor (RL+RL) and an LLM planner with an LLM executor (LLM+LLM). We evaluate both against expert autonomous defenders in CybORG CAGE-4 and in Cyberwheel at two network scales, across 18 configurations under one unified disruption metric. We find a pronounced environment-dependent inversion. RL+RL wins the compact, densely rewarded CAGE-4 (78.5% disruption success versus 18.0% for the strongest LLM configuration) and the 100-host Cyberwheel network (81.0% versus 50.5%), while a pretrained cybersecurity LLM agent wins the larger, escalation-gated 1010-host Cyberwheel network (55.0% versus 0.0% for RL). A kill-chain analysis explains the inversion through architecture-specific bottlenecks that aggregate success rates conceal.In the 1010-host Cyberwheel network, RL discovers and compromises hosts but stalls at privilege escalation, whereas in CAGE-4, LLM agents obtain privileged access but rarely convert it into operational impact. These results indicate that conclusions drawn in a single environment may not generalize, and that hybrid planner-executor designs should be motivated by specific failure modes rather than the assumption that one architecture is universally preferable.

We evaluate hybrid quantum-classical machine learning for the reduced-order prediction of spatiotemporal brain deformation fields. To mitigate the computational intractability of high-dimensional displacement fields, we employ Proper Orthogonal Decomposition (POD) to project the data into a compact latent space. Within this framework, we formulate two distinct learning objectives: static temporal-to-latent regression and autoregressive latent state forecasting. We systematically benchmark compact classical baselines against both minimal and enhanced hybrid quantum architectures. Our results demonstrate that classical networks provide the strongest baselines in the present setting. For static regression, a classical POD-MLP outperforms all evaluated quantum variants, although an enhanced Variational Quantum Circuit (VQC) substantially improves upon a minimal VQC baseline. For temporal forecasting, a classical POD-LSTM delivers superior predictive accuracy and statistical robustness compared to an enhanced Quantum LSTM (QLSTM) across varying history windows and random initializations. Overall, this study establishes reduced-order physical field learning as a rigorous testbed for near-term QML, highlighting that while hybrid enhancements successfully recover expressivity in weak quantum circuits, classical architectures retain a definitive advantage in both fidelity and stability.

We study adversarial online maximization of nonnegative, non-monotone DR-submodular functions over compact convex down-closed sets. A learner commits each action before observing its objective and competes with the best fixed action in hindsight. We prove a comparator-uniform first-order inequality that gives coefficient $4/9$, improving the online $0.401$ benchmark, with one gradient query and one projection per round and $O(\sqrt T)$ expected approximate regret. If $ζ{\bf 1} \in K\subseteq[0,1]^d$, the coefficient improves to $\underlineα(ζ)=\tfrac12-(1-2ζ)_+^2/[2(3-2ζ)^2]$. The proof is a direct ordered-coordinate argument with an objective-independent rational action. Conversely, a three-group symmetry-gap construction yields an offline oracle upper bound $β_*=0.470438681380894\ldots$ at $ζ=0$, even with exact value and full-gradient responses. A parameterized extension and exact finite-instance bounds define an upper function for every $ζ$. The lower and upper bounds match at $1/2$ for $ζ\ge1/2$, and show that the optimal deficit from $1/2$ is $Θ((1/2-ζ)^2)$ as $ζ\uparrow1/2$. For coefficient-revealed polynomials we obtain $1/2$ for quadratics and a geometry-dependent cubic coefficient starting at $8/17$, including $0.49$ at $ζ=1/5$. A constant objective sequence yields an offline $(4/9-\varepsilon)$ approximation with polynomially many first-order queries on the cube and projections, without requiring a supplied positive lower bound on the optimum. We also give nonanticipating adaptive-adversary and value-feedback guarantees, including $O(T^{3/4})$ regret with one noisy value per round.

Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits requires training samples that capture both visits, often spanning minutes. Yet dense attention over the full span incurs quadratic costs, making long-span supervision expensive. Memorizon breaks this coupling: long spans are needed for supervision, but not for attention, since the two visits can share a forward pass without including every intervening frame. A training sample covers a span of any length but is scored only on its last $k$ chunks. Instead of tokenizing the history before them, each scored chunk retrieves its own top-$K$ latents by camera co-visibility, and the union of these requests forms a shared bank. The bank is bounded by $kK$, so the sequence stays bounded however long the span; at the shortest span the recipe is exactly conventional training. Adding the bank raises the cost of a step once; beyond that, a longer span costs little, and going from 100 to 400 s adds 12% to the step time. Against a sliding-window baseline, retrieval raises revisit consistency on every split, and a span long enough to reach the first visit of each return adds a further 24% to 30%, at some cost in image quality; beyond that span, more length no longer helps. Filling the bank from another episode lowers revisit correlation by 83%, so the model uses what it retrieves. Project page: https://tingtingliao.github.io/memorizon

Continual imitation learning evaluates whether a robot can learn new knowledge without forgetting previously learned skills. However, retaining task performance does not ensure the behavior remains grounded in language because policies may rely on scene cues, object associations, or memorized task structure. We introduce a benchmark protocol to study how language-guided behavior changes as robotic policies learn successive tasks. We construct meaning-preserving and meaning-changing instruction variants for the Goal, Spatial, Object, and Long suites of LIBERO. Policy experiments focus on LIBERO-Goal, evaluating Original and Paraphrase instructions after each continual-learning stage. We compare representative continual imitation learning methods under their original assumptions while separating task competence from language sensitivity. The proposed diagnostics complement standard learning and forgetting metrics by measuring semantic robustness, goal adaptation, and language sensitivity. Results show that strong continual-learning performance does not always translate to reliable language grounding, and our diagnostics help determine whether retained skills remain correctly guided by their instructions. Additional materials are available at https://sites.google.com/view/stillgrounded

Claims about the grammatical competence of multilingual language models vary sharply with how competence is measured, yet the interaction between evaluation paradigm, post-training, and language resource availability has not been systematically examined. We evaluate base and post-trained models from six families on MultiBLiMP, a syntactic minimal-pair benchmark covering 101 languages, using four evaluation methods. We report three principal findings. First, post-training degrades grammatical competence, but the magnitude of this effect is reduced unevenly by model scale, while low-resource languages bear the highest cost. Second, post-trained models retain grammatical knowledge they cannot articulate through explicit prompting, yet this is measurable only in high-resource languages, because near-chance baselines in low-resource settings leave little knowledge to hide. Third, native-language prompting recovers otherwise hidden competence on low-resource languages, demonstrating that only high-resource languages can be probed directly from unprompted probabilities. We conclude that multilingual grammatical evaluation must adopt language-informed, multi-paradigm protocols to avoid systematically underestimating low-resource abilities.

A real-time auditory scene analyzer (ASA) aims to carry out the tasks of locating, separating and classifying the sound sources present in a given acoustic environment. Recently, an effort has been made into modelling an ASA as a multi-agent system, with each one of its agents performing one of the aforementioned tasks and communicating their results to the rest of their peer agents. These communication routes are used as feedback loops to fix local errors at a global level, providing robustness while reducing local complexity. An example of the benefits of this approach is the optimization of speech quality by correcting in real-time the estimated location of the speech source of interest. However, their optimization speed has been shown to be considerably slow. One possible reason is that it solely relies on a series of single quality estimations (provided by a reference-free quality estimator model) that vary considerably from one window to the next, which results in a difficult search space to optimize. In this work, a new optimization mechanism is proposed that instead relies on a series of sets of quality estimations over a range of locations, providing a clearer view of the search space, simplifying its optimization. The proposed ASA now has a considerably smaller optimization time, is more accurate, and is more stable when being evaluated in real-life acoustic scenarios to correct higher levels of localization errors, all while being less complex than previous efforts. The only trade-off is that there is an increase in the response time of the quality estimation agent, but the complete ASA is still able to run in real-time. The performance shown in this work again shows the benefits of modelling an ASA as a multi-agent system.

AI-generated content, often called AI slop, is increasingly common everywhere, particularly in academia. Slop in AI-generated scientific papers, however, has more complex patterns that cannot be easily detected by existing token-based AI detectors. Each part of such a paper looks plausible while the scientific reasoning that connects the parts breaks down, which can mislead how readers assess the work. We benchmark these failures as scientific slop through six measures across Structure, Argument, and Artifacts. We construct SciSlopBench with 390 AI-generated papers, mostly in computer science but spanning the life, social, and natural sciences, each paired with a human-written paper matched by research problem and contribution type. Our measures identify the AI paper in each pair with 85.9% accuracy, compared with 68.7% for Binoculars. Higher scientific slop accompanies lower ICLR ratings and distinguishes rejected from accepted papers above chance in every year from 2017 to 2025. Reducing these patterns, however, is not as simple as directly optimizing the measures. We therefore propose SciSlopHarness, a harness-level framework that guides a fixed LLM to revise slop only where the experiment records support the change. While standard revisions leave residual slop and direct slop-aware prompting triggers reward hacking, SciSlopHarness reduces the remaining AI-human gap by 63% over the strongest revision baseline without requiring human reference targets. Overall, we demonstrate that AI-generated scientific papers leave fundamental traces in their global reasoning, and that responsible mitigation demands strict evidentiary grounding rather than mere prose refinement.

Vision-language-action (VLA) models often struggle to generalize to skill combinations absent from their fine-tuning demonstrations, even when every constituent skill has been demonstrated. We focus on a vision shortcut as one failure mode: during fine-tuning, visual observations can serve as a proxy for the instruction, so a policy may execute a demonstrated combination associated with similar observations rather than the instructed combination. This motivates training with counterfactual pairs formed by holding a demonstration observation fixed while changing the instruction to specify an undemonstrated combination. These pairs, however, lack corresponding demonstrated action targets. Crucially, the currently required skill has already been demonstrated, but actions from those executions cannot serve as direct targets because the same skill can require different actions across observations. We propose CRAFT, which transfers supervision from demonstrated executions of the required skill to counterfactual pairs using skill representations that can be reused across executions of the same skill. Across three VLA models and two simulation benchmarks, CRAFT improves success on undemonstrated combinations while maintaining high success on demonstrated ones; it also improves compositional generalization on a real robot. Project website: https://taegeunyang.github.io/craft/

Conformal prediction guarantees marginal coverage, but a single calibration threshold can still spread that coverage unevenly, over-covering easy regions and under-covering hard ones. SimplexUQ is, to our knowledge, the first benchmark and reproducible protocol for measuring this allocation problem on simplex-valued predictions; it compares existing conformal wrappers rather than proposing a new one. Its task suite, SimplexTasks-12, combines six controlled synthetic regimes with six frozen-predictor real tasks spanning class probabilities, topic mixtures, spectral abundances, cell-type fractions, age distributions, and emotion mixtures. Each comparison fixes the predictor, score, and response-free stratification map, varies only the wrapper, and reports marginal coverage, worst-stratum coverage, max disparity, and within-task radius and compute. Global calibration can look valid while failing badly: on CIFAR-10 it attains 0.900 marginal coverage but only 0.542 in the worst entropy stratum, and Mondrian calibration raises that stratum to 0.886 while reducing max disparity from 0.358 to 0.022. No wrapper dominates, however. Under smooth synthetic heterogeneity, several repairs are competitive; fixed-map analyses show that rankings depend on the evaluation groups and protocol; and in a 12-task comparison, Mondrian has lower disparity on its single target partition for all 12 tasks, whereas BatchMVP has lower disparity over overlapping groups on five. These are empirical comparisons, not new coverage guarantees. A controlled predictor-bias sweep shows that removing predictor bias only partly reduces global-threshold disparity. We release task cards, result provenance, permitted derived arrays, and rebuild instructions, and treat wrapper selection as a diagnostic comparison rather than a universal ranking.

Neural operators learn maps between function spaces, while hereditary network dynamics are described by Volterra resolvents with non-rational Laplace symbols. We introduce a fractional Laplace neural operator (fLNO) that embeds this structure in the learned map. For commuting excitation--Laplacian pairs, one block graph-spectral layer represents the full linear Volterra solution operator exactly. We establish an expressivity frontier for finite rational realizations: they approximate fractional memory geometrically on compact frequency windows, but cannot reproduce the non-integer critical asymptotics generated by a branch point, and on the half-line the best rational rate is root-exponential. The same theory yields trainable parametrizations that enforce a prescribed stability margin by construction, and a graphon-transfer theorem separates genuine operator consistency from parameter sharing. In a common-data benchmark, positive rational operators can match or exceed fLNO accuracy on finite horizons, whereas in controlled near-critical experiments fLNO recovers the branching coordinate more faithfully with far fewer parameters; unconstrained rational fits can cross the stability boundary, while certified parametrizations cannot. A four-parameter spectral law transfers without retraining from graphs of size 48 to 192 with 0.51--0.62% relative error. Applications to Chilean aftershock sequences and to renewal models for Chile and 21 Italian regions illustrate structured inference with explicit uncertainty. The contribution is an operator-learning architecture in which exact memory structure, physical coordinates and stability guarantees coexist with competitive accuracy.

Before a difficult decision, people often act simply to understand the situation better. We turn an object to see another side, place alternatives next to each other, or change one condition and observe what happens. These actions may not complete the task, but they improve the evidence needed for the next choice. LLM-based agents can search and explore, yet agent design gives less attention to an earlier question: is the available evidence ready for the decision? Sometimes necessary evidence is missing. In other cases, the evidence is present but its form hides what matters, or the comparison needed to judge it does not yet exist. Cognitive science calls actions that improve the basis for a later choice epistemic actions. We bring this idea to LLM-based agents and distinguish three modes: acquiring missing evidence, transforming available evidence, and probing a system to create a revealing response. We use the term epistemic scaffolding for the interfaces, tools, and environments that make these actions possible and auditable. This paper argues that agent design must address how decision-ready evidence is produced.

We present Gumbel Straight Flow (GSF), a continuous flow map language model that leverages the noise-data coupling of a pretrained autoregressive language (AR) model. We theoretically demonstrate that the coupling between Gumbel noise and one-hot token sequences induced by an autoregressive model yields non-intersecting linear paths connecting the noise to the sequence representations. To further enhance high-quality few-step path sampling, we use a flow map semigroup objective where the tangent (velocity) condition is guided directly by the AR teacher. Across various benchmarks, including pretraining and downstream tasks, GSF can outperform current few-step language generation baselines.

When Isaac Newton discovered the law of gravitation, he did so through an iterative process of analyzing observed data such as planetary patterns, finding the underlying mechanisms by describing patterns in mathematical equations, and refining his theory against the Moon's orbit, revealing the startling insight that the same force governs both falling apples and orbiting planets. Would it be possible for AI agents to make similar discoveries? To measure this ability, we introduce EurekaBench, a cross-domain benchmark that tests AI agents' ability to conduct long-horizon experiments and discover mechanisms that explain observations. We evaluate these mechanisms by the scientific insights that can be derived from them. EurekaBench contains an expert-verified set of 26 long-horizon tasks across neuroscience, computer science, chemistry, astrophysics, geophysics, and plasma physics, with a total of 306 scientific insights that the discovered mechanisms are expected to support. Our evaluation framework tests three axes of scientific discovery: agents' ability to follow known scientific constraints, the predictive accuracy of the discovered mechanisms, and whether these mechanisms yield scientific insights or inform future research. Our results show that current AI agents often overly fixate on predictive accuracy optimization, surpassing human scientists, while falling substantially short in deriving scientific insights.

Next-generation large language models (LLMs) are expanding from the cloud to ubiquitous edge devices. However, edge devices typically either lack the memory to store increasingly large LLM weights or, even with enough memory, spend unaffordable energy on loading the weights. This raises our question: can an edge device run an LLM without storing or loading its weights, but receive them over the air and consume them on the fly? Inspired by wireless broadcasting, we present AIR-LLM, an LLM inference architecture for edge devices, which is composed of: (i) a central radio (e.g., 5G base stations) that broadcasts the LLM weights into the air, and (ii) the edge user that receives the weights and completes the general matrix-vector multiplication (GEMV) of LLM inference directly in the radio frequency (RF) domain using RF mixers. To further shorten the airtime, AIR-LLM exploits MIMO spatial multiplexing and proposes an energy-efficient precoder-postcoder pair on the edge to calibrate its own wireless channel. Since the central radio stays user-unaware, AIR-LLM is user-scalable so that one broadcast serves unlimited users within its coverage. We implement AIR-LLM on the NVIDIA Sionna ray-traced channels of two real-world urban scenes and the profiling of a real RF mixer. With a WikiText-2 perplexity degradation of 4.0% on LLaMA-3.1-8B, AIR-LLM saves the energy by 157.7x/40.4x against the FP16 and weight-only quantization baselines; with 20 users, its airtime is 104.1x/26.0x shorter, respectively.

Human motion, environmental contacts, and interaction forces are governed by common physical laws, yet existing approaches typically separate visual pose reconstruction from contact and force estimation. This separation limits joint reasoning and can propagate errors between stages. We introduce PACT, an end-to-end model that jointly learns to estimate human pose, contacts and contact forces from monocular video. Our approach augments a human reconstruction foundation model with learnable contact-force tokens and a temporal transformer that integrates visual features with world-space motion. Joint prediction heads refine human poses and estimate contacts and forces, while physics-based supervision encourages consistency between the reconstructed motion and interaction forces. To address the scarcity of force annotations, we develop a data annotation pipeline that combines contact labeling with physics-based motion and force optimization, producing training supervision from synthetic and real-world videos. We also introduce a real-world climbing benchmark ForceWall with climbing videos and corresponding ground-truth contact forces obtained from the force sensors. Experiments demonstrate state-of-the-art contact and force estimation, outperforming staged reconstruction approaches and generalizing to interactions beyond the training distribution. These results support end-to-end joint learning as an effective approach to recovering human motion and physical interactions from video.

Can a text-to-3D leaderboard change when every generated scene stays fixed? We audit this question for rendered-image evaluation, where camera settings and caption wording become part of the measurement protocol. Across 300 frozen scenes from six generators, we vary eight render and caption factors for 19 alignment evaluators plus one perceptual-quality control, then test four targeted scene degradations. Peak configuration variance exceeds between-generator variance for 17/19 alignment evaluators, with prompt-bootstrap lower bounds above 1 for 11/19. Rankings are more stable than scores, yet 18/19 evaluators change their point-estimate winner under some configuration. Pairwise protocol margin envelopes show which comparisons keep their direction across the tested settings. Selected pairs have opposite pointwise intervals, but no reversal survives simultaneous inference over the full search. Thus the observed winner changes are descriptive, not confirmed changes in generator superiority. Sensitivity remains separate: no evaluator, even the prompt-free control, exceeds 67% tie-adjusted directional discrimination on layout scrambling, which is diagnostic rather than human-validated ground truth. The audit separates score stability, decision uncertainty, and targeted sensitivity, and recommends reporting (generator, score, card ID) with protocol-dependent comparisons and selection-aware uncertainty.

Humanoid whole-body manipulation has advanced rapidly, enabling policies to coordinate locomotion, posture, bimanual interaction, and dexterous hand movements. Meanwhile, egocentric human videos provide diverse examples of everyday interactions across objects and scenes, offering scalable supervision without robot operation. However, existing supervision from these videos provides limited coverage of whole-body movement and coordination with hand-object interaction, while obtaining such supervision through humanoid teleoperation is also costly and difficult to scale. We therefore explore how human experience can support scalable learning of humanoid loco-manipulation. To support this study, we introduce HumanVerse-500, a 500-hour dataset of diverse human loco-manipulation behaviors in open-world environments, collected with a lightweight wearable system that synchronizes egocentric video with body and hand motion. Building on this dataset, we develop $λ_0$, a whole-body humanoid vision-language-action policy, through three-stage training that first learns interaction from diverse egocentric datasets, then coordinates body and hand motion using HumanVerse-500, and finally adapts the policy to downstream tasks and robot embodiments. Across these stages, $λ_0$ learns a shared representation space for human experience transfer, while domain-specific interfaces handle differences between human and robot states and actions. We evaluate $λ_0$ on SIMPLE and 4 real-world loco-manipulation tasks, achieving state-of-the-art performance, and further analyze its scaling behavior, generalization, and training-stage contributions to understand how human data support downstream whole-body humanoid control. We will release our code, models, and data to support further research.

LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computationally expensive. Jev-style models offer fast probabilistic predictions over finite fields, but require those fields to be specified in advance. This requirement limits autonomous task solving, where the available actions must be derived from natural language instructions and adapted through interaction. We introduce JevSpawn, a compositional policy that connects natural language task specifications to finite probabilistic exploration. Parallel action spawning is coupled with feedback driven branch selection, representation revision, and recovery from retained alternatives. Shared action structure and model prefixes reduce repeated generation and context computation without additional training. Evaluations on eight benchmark tasks against seven agent baselines and a TypeSafe Jev variant establish JevSpawn as a promising approach to structured agentic inference, with improved task performance and faster navigation.

We study how AI agents discover and validate scientific formulas using a controlled case study of the hydrotope, a recently discovered geometric formula that combines the different polynomial pieces of nonlinear surface-wave scattering into one global expression. This problem is deceptively difficult: simple formulas can hold within individual frequency regions, but the global result must identify their boundaries and combine exponentially many potentially active terms. We reconstruct how the formula was originally discovered through human--agent collaboration and analyze 18 single-prompt rediscovery runs under no hint and two forms of human guidance: a false hint representing an incorrect prior and a true hint representing domain-informed insight. Only four recover the formula across all kinematic chambers (i.e., regions in which a single polynomial form applies), while most unsuccessful runs find correct chamber polynomials but fail to combine them or test their full domain. Conventional and LLM-assisted symbolic regression and standard machine-learning regressors likewise fail to recover the global formula in our experiments. Guided by these failure modes, we test a PI$+$two-student workflow in which a coordinating lead agent assigns complementary analytic and numerical tasks to two research agents and independently evaluates their results. The PI$+$two-student team successfully rediscovers the complete hydrotope formula, while the same workflow applied to the harder three negative wavenumber problem discovers a new independent verified analytic expression for the six-point amplitude $A_6$.

Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of previously acquired knowledge, adaptation to new tasks, and strict parameter budgets. We present \textbf{ChainLoRA}, a replay-free continual merging framework built on chain-updated task-vector geometry. From a parameter-merging perspective, we formulate a geometric view of forgetting through a measurable interaction between task updates, separating directional overlap from coefficient coupling. Building on this view, ChainLoRA combines chain-updated training with post-stream adaptive SVD merging. During training, initialization and a one-sided orthogonality proxy use only the last carrier, keeping their historical-state footprint and regularization overhead constant as the task stream grows. At merging time, Adaptive SVD extracts a shared carrier and aligns it to the latest task through Procrustes adaptation. Our theoretical analysis shows that Procrustes adaptation facilitates geometric approximate separation of shared and task-specific components. The one-sided proxy further bounds inter-task interference. An effective-rank penalty additionally promotes efficient utilization of the task subspace during continual learning. Experiments show that ChainLoRA achieves state-of-the-art performance among the evaluated replay-free methods on the Large and SuperNI benchmarks, while remaining competitive on Standard CL and attaining almost the closest average scores to the evaluated replay-based method across all three benchmarks.

Autonomous large language model (LLM) agents increasingly interact in network environments where adversarial content can propagate between agents. Known attacks include agent worms, which spread through self-replicating prompt injections or configuration compromises. We introduce \emph{memetic trojans}, a distinct class of network-mediated attack that exploits agents' tendencies to retransmit and amplify content. Unlike agent worms, whose propagation is adversarially induced, memetic trojans exploit \emph{endogenous} transmission by embedding adversarial payloads in \emph{social contagions}: content agents have internal reasons to share. As part of our work, we extract social contagions from Moltbook, a social media platform for LLM agents. Controlled transmission experiments reveal large differences in virality: the most effective contagion is retransmitted in approximately 50\% of subsequent agent posts and upvoted at 2.5x the average post's rate. Its memetic trojan counterpart largely inherits these properties. Monte Carlo attack simulations show that memetic trojans amplify expected exposure by up to 3.19x. Network structure and amplification mechanisms strongly shape propagation, producing heavy-tailed outcomes with near network-wide exposure. These results identify endogenous social transmission as a distinct security vulnerability in multi-agent systems. Because propagation does not require agents to follow malicious retransmission instructions, defenses focused on prompt-injection detection or preventing agent compromise cannot alone prevent memetic trojan propagation. Securing large-scale agent ecosystems may require network-level defenses that account for how agent preferences, recommendation mechanisms, and network topology amplify adversarial payloads.

Code generation has emerged as a central capability of large language models, with coding agents now able to produce functionally correct software projects from natural language prompts. However, functional correctness alone does not capture a critical dimension of generation quality: environment specification, defined as the accurate identification of the dependencies required to execute generated code, is equally critical. We develop an agent protocol for environment specification and introduce a three-layer framework comprising declared, runtime-installed, and necessary-and-sufficient dependencies to systematically assess coding agents for environment specification. Using this protocol, we evaluate the extent to which coding agents systematically misspecify software environment dependencies and how this misspecification varies across three agents, four languages, and fifty programming tasks. Our results show that current coding agents exhibit systematic generalization failures along this dimension, producing dependency specifications that are inconsistent, redundant, or incomplete in ways that functional tests do not detect. Across agents, dependency set agreement is as low as 7% for identical tasks, and newer agents show no meaningful improvement, suggesting the failure is not resolved by scale or recency. The largest divergence occurs between the declared and runtime dependency layers, implicating environment priors learned from the models' training distributions as the primary driver. Our findings establish environment specification as a distinct, measurable axis of code generation quality that current benchmarks do not capture, and motivate training objectives and evaluation protocols that jointly optimize for functional correctness and environmental portability.

Automated classification of brain tumors from MRI is a heavily published application of deep learning in medical imaging, with reported accuracies on public benchmarks routinely exceeding 98%. However, accuracy does not capture a critical dimension of benchmark quality: dataset integrity, defined as the independence of test from training data at the image, patient, and acquisition-source levels. We introduce a three-layer contamination framework comprising duplicate, patient, and source-label leakage to assess the public corpora on which this literature rests. We audit the three most widely used corpora against a chest-radiograph negative control and quantify each layer's effect on measured performance across nine architectures and three evaluation conditions. Contamination is severe at every layer: 28.8% of the dominant corpus's official test split has a near-twin in its own training split, a second corpus leaks 22.3% of its test images byte-identically, 95.5% of traceable test images share a patient with training, and file-header features containing no anatomy separate tumor from no-tumor at 0.959 balanced accuracy, at parity with fine-tuned ResNet backbones. The unexpected result is that removing every identified leaked test image leaves balanced accuracy essentially unchanged: stable performance after deduplication does not establish benchmark integrity. Our findings establish dataset integrity as a distinct, measurable axis of benchmark quality that a stable leaderboard cannot certify. For biomedical research, reported accuracy on these corpora alone does not establish that a model has learned to recognize tumors rather than exploit dataset-specific cues. We release the contaminated-file lists, recovered patient identifiers, and deduplicated splits.

Scaling Transformers to long contexts is constrained by the quadratic cost of self-attention and the linear growth of key-value cache memory transfer. Sparse attention mitigates this by retrieving only relevant tokens, but current approaches either require large-scale training or, within the training-free regime, rely on semantically coarse heuristics or expensive clustering that is difficult to update efficiently during decoding. We introduce CommunityKV, a framework that formulates sparse attention as a community detection problem. CommunityKV constructs a token graph from the $QK^T$ scores already computed during standard prefill, and partitions the graph into communities to enable retrieval of semantically coherent token groups. A local update rule assigns newly generated tokens to communities in constant time, enabling sparse retrieval throughout streaming decoding without global re-partitioning. We evaluate CommunityKV on Qwen3 and Llama-3.1 models across three long-context benchmarks. With one graph per query head, CommunityKV delivers up to $1.25\times$ the end-to-end generation throughput of dense attention, while query-group graph aggregation yields up to $1.71\times$ with comparable accuracy.

Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder tasks can require expensive grading or execution infrastructure. These challenges are amplified in automatic prompt optimization (APO), where evaluation is repeated throughout the search for better prompts. Studying APO therefore requires a benchmark that is cheap and deterministic to score, hard enough to leave room for improvement, and renewable as models evolve. We introduce a chess benchmark built from 1,118 Lichess puzzles to study APO for frozen LLMs: we optimize their prompts without updating their model weights. Chess combines inexpensive exact-match scoring, engine-based evaluation of alternative moves, and a renewable supply of problems with adjustable difficulty. Unlike evaluations that report only success on isolated test items, the benchmark also connects puzzle-solving gains to short game-play rollouts within the same domain. We use it to evaluate six APO algorithms on eight target models, measuring not only baseline strength but also how much each model responds to optimization and whether optimized prompts transfer across models and to game play. Chess is thus a well-suited benchmark for APO: it is (i) challenging, as even the strongest evaluated model, Gemini 3.5 Flash (used as the meta-model), solves only about 55\% of puzzles; (ii) discriminative, revealing gains, unchanged performance, and regressions across methods and models; (iii) renewable, with fresh puzzles to reduce contamination risk and adjustable difficulty to maintain headroom as models improve; and (iv) affordable, as the complete study runs for around \$800. We release the puzzles, optimization and evaluation code, and dataset-renewal scripts (https://github.com/imec-ailabs/Automatic-Prompt-Optimization-with-Chess).

Machine-learning surrogates accelerate physical simulation, but lower prediction error need not coincide with lower error in physically relevant flow statistics. We examine this question for flow around a NACA4418 airfoil using paired computational-fluid-dynamics simulations and experimental particle-image-velocimetry measurements. A mean-preserving input intervention removes velocity fluctuations from selected regions of observed flow histories. Across four neural operators, removing fluctuations from the most energetic 10% of valid observed cells changes forecasts more than equal-area random removal. Because the masks are not matched for removed fluctuation energy, this contrast measures sensitivity, not independent evidence of physical importance. Separately, a CNO has lower velocity-field error but substantially higher two-component fluctuation-energy error than the reference on both analysis subsets. An output attenuation stress test also demonstrates disagreement between benchmark errors and domain-summed fluctuation energy. These single-benchmark results motivate reporting complementary physical diagnostics alongside aggregate prediction scores; they do not establish counterfactual physical correctness.

Foundation models pretrained on large-scale datasets demonstrate strong transferability to medical imaging tasks. However, understanding how their latent representations encode clinically relevant information remains an open challenge in safety-critical domains. This study proposes a prototype-based fuzzy-rule framework that interprets the patch-level features produced by the inner layers of pretrained foundation models, without any fine-tuning. Class-specific prototypes are learned by clustering in the feature space, yielding compact visual patterns. Patch features are then expressed as prototype similarities and classified by fuzzy rules with linguistic IF-THEN conditions that are human readable. The framework is applied across the final two blocks of ViT-S/16 backbones pretrained on ImageNet-1K and GastroNet-5M, and benchmarked against k-nearest neighbours, kernel SVM, and linear probing under identical frozen features, on wireless capsule endoscopy classification, gastrointestinal endoscopy classification, and colonic polyp segmentation. The experimental analysis shows that the proposed method, without backbone fine-tuning, reaches accuracy comparable to these black-box classifiers, and that domain-specific pretraining yields features that are both discriminative and symbolically compressible. Because the resulting rules are extracted from real data and expressed in interpretable terms, they are further used as an instrument to investigate synthetic medical images, providing a human-readable account of which real prototypes and rules a generator reproduces or fails to reproduce, localising where a synthetic image departs from real tissue rather than summarising it with a single score. The framework thus offers a transparent, depth-resolved view of how foundation models organise clinically relevant structure, together with a practical downstream use of the extracted rules.

KV cache pruning reduces long-context inference memory usage by evicting less important key-value pairs. KVzip estimates importance through context reconstruction: prompting a model to repeat the context chunk by chunk. This achieves strong compression quality at the cost of additional forward passes. Learned approximations reduce this cost but require model-specific training. We analyze how KVzip identifies important cached information and show how to approximate its reconstruction scores using information already computed during prefill. These findings motivate EchoPress, a training-free method that approximates reconstruction attention using queries and keys from standard prefill. For each request, it reconstructs only the first chunk to calibrate importance scores for the remaining context. Experiments on LongBench and RULER with Qwen3-8B and Llama-3.1-8B-Instruct show that EchoPress matches KVzip in task accuracy across eviction ratios from 50% to 90%, while reducing compression overhead by a factor of 1.7-19.6 and total prefill time by a factor of up to 2.9. Code is available at https://github.com/ljwljwljwljw/kvpress/tree/echo-press.

This paper describes the approach of the UniBuc team in tackling the SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. We used SOLAR Instruct, without any fine-tuning, while focusing on input manipulation and tailored prompting. By customizing prompts for individual CTR sections, in both zero-shot and few-shots settings, we managed to achieve a consistency score of 0.72, ranking 14th in the leaderboard. Our thorough error analysis revealed that our model has a tendency to take shortcuts and rely on simple heuristics, especially when dealing with semantic-preserving changes.

Evaluating Retrieval-Augmented Generation (RAG) systems remains a challenge for Low-Resource Languages (LRLs), where standard reference-based metrics fall short. This paper investigates the viability of the "LLM-as-a-Judge" paradigm for Romanian by adapting the Ragas framework using next-generation models (Gemini 2.5 and Gemini 3). We introduce AdminRo-Eval, a curated dataset of Romanian administrative documents annotated by native speakers, to serve as a ground truth for benchmarking automated evaluators. We compare three evaluation methodologies - direct scoring, comparative ranking, and granular decomposition - across metrics for Faithfulness, Answer Relevance, and Context Relevance. Our findings reveal that evaluation strategies must be metric-specific: granular decomposition achieves the highest human alignment for Faithfulness (96% with Gemini 2.5 Pro), while comparative ranking outperforms in Answer Relevance (90%). Furthermore, we demonstrate that while lightweight models struggle with complex reasoning in LRLs, the Gemini 2.5 Pro architecture establishes a robust, transferable baseline for automated Romanian RAG evaluation.

Aerial grasp-and-lift tasks require whole-body coordination across approach, acquisition, and lifting under partial target observations. Early approach failures can limit exposure to later task stages during training, while changing visibility complicates alignment and closure timing during execution. We present a recurrent teacher-student framework that learns a single policy in simulation to jointly command flight, arm motion, and gripper closure without an explicit task-phase input. A privileged teacher learns through reinforcement learning with a critical-state curriculum that exposes acquisition and lifting states before connecting them to normal approach trajectories. Its behavior is distilled into a recurrent visual student that replaces privileged target states with dual-view point clouds and proprioception, integrating observation history for closed-loop control. A dedicated closure objective supervises closure timing from sustained model-defined readiness sequences. Training and primary evaluation use a simulated acquisition-and-payload model with condition-triggered latching, virtual attachment, and wrench-based payload loading for short-distance lifting. Across 8,996 completed simulation episodes under this model, the frozen student achieves full-task success rates of 99.97%, 97.14%, and 95.84% under nominal, physics/control-randomized, and additional camera-randomized conditions, respectively. The nominal latch-count-weighted mean of per-seed 90th-percentile alignment errors at acquisition is 8.12 mm.

A network can fit its training examples while failing to recover the rule that generated their labels. We examine this separation in single-hidden-layer multilayer perceptrons (MLPs), using synthetic tasks that control interaction order and the presence of nuisance inputs. We establish elementary benchmark properties: pure parity contains no predictive lower-order marginals, admits an exact Bayes posterior, and can be represented on clean latent inputs by a width-$k$ ReLU network. Experiments then identify distinct optimization outcomes. In a matched order-2--4 sweep, SGD, Adam, and Muon all reach 100\% peak test accuracy at order two; at order three they reach 96.25\%, 50.87\%, and 76.82\%, respectively, while Muon reaches 99.21\% at order four. In a separate mixed-order task, freezing only the first-layer weights connected to independent nuisance inputs raises AdamW's epoch-10 accuracy from 44.73\% to 95.07\%. Removing the same inputs only at test time raises it to 48.38\%. Thus, nuisance-weight learning changes the training outcome beyond its immediate effect on prediction. Bias interventions expose a connection between target symmetry and shallow ReLU representations. In a compact signal-only regime, both SGD and Muon learn orders five through eight, with higher SGD peak accuracy at orders nine through eleven. Together, the results show how optimization and nuisance learning constrain the higher-order rules realized by a shallow network.

Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or states in isolation. We show that such attacks leave a detectable signature in the agent's internal representations: harmful behavior emerges as an accumulated representation transition across context updates, whose triggering context can be identified from the same signal. We further find that naive aggregation is confounded by benign representation drift, as a contrastive safety direction need not assign zero to benign transitions. We address this by denoising the direction, anchoring benign traffic at zero and removing its leading variation directions, with no runtime cost. These findings motivate DART, a runtime framework that detects and attributes representation shifts and intervenes with targeted reminders. Across six models and two multi-turn benchmarks, DART reduces attack success from 84% to 25% on MT-AgentRisk, catching every attack at a mean false-alarm rate of 12%, and from 97% to 52% on ASEval, at costs in benign non-refusal of 8% and 0%, respectively. On MT-AgentRisk, it outperforms ToolShield, the state-of-the-art multi-turn defense, on all six models: under the same protocol, ToolShield reaches only 55%. Denoising is critical: on ASEval, the undenoised monitor catches only 7%-40% of attacks, while the denoised monitor catches 60%-85%. The same monitor covers single-turn indirect injection without modification and adds only 0.14-0.56 s overhead per monitored step without requiring an auxiliary model, making it a lightweight complement to computation-heavy speculative defenses.

This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory branch show a sharp separation of training and validation loss at epoch boundaries, resembling the shape of forks. We study this phenomenon in a controlled vanilla NanoGPT setting and reproduce it in a DeepSeek-style model with Engram. Mechanistically, repeated updates sharpen the continuations observed in training while suppressing the probability of unseen continuations, whose loss grows with each pass. The n-gram module creates weakly interacting context-specific subspaces, amplifying this effect. Low-frequency contexts contribute most of the gap, whereas larger training budgets and heavily crowded tables suppress it. We also observe forking in short-budget, heavily repeated SFT and RL-like regimes. The contributions of this paper are twofold: (1) Forking reveals yet another curious phenomenon in deep learning, in addition to grokking and double descent. (2) Forking is an unexpected and unpleasant by-product of tricks proposed by autoresearch agents. While these agents produce an enormous number of results that seem useful, we should always be careful with their results.

Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinical data is restricted due to privacy, ethical, or data availability limitations. Existing probabilistic and deep generative models often lack interpretability and fail to preserve clinically meaningful dependencies, limiting their suitability for safety-critical applications. This paper proposes a novel application of Fuzzy Cognitive Maps (FCMs) in a framework for synthetic medical tabular data generation with explicit causality and privacy preservation. Clinical features are described using linguistically interpretable fuzzy sets, and inter-feature dependencies are encoded as FCM edge weights computed from fuzzy set intersections. Synthetic patient records are generated by propagating randomly initialized linguistic activation vectors through the FCM until convergence, followed by defuzzification to produce clinically coherent numerical values. The approach natively handles mixed data types, and domain constraints common in health records. Experimental evaluation on UCI medical benchmark datasets demonstrates competitive performance under a Train-on-Synthetic-Test-on-Real (TSTR) protocol. The proposed method achieves accuracy of up to 0.81 and AUROC of up to 0.90 on the Heart Disease dataset, matching or exceeding TVAE and Gaussian Copula baselines while running exclusively on CPU. Fidelity metrics including KS Complement (up to 0.91) and Correlation Similarity (up to 0.95) confirm strong statistical coherence, and DCR Baseline Protection scores consistently exceed those of TVAE, confirming adequate privacy guarantees. These results demonstrate that causally grounded, interpretable fuzzy modeling offers a computationally efficient and transparent alternative to deep generative models for trustworthy synthetic data generation in CBMSs.

Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism. Pointwise scoring rubrics provide limited information about the relative quality of sample answers under the same prompt; merging multiple rubric judgments into a single score may also mask the differences between these answers. We propose MatrixReward, which constructs rewards from a rollout-by-rubric win-rate matrix obtained by comparing every pair of sampled responses under each rubric. The spread of each matrix column captures how strongly that rubric distinguishes the current rollouts, while correlations between columns reveal rubric repetition; together, these statistics yield data-dependent rubric weights. We combine these weights with the prior weights of rubrics. After column normalization and weighting, the observed per-rubric maxima and minima define positive and negative ideal profiles. Each rollout's distances to these two ideals determine its relative-closeness quality reward. Evaluated using Qwen3-8B on four open-ended query-answering benchmarks, MatrixReward achieves an average score of 63.02, outperforming the strongest baseline by approximately 2.0%. These results support the idea that matrices derived from relative comparisons can be used to construct rewards more reasonably for open-ended generative reinforcement learning.

Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, rewards in many interactive tasks reflect only the final outcome, providing limited guidance on which intermediate decisions advance the task. Successful training trajectories contain intermediate states that can provide supervision for subsequent interactions. We introduce Trajectory-to-Step Policy Optimization (T2SPO), a method that uses past interaction trajectories to provide step-level feedback for policy learning. T2SPO derives remaining-distance targets from successful trajectories and pairs them with representations of the states visited along the way. Conditioned on these examples, a pretrained TabPFN regressor estimates the remaining distance to success at each state of a new rollout. Changes in this distance estimate across consecutive states yield auxiliary credit for agent steps alongside task-level supervision. As training proceeds, newly completed trajectories refresh the estimator's context, incorporating new experience without updating its parameters. Experiments with 1.5B and 7B language models on ALFWorld and WebShop show that T2SPO consistently improves overall task success over GRPO.

Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response length, although cache-level correctness and downstream learner utility are distinct objectives. We formalize this selection-to-learning gap and introduce FAER as an auditable full-trajectory replay framework. Its training-free fixed selector is a protocol baseline; FAER-UTILITY is the learner-aware selector fitted on disjoint calibration blocks. The normalized gradient alignment is reported as a baseline, while a disposable optimizer-aware virtual update supplies a magnitude-aware utility surface. The audit contract freezes observed fields and replay traces before evaluation labels are joined. On GSM8K with Qwen2.5-1.5B-Instruct, the matched learner study reports quality 0.6329 for the fixed selector, compared with 0.5482 for uniform and 0.6037 for format-feedback under 128 updates. Metadata-only cross-fitted calibration reaches $0.6476\!\pm\!0.0139$ over eight seeds (median 0.6481; paired 95% interval $[+0.079,+0.122]$) at 63,276 target-run tokens; its recorded full cost is 189,642 tokens and 3.48 GPU-hours including calibration. The completed FAER-UTILITY row reaches 0.6624 at 62,844 target-run tokens and 4.26 GPU-hours. Format-feedback selects records with correctness 0.6953, compared with 0.3594 for the fixed selector, despite the different downstream ranking. The completed comparison surfaces report the learner-aware ablation, same-seed gap, policy-optimization rows, and strict zero-shot transfer.

The Natural Image Quality Evaluator (NIQE) scores an image by its statistical distance from a model fitted on pristine images, and its distributed model is fitted on photographs. We release the Radiology Image Quality Evaluator (RIQE), a NIQE-style model fitted on 3,792 full-dose slices from 158 patients of the public LDCT-and-Projection-data collection, with a declared intensity mapping, a manifest of every slice and a script that reproduces the fit. On 40 held-out patients, RIQE ranks reduced-dose reconstructions, simulated by projection-domain noise insertion, worse than the full-dose reconstruction of the same slice in 240 of 240 chest and 230 of 240 abdominal pairs, and ranks images with 20% more noise worse than their source in 97.5-100% of cases. Its preferences among filtered images, however, do not follow lesion signal. With a 4 mm, +10 HU lesion inserted in noisy abdominal slices, RIQE prefers bilateral filtering to the unfiltered image in every image up to a 32 HU residual, at which 29% of the lesion's matched-filter signal remains and its detectability index falls from 0.51 to 0.33; it never prefers Gaussian smoothing, which at the same 32 HU residual leaves 70% of the signal and a detectability index of 0.48. Fitted on photographs with the parameters published for NIQE, the same code ranks every simulated reduced-dose abdominal image better than its full-dose counterpart. RIQE is suited to ranking a degraded image against its source; under the conditions tested it should not be the sole criterion for selecting, comparing or tuning denoisers.

Model quantization reduces the numerical precision of neural network weights and activations to lower storage and computational costs. Model inversion attacks recover or reconstruct sensitive training data or inference inputs from model outputs or intermediate features, so quantization may also alter their effectiveness. However, two questions remain unresolved: How does model quantization affect model inversion? How do data characteristics influence this relationship? To address the first, we bound quantization-induced changes in mutual information between inputs and a categorical variable defined by prediction probabilities, distinguishing informational effects from attack optimization obstacles. To address the second, we identify data-dependent changes in feature distributions and inversion outcomes, with pronounced quantization sensitivity differences at 4 bits. These insights guide a privacy-aware post-training quantization method that improves inversion resistance while recovering utility. It uses a Fisher-type task-sensitivity proxy for budget-aware bit allocation, calibrates activation ranges, and jointly optimizes weight and activation scales and weight-rounding decisions with task-recovery and geometry-retention objectives and scale and rounding regularization. Experiments cover multiple metrics, neural network architectures, and face, palmprint, and iris recognition tasks. On ResNet-50, Palm at 4 bits reduces RL-MIA's strict success from 54% to 26%, while accuracy decreases from 99.01% to 96.55% relative to FP32. Our method also supports output-level defenses: adding Stealthy Shield Defense (SSD, epsilon = 0.1) to Iris at 4.5 bits reduces BREP-MI's strict success from 63.33% to 37.33%, while accuracy decreases from 92.8% to 87.6% relative to quantization alone.

Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Yet recovery is usually judged only by average task success. This hides an important tension. The same operation can rescue a failing trajectory or disrupt one that would otherwise succeed. We frame recovery as a causal decision problem. Starting from the same execution state, we compare what happens with and without recovery, separate rescue from harm, and study how the value of recovery changes over time. We then introduce the Causal Intervention Router (CIR), a lightweight policy that uses information available before recovery to decide when intervention is worthwhile. On long-horizon ALFWorld tasks with Qwen3-14B, CIR raises success from 70.33% to 73.33%, a gain of 3.00 percentage points. It leaves all evaluated trajectories with correct observations untouched. Additional controls show that the benefit of recovery cannot be explained solely by the new observation returned by the environment. These results provide a practical way to evaluate recovery and apply it selectively.

Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the purpose of collaboration. We introduce authorization-paired evaluation, which makes blocking prohibited uses and completing required authorized uses a joint success criterion, and FlowReview, a framework connecting object resolution, permission ranking, and deterministic enforcement. In controlled composition experiments, reviewing combined artifacts reduces the denied-commit rate from 86.0% to zero with no loss of authorized supply. Our findings show that preserving information and lineage alone does not ensure correct permission attribution. Object identity and permission must remain connected to execution through components whose outputs can be verified. Together, these findings establish a system-level requirement for multi-agent safety: govern composed information flows while preserving the authorized capabilities that make collaboration useful.

Station weather forecasting is fundamentally shaped by both complex spatial dependencies across stations and strong physical coupling among weather variables. However, existing studies often consider these relationships separately and use different datasets and experimental settings, hindering systematic assessment of their individual and joint contributions. In this paper, we introduce $M^2$Weather, a benchmark for joint multi-station and multi-variable weather forecasting. Through multi-criteria quality control and station stratification, we collect 2,809 high-quality stations with 5 physically coupled weather variables across three spatial scales: France, Europe, and Global. This multi-scale design lets us examine whether conclusions persist from national to global station networks. We also introduce unified training and evaluation protocols to enable fair comparison of different station-variable modeling paradigms. To further examine the benefits of modeling station-variable relationships, we design a lightweight, plug-and-play adapter. With a trained weather forecasting model, this adapter can introduce missing station or variable relationships without retraining the model. This enables fair and efficient investigation of station-variable relationships. Systematic evaluation of 16 representative models shows the benefits of jointly modeling station and variable relationships. Completing missing relationships further reduces MSE for all adapted models on all three datasets. Together, these results identify the complementary information across stations and variables as an important resource for improving station weather forecasting. Our code can be obtained at https://github.com/hnu-vis/M2-Weather.

World-model planners typically scale outward by rolling farther, sampling more trajectories, or optimizing longer, while assigning the same computation to every imagined transition. We show that making every transition uniformly deeper wastes computation and can degrade planning because useful refinement is concentrated at a small set of decision-critical events. We introduce DeepJEPA, a weight-tied joint-embedding predictive world model that treats transition depth as an inner test-time scaling axis and learns when another recurrent update is worth computing for each candidate and rollout step. Across five visual-control settings, DeepJEPA improves or matches the strongest fixed-depth planner while averaging only 1.00-1.26 updates per transition. Its additional computation concentrates at contact onset and sustained object interaction, where latent corrections can change which candidates enter the planner's elite set and which action is selected. Representation probes further show that improved planning does not require uniformly better object-state decodability. DeepJEPA therefore reframes world-model scaling as a problem of allocating internal computation where it can change the planner's decision: think deeper at decision-critical transitions instead of making every rollout uniformly deeper or longer.

Mixture-of-Experts (MoE) models enable parameter scaling with limited per-token computation by activating only a small subset of experts for each token, but deploying them still requires loading the complete expert pool into memory. Structured expert pruning can effectively reduce the memory usage by removing experts. However, existing pruning methods either use expert ranking criteria that are not well aligned with model performance or rely on effective expert subset searching that is computationally expensive. Moreover, these methods typically overlook the routing-behavior redundancy among the retained experts. In this paper, we propose MoE Pruning via Router Bias Learning and Expert Approximation (MoRA), a framework for structured MoE expert pruning. We introduce a learnable router bias for each expert and optimize these biases by minimizing the language-modeling loss and a routing-diversity regularizer. The learned router biases sharpen the routing probability distributions to identify experts critical to model performance while encouraging the selection of experts with diverse routing preferences. In addition, we introduce an expert approximation mechanism as a post-pruning enhancement. It leverages the remaining experts to approximate the outputs of pruned experts by affine transformation, further improving the performance of the pruned model. We evaluate MoRA on Qwen3-30B-A3B, DeepSeek-V2-Lite, and Moonlight-16B-A3B, removing 25\% and 50\% of the routed experts in each MoE layer. Extensive experiments on nine zero-shot benchmarks show that MoRA outperforms state-of-the-art pruning algorithms. Our code will be released.

A persistent agent must decide both what to retain as information arrives and what to surface once a query appears, yet memory evaluations can confound these decisions by comparing methods that differ in both retention and selection. We build a streaming-recall benchmark crossing retention and selection rules and evaluate every condition on the same 300 seeded episodes. Holding access fixed, query-aware selection improves required-fact recall by 15.5 percentage points (95% CI: 12.8 to 18.2), whereas a mixed comparison that also changes history access reports a 68.7-point advantage, of which 53.2 points are attributable to access. Under bounded retention, query-aware, dense, and oracle selection reach the retention ceiling, and all 319 observed failures in the bounded recency condition are caused by eviction rather than ranking errors. Recall falls to 0% as targets recede sufficiently far into the past. Repeating the evaluation on SQuAD preserves the retention ceiling while showing that dense retrieval can outperform lexical retrieval on natural text. These results show that bounded-memory evaluations should hold access fixed and report retention and selection separately.

Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise that serves the first goal can interfere with the second. In trajectory-guided settings such as ViViDex, where RL refine hand-object trajectories from human video, our baseline PPO runs end near their initial action noise after 5M steps, motivating explicit control of exploration scale. DexPolicy makes that scale an explicit function of training steps, annealing from broad to narrow exploration while holding loss, architecture, reward, and optimizer settings fixed. We study three policy-optimization settings: PPO, critic-free GRPO continuation, and a flow-parameterized PPO variant (FPO). Across five YCB objects and three training seeds, mean deterministic Target success rises from 49.4% to 68.1% (FPO), 14.1% to 45.4% (GRPO), and 32.0% to 35.7% (PPO). On a RealMan RM75 arm with an Inspire/RH56 hand, 360 trials over three objects raise mean Target success from 25.0% to 85.0% (FPO), 10.0% to 63.3% (GRPO), and 8.3% to 43.3% (PPO), with one trained model per object-method condition. PPO component screening favors noise control over the tested optimizer contraction; the selected PPO schedule yields higher mean Target success than linear decay with the same endpoints on three tested objects. Training return, deterministic Target success, and tolerance to execution noise dissociate; schedules should therefore be judged by terminal task success under the intended execution conditions, per task and policy-optimization setting. Code: https://github.com/AIGeeksGroup/DexPolicy. Website: https://aigeeksgroup.github.io/DexPolicy.

Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and memory constraints. Existing point-based and voxel-based methods often incur substantial computational overhead, whereas conventional bird's-eye-view (BEV) representations improve efficiency at the cost of discarding vertical geometric information. We present IndoorBEV, a lightweight LiDAR perception framework that mitigates this tradeoff through a height-aware BEV representation and geometry-conditioned feature fusion. IndoorBEV summarizes the vertical point distribution in each BEV cell using statistical height features and multi-frequency height encoding, allowing informative three-dimensional cues to be processed efficiently by two-dimensional convolutions. A lightweight encoder then integrates complementary geometric features with multi-scale local representations and compact global scene context. Decoupled dense prediction heads jointly produce semantic BEV maps and oriented object bounding boxes. IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage. On an NVIDIA AGX Orin, it uses 21.52 MB of GPU memory per inference and achieves a mean latency of 169.6 ms under a 200 ms perception deadline, with a deadline miss ratio of 1.8\%. Evaluations on simulated scenes, real-world robot scans, and an open-source indoor point-cloud dataset demonstrate a favorable tradeoff among perception accuracy, latency, and memory consumption. These results indicate that explicitly encoding vertical geometry within a compact BEV representation provides an effective approach to resource-efficient indoor LiDAR perception.

AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of defense is a pre-signing check: a static allowlist, an LLM reviewer, or a transaction simulation. All three share a gap: the check describes the chain state at check time, but the transaction executes in a later state that an adversary can shape through front-running, contract upgrades or token-parameter changes. We call this state drift. We present Proof-Gated Signing (PGS), which simulates a proposed transaction, extracts its effects, and uses an SMT solver to check a declarative value-and-permission policy for every price in an oracle-uncertainty band. It then compiles on-chain post-conditions (wallet balance bounds, payee receipts, allowance caps and ownership) and proves that every execution satisfying them also satisfies the policy. The agent's smart-contract wallet enforces them atomically, so the guarantee applies to the executed transaction under arbitrary drift. On an open testbed of 260 scenarios (14 attack families including five drift and two adaptive families, and 12 benign families), with harm measured from attacker balances rather than from any policy, PGS prevented 93.6% of the 140 harmful scenarios and passed 97.5% of the benign ones. Simulation-only checking prevented 57.9% and a static allowlist 71.4%. None of the 50 drift scenarios produced attacker gain under PGS. The only unprevented family, an in-policy drain, was bounded by the per-session budget. We also find that giving an LLM reviewer a clean pre-drift simulation made it more likely to approve a drift attack. Overhead is about 41k gas and 0.1-0.2 s per check.

A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the balance stays unverified. We formalize legal judgment as a reference-anchored task, whose object is a single decision that stays tied to the statute and to the circumstances at once. We introduce JusticeAxis, 256 real-world criminal cases from 18 countries with audio, image, and text evidence, and three lawyer-written judgments for every case: the recorded one and one for each failure. We further propose JusticeAgent, a harness whose element agents establish the facts and whose judge agent applies the law under skills carrying experience of the circumstances. Skills are distilled from execution trajectories and admitted only under Bayesian credible bounds. Experiments show that failure turns direction with scale: open-weight backbones drift to unsupported grounds, frontier models to the statutory default. We further verify that JusticeAgent, as a simple yet effective plugin, carries a frozen open-weight backbone to commercial level. Project resources are available at https://github.com/beita6969/JusticeAxis.

Spiking Neural Networks (SNNs) offer an energy-efficient approach to processing event-camera data, yet out-of-distribution (OOD) detection remains challenging in this setting. Existing OOD detection methods often depend on model outputs or computational components that are unavailable in object detection SNNs or are poorly suited to low-compute deployment. To that effect, we show that the subthreshold membrane potential \(V_{\mathrm{mem}}(t)\) provides a useful internal signal for detecting distribution shifts. Simple per-channel statistics derived from these membrane dynamics enable OOD detection. To evaluate this approach, we introduce Gen1-C, an event-camera corruption benchmark developed upon the Prophesee Gen1 automotive detection dataset, containing six sensor-motivated histogram-level stress tests at five severity levels. We further propose the Multi-Descriptor Deviation (MDD), a corruption-blind method that operates on membrane-potential statistics. At the highest corruption severity, MDD achieves an AUROC of more than 0.88 on five of the six corruptions using only a bounded 64-frame observation window. Notably, the remaining corruption is also the one that has the smallest effect on the underlying detector. These results show that the temporal membrane-potential dynamics can provide an effective and low-cost signal for OOD detection in SNN-based event perception.

Language models increasingly make real-time decisions in applications that apply the latest answer until a newer one arrives. A late answer can prolong an outdated decision, such as a call recorder still running while a customer reads out card details, an error offline accuracy misses. We make three contributions. First, we release StreamDecisionBench (SDB), a dataset of eight streaming scenarios in four application families, with executable reference decisions derived from public rules. Second, we propose an evaluation protocol and a metric, in-force accuracy: the share of time the applied decision is correct across update intervals of 0.5-8 s. It reflects accuracy and latency jointly, attributing each error to judgment, latency or both. Third, we evaluate thirteen single-model settings, and this attribution separates speed-limited from judgment-limited models: slower, more accurate models lose 42-51% of the time to outdated answers, a fast model 34% to wrong ones. We therefore test hybrids in which a slow model corrects a fast one; with the right pairing and configuration, a hybrid outperforms every single model. However, even the best evaluated system keeps a correct decision in force only about two-thirds of the time, leaving a substantial gap for real-time use.

Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child allocation constraints, affine objects, and distributed escrow do not by themselves prevent overspend when replies are lost, effects complete after timeout, messages repeat, branches partition, or DAG joins alias one lineage. We formalize fault-tolerant budget conservation for distributed multi-agent delegation. Budgets are quantized resource vectors represented by exclusive escrow credits that move through a delegation DAG. Before dispatch, a branch converts credit into an operation reservation bound to lineage, epoch, normalized effect, maximum charge, receiver, and idempotency key. It persists a signed dispatch permit with quarantine; the gateway verifies that permit before first acceptance. Uncertain effects remain charged until authenticated settlement, a fenced authoritative no-effect proof, or permanent retirement. We prove ownership partition, ledger and effect conservation, descendant non-amplification, at-most-once settlement, late-completion safety, and partition confinement under explicit mediation, durability, authentication, normalization, and gateway assumptions. An indistinguishability result shows that partition-local availability requires exclusive preallocation. Bounded TLA+ checking, an independent JavaScript explorer, and crash-injected two-process SQLite experiments exercise the declared scope and detect timeout-refund and historical-certificate-validation mutants. The mechanism preserves the issued budget bound across the evaluated crash, retry, duplicate, partition, join, and late-completion schedules.

Self-modifying AI agents can replace, fork, and roll back identity-bearing software while descendants remain executable. Per-successor authorization does not constrain the resulting population: siblings may duplicate quotas, combine permissions, survive ancestor cuts, or overlap predecessors during promotion. We define authorization succession, which conserves authority across the active frontier of a single-parent generation forest. Our external protocol binds each generation to a manifest, root, unique parent, complete lineage, and fresh population sequence. Separate invariants bound root-lifetime consumption and current population exposure. A staged reservation freezes predecessor residual authority during replacement, while a partitioning fork validates the complete child family. Each commit atomically fences the predecessor and activates successors. Ancestor cuts invalidate dependent descendants; rollback creates a fresh generation without restoring spent authority; and a new root requires an independent grant. Under complete mediation, authenticated records, sound effect abstraction, durable monotone state, and complete lineage accounting, we prove population-safe succession, fork conservation, revocation closure, atomic handoff, rollback non-reminting, and exclusion of self-certification. An executable evaluation covers 32 registered decisions through direct-call and mailbox mappings (64/64 replays; 28 allows, 36 denies). An independent checker accepts all 64 original traces and rejects 28/28 semantic mutants; 12/12 profile invariants, 16/16 crash cuts, and 32/32 contender schedules pass. Two external adapters reproduce all 32 decisions around measured OurArk and Darwin Godel Machine mutations, including fresh-process restart, atomic succession, and predecessor rejection. The results establish authorization succession for registered protected effects.

Software that hands branching decisions to a model needs a declared option and a probability it can threshold. Typed decision models, also called System One models, return such probabilities without generating text, while supervised classifiers and generative language models are the established alternatives. Under matched conditions, one harness sends eight decision-model checkpoints from six families, including the hosted model Jev, and two generative comparators the same semantic requests, and scores supervised and zero-shot classifiers on the same workflow, intent and social-science items. The ranking of the model classes depends on the conditions. With the task's own labels, small trained classifiers are the most accurate on intents and not significantly different from the best decision models on workflows. Without labels, every decision model except the encoder-based checkpoints exceeds a zero-shot entailment classifier on workflows and intents. Read through option-key likelihoods, a larger generative model is level with Jev on workflows and intents and accepts more workflow decisions at five percent risk, and fine-tuned decision checkpoints gain intent accuracy over their untuned backbones. Stored temperatures fitted on few options raise calibration error with many options, and a held-out threshold for five percent in-scope risk still lets Jev accept 0.310 of out-of-scope requests. Swapping yes and no flips 50.5 answers per hundred for Jev, while fine-tuned checkpoints cut their backbones' social-science flips. An intent-trained first stage escalating to Jev matches its accuracy at 0.43 of its cost at full graphics-processor utilization. The results yield condition-dependent design rules for automated decision gates.

As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generation tasks becomes a critical challenge. Unlike unimodal threats, synergistic risks emerge when text and image modalities are coordinated to produce harm that significantly exceeds their individual components. We introduce UnifiedAttack, a novel benchmark designed to evaluate LMM safety in collaborative scenarios by focusing on the harmfulness gain achieved through cross-modal synergy. The benchmark incorporates samples filtered for their multimodal potential alongside a novel subset of synthesized disinformation queries. To verify identified vulnerabilities, we propose a synergistic hijacking framework featuring In-Context Reskinning (ICR) and Cognitive Planning Injection (CPI). ICR utilizes few-shot learning to wrap adversarial intent in benign virtual shells to desensitize safety filters, while CPI hijacks the reasoning path by enforcing a plan-then-execute paradigm. By compelling the system to commit to a neutral logical plan, we exploit its internal drive for consistency to induce the synchronized generation of harmful multimodal content. Extensive evaluations on state-of-the-art architectures demonstrate that UnifiedAttack consistently bypasses modern alignment. Our findings reveal that the structural helpfulness and logical coherence of unified models can be systematically weaponized, highlighting the urgent need for logic-aware defenses in synergistic generation tasks. Code is available at https://github.com/bingjunluo/UnifiedAttack .

Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate retrospective open-vocabulary memory as probabilistic inference from censored observations, where the key idea is to reason with evidence per opportunity: a detection or non-detection should influence belief only in proportion to the robot's opportunity to observe the corresponding location. We introduce ECROM, which uses this principle to estimate long-term prevalence for concepts specified only at query time and converts the resulting belief directly into an active-search prior. To evaluate this problem, we introduce a controlled long-term benchmark in ten HM3D homes that independently varies object placement and observation opportunity across repeated traversals. ECROM improves support-level AP on held-out queries by 4.5 points and search SPL by 4.2 points over the strongest competing memory in each metric. The benchmark, dataset, and code will be open-sourced.

Selective state space models (SSMs), such as Mamba, S4D, and LRU, are bounded by transition matrix commutativity (A_t A_t' = A_t' A_t) and solvable affine transformation groups (Aff_D of derived length <= 2). Consequently, stacked multi-layer diagonal networks face severe optimization degradation on non-solvable simple groups such as A_5 due to the exponential circuit emulation depth required to simulate non-abelian commutators. We propose Non-Commutative State Space Models (NC-SSM), their real-orthogonal counterpart SO(3)-SSM, and arbitrary-dimension Cayley-SSM, lifting state transitions to compact Lie groups SU(2), SO(3), and SO(N). Via closed-form Euler-Rodrigues maps and rational Cayley transforms, NC-SSM achieves exact norm-preserving isometry (||U_t|| = 1). We introduce pure Hopf-fibration Bloch projective readouts (S^3/{+-1} =~ S^2 =~ SO(3)) to eliminate sign ambiguity, true quaternion parallel prefix scans (9.06x speedup at T=2048), and Identity-Gated Lie SSMs to eliminate sparse syntax phase drift. Extensive benchmarks across 14 experimental regimes show: (1) NC-SSM achieves 100% tracking on S_3, D_4, Q_8 and simple group A_5, where a 3-layer deep diagonal baseline collapses to 6.60% (p = 8.81e-4); (2) Cayley-SO(5)-SSM breaks Klein's 1884 ceiling on symmetric group S_5 (50.92% vs diagonal 5.25%, p = 0.0015, delivering 7.8x variance reduction over SO(3)); (3) SO(3)-SSM preserves Riemannian manifolds across 300 steps (< 3.12e-6 drift, > 580,000x advantage), achieving 0.04 deg dead-reckoning error and active tangent denoising; (4) NC-SSM achieves 74.36% on Dyck-2 and 30.26% on deep AST scope tracking (p = 0.0081); and (5) ablation confirms strict isometry is mathematically necessary for lossless long-range associative memory.

Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control. While chunk-level training is convenient across robot embodiments, it optimizes local action likelihood without explicitly accounting for long-horizon task success. Sequence-level reinforcement learning can address this limitation, but typically requires policy rollouts and closed-loop interaction, which are costly for real-robot manipulation. We introduce DriftOPD, a teacher-free, rollout-free framework for sequence-level on-policy distillation of continuous VLA action experts. We show that the sequence-level reverse Kullback-Leibler (KL) divergence decomposes into a chunk-level reverse-KL term and a future-potential term that captures the long-horizon effect of the current action. DriftOPD optimizes these two terms using a one-step drifting objective and a Q-function critic learned from offline demonstrations, respectively, enabling sequence-level optimization with only offline data and one-step action generation. Across multiple VLA architectures in simulation and real-world manipulation, DriftOPD generally outperforms existing one-step distillation baselines while achieving task success performance comparable to multi-step teacher policies. These results demonstrate that long-horizon behavior can be effectively distilled into one-step VLA action experts without online interaction or a separate teacher.

Voice agents enable low-latency, natural interaction, yet their ability to faithfully ground responses in external documents remains underexplored. We introduce DuplexSpeechBench-Document Grounding (DSB-DG), a benchmark for evaluating document grounding in voice agents across five professional domains. DSB-DG targets three failure modes: Context Saturation, which measures grounding under increasing document length; Grounding Decay, which measures retention of document facts across multi-turn dialogue; and Proactive Grounding, which evaluates whether context re-injection mitigates conversational drift. The benchmark contains 1,636 adversarially verified QA pairs from 50 documents covering five professional domains, and supports fully automatic evaluation of grounding accuracy, hallucination, and response latency. Across systems spanning cascaded, proprietary full-duplex and real-time, and open-weight speech2speech architectures, we find substantial differences in effective grounding capacity. While cascaded pipeline (ASR-LLM-TTS) achieves the highest grounding accuracy, Gemini-Live and GPT-Realtime closely trail behind. Open-weight systems exhibit distinct failure modes, most notably an abrupt context-capacity collapse and multi-turn grounding decay. More broadly, grounding fidelity degrades with context and conversational load, and failures frequently manifest as unsupported generations rather than abstention. We show that contextual grounding as a key unresolved challenge for reliable full-duplex voice agents.

Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while varying description, matched explanation, and donor context. Five checks track commitment, delivery, predictive gain, alignment, and known-signal uptake. Across 336 prospective states in controlled learning, 12 Tox21 endpoints, and 24 OpenML tasks, v5's frozen credit decision was inconclusive. Tox21's preregistered ROC AUC interval-score harm test was unmet ($D-M=-.0026$, 95 percent interval [$-.0174$, .0104]); OpenML's joint formation, point-equivalence, and repeatability rule was unmet. Matched point-accuracy gains over description remained unconfirmed, and Tox21/OpenML seed-donor intervals spanned zero. Under requested DeepSeek V4 Pro, matched and donor cards reduced secondary Tox21 drift by 64.5 and 59.1 percent. A DeepSeek V4 Flash replay raised matched point MAE from .01823 to .02020 and missed matched-donor interval-score equivalence. OpenML full-card assignment widened nominal 80 percent intervals by 21 percent, with 49.3 percent coverage versus 51.4 percent for description and content in 66/144 cards. Direct-text Flash delivered all 144 notes without detectable matched point-accuracy gain. A researcher-authored mechanism positive control lowered point MAE by 2.60 percentage points versus description. The protocol measures predictive credit for research-agent benchmarks and scientific forecasting; natural-explanation credit remained unconfirmed at the tested donor resolutions.

Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to Tools (R2T) supplies prepared executable checks of public scientific requirements. Matched SciCode repair groups share written checks, starting programs, model, and budgets; the tool group receives a callable implementation. Across two task-ID cohorts, complete repair is 26/30 with text and 29/30 with the prepared checks. Three task IDs favor tools, one favors text, and eleven tie. The eight-ID cohort scores 13/16 versus 15/16, with a task-cluster bootstrap 95% interval of [-12.5, 43.75] percentage points for the difference. The larger shared-definition SciCode cohort ties at 13/24 per group. Five development-exposed tasks with alternate starting programs score 3/10 versus 7/10. The tool group favors tasks 17, 77, and 11; initial checks flag task 17 and report no violation for tasks 77 and 11. Task 37 favors text and has no initial reported violation. A fresh source-through-Python arm also reaches 15/16, matching the dedicated command's aggregate. In a matched PDE comparison, detailed text scores 23/24 and checks score 24/24, with 31.2% lower reported model output for checks. Agent-side output savings vary by cohort, while public CPU use rises in both task-ID cohorts. These results measure task-dependent repair outcomes and agent-side costs with prepared checks.

Crowdsourced imagery provides timely, fine-grained, street-level observations for disaster mapping, complementing conventional remote sensing imagery (RSI) during emergency response. However, such imagery is often unstructured, spatially ambiguous, and lacks reliable geographic metadata, making manual geolocalization and interpretation labor-intensive and difficult to scale. This work proposes a multi-task Geospatial Reasoning Disaster mapping framework, namely GRDisaster, to examine the potential of vision-language models (VLMs) in understanding, geolocalizing, and reasoning over crowdsourced disaster imagery. GRDisaster is built on a newly curated benchmark dataset derived from PhotoMappers, comprising 26,340 images organized into human-validated volunteered geographic information (VGI), street-view imagery (SVI), RSI cross-view triplets covering multiple disaster events from 2018 to 2024. The framework combines deterministic and probabilistic cross-view geolocalization with multi-view fusion to associate VGI images with georeferenced SVI and RSI. It introduces two sets of spatial reasoning indicators for cross-view geolocalization validation and disaster damage assessment. These indicators use structural, environmental, and global-scene cues to validate cross-view correspondences and visually observable damage evidence with expert-verified annotations to assess disaster severity, improving the interpretability of VLM outputs. To our knowledge, this study provides the first systematic investigation and unified evaluation framework for examining how VLM-based spatial reasoning can transform crowdsourced disaster imagery into actionable geospatial artificial intelligence (GeoAI) through cross-view geolocalization validation, interpretable spatial reasoning, and damage-aware severity assessment.