Physical AI Brief

We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multiproduct retail demand. The model learns log-demand as a smooth, context-conditioned function of log-prices, allowing elasticities to be derived exactly from the learned demand surface. On the Dominick's beer dataset, ICDN improves out-of-sample generalization over a directed log-log benchmark and yields more stable, economically plausible elasticity estimates, especially for weakly identified cross-price effects.

Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is largely absent from multimodal LLMs (MLLMs) for video understanding, which process frames as isolated 2D snapshots, instead of the persistent scene humans perceive. We revisit pose as a lightweight supervisory signal and introduce Cambrian-P, a video MLLM augmented with per-frame learnable camera tokens and a pose regression head. With a carefully designed sampling scheme, the model achieves substantial gains of 4.5-6.5% on spatial reasoning benchmarks such as VSI-Bench, generalizes across eight additional spatial and general video QA benchmarks, and, as a byproduct, achieves state of the art streaming pose estimation on ScanNet. Surprisingly, training on pseudo-annotated poses from in-the-wild video further improves general video QA benchmarks, showing pose helps beyond spatial reasoning. Together, these results position camera pose as a fundamental signal for video models that reason about the physical world.

Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by missing secondary causal consequences. To address this, we introduce MotiMotion, a novel framework that reformulates motion control as a reasoning-then-generation problem. To encourage causally grounded and commonsense-consistent interactions, we leverage a training-free vision-language reasoner to refine image-space coordinates of primary trajectories and to hallucinate plausible secondary motions. To further improve motion naturalness, we propose a confidence-aware control scheme that modulates guidance strength, enabling the model to closely follow high-confidence plans while correcting artifacts under low-confidence inputs with its internal generative priors. To support systematic evaluation, we curate a new image-to-video benchmark, MotiBench, consisting of interaction-centric scenes where new events are triggered by motion. Both VLM-based evaluation and a human study on MotiBench demonstrate that MotiMotion produces videos with more plausible object behaviors and interaction, and is preferred over existing approaches.

Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the standard paradigm of LLM post-training optimizes a pre-specified scalar reward, often leading current LLMs to produce low-entropy response distributions and thus to struggle at displaying the diversity that inference-time search will require. We propose Vector Policy Optimization (VPO), an RL algorithm that explicitly trains policies to anticipate diverse downstream reward functions and to produce diverse solutions. VPO exploits that rewards are often vector-valued in practice, like per-test-case correctness in code generation or, say, multiple different user personas or reward models. VPO is essentially a drop-in replacement for the GRPO advantage estimator, but it trains the LLM to output a set of solutions where individual solutions specialize to different trade-offs in the vector reward space. Across four tasks, VPO matches or beats the strongest scalar RL baselines on test-time search (e.g. pass@k and best@k), with the gap widening as the search budget grows. For evolutionary search, VPO models unlock problems that GRPO models cannot solve at all. As test-time search becomes more standardized, optimizing for diversity may need to become the default post-training objective.

Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for end-to-end action prediction, they often lack an explicit and explainable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly building a scene map for heuristic planning is intuitively appealing but relies on additional 3D sensors and hinders large-scale vision-language pre-training. To bridge this gap, we propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism, enabling it to understand the agent's state and task progress in a fully end-to-end and data-driven manner. Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training. Extensive experiments on various datasets in Habitat simulator show our AwareVLN significantly outperforms previous state-of-the-art vision-language navigation methods. Project page: https://gwxuan.github.io/AwareVLN/.

Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived from the mismatch between the agent's predictive model of the world and reality. However, translating this intrinsic motivation to complex, photorealistic environments remains difficult, as agents can become trapped in local loops and receive fresh rewards for revisiting forgotten states. In this work, we demonstrate that this failure stems from a lack of spatial persistence and episodic context. We show that effective curiosity requires a model of the world that is persistent and continuously updated, paired with an agent that maintains an episodic trajectory history to navigate toward novel regions. We achieve this using an online 3D reconstruction as a persistent model of the world, while the agent policy is parameterized as a sequence model over RGB observations to maintain episodic context. This design enables effective exploration during training while allowing the agent to navigate using solely RGB frames at deployment. Trained purely via curiosity on HM3D, our agent outperforms RL-based active mapping baselines and generalizes zero-shot to Gibson and AI-generated worlds. Our end-to-end policy enables efficient adaptation to downstream tasks, such as apple picking and image-goal navigation, outperforming from-scratch baselines. Please see video results at https://recuriosity.github.io/.

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action. However, existing VLA systems primarily rely on textual instructions and struggle to resolve spatial ambiguity in complex scenes with multiple similar objects. To address this limitation, we introduce gesture as a parallel instruction modality and propose a Gesture-aware Vision-Language-Action model (GesVLA). Our approach encodes gesture features directly into the latent space, enabling them to participate in both high-level reasoning and low-level action generation, and adopts a dual-VLM architecture to achieve tight coupling between gesture representations and action policies. At the data level, we construct a scalable gesture data generation pipeline by rendering hand models onto real-world scene images. This reduces the sim-to-real visual gap while producing rich data with diverse motion patterns and corresponding pointing annotations. In addition, we employ a two-stage training strategy to equip the model with both gesture perception and action prediction capabilities. We evaluate our approach on multiple real-world robotic tasks, including a controlled block manipulation task for validation and more practical scenarios such as product and produce selection. Experimental results show that incorporating gesture consistently improves target grounding accuracy and human-robot interaction efficiency, especially in complex and cluttered environments. Project page: https://gwxuan.github.io/GesVLA/.

Robustness, domain adaptation, photometric and occlusion invariance, compositional generalisation, temporal robustness, alignment safety, and classical anisotropic regularisation are usually treated as separate problems with separate method families. This paper argues that much of their shared structure is one statistical problem: estimate the covariance of label-preserving deployment nuisance, then regularise the encoder Jacobian along a matrix whose range covers that covariance (the matching principle). CORAL, adversarial training, IRM, augmentation, metric learning, Jacobian penalties, and alignment-style constraints are different estimators of that object, not independent robustness tricks. In the linear-Gaussian model we prove closed-form optimality (Theorem A), including cube-root water-filling within the matched range; necessity of range coverage for quadratic Jacobian penalties (Theorem G); the same range dichotomy at deep global minima; and two falsification controls (Lemma C; Corollaries E), with seven conditional consistency lemmas (D1-D7) for estimation under standard identifiability assumptions. We introduce the Trajectory Deviation Index (TDI), a label-free probe of embedding sensitivity when task accuracy or Jacobian Frobenius norm is insufficient. Thirteen pre-registered blocks from classical ML through Qwen2.5-7B test the predicted matched, then isotropic, then wrong-W ordering on geometry and deployment drift; twelve pass, and the sole exception (Office-31) is an eigengap failure named before the run. At 7B scale, matched style-PMH improves selective honesty and preserves Style TDI where standard DPO degrades it. The contribution is naming the deployment nuisance covariance, stating what the regulariser must do, and supplying a closed-form falsifiable theory once that object is identified, not universality on every leaderboard.

Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine evolution to text-mutable artifacts -- skill files, prompt configurations, memory schemas, workflow graphs -- and leave the agent harness untouched. Since routing, hook ordering, state invariants, and dispatch live in code rather than in any text artifact, an entire class of structural failure is physically unreachable from the text layer. We argue that source-level adaptation is a fundamentally more general medium: it is Turing-complete, a strict superset of every text-mutable scope, takes effect deterministically rather than through base-model compliance, and does not erode under long-context drift. We present MOSS, a system that performs self-rewriting at the source level on production agentic substrates. Each evolution is anchored to an automatically curated batch of production-failure evidence and proceeds through a deterministic multi-stage pipeline; code modification is delegated to a pluggable external coding-agent CLI while MOSS retains stage ordering and verdicts. Candidates are verified by replaying the batch against the candidate image in ephemeral trial workers, then promoted via user-consent-gated, in-place container swap with health-probe-gated rollback. On OpenClaw, MOSS lifts a four-task mean grader score from 0.25 to 0.61 in a single cycle without human intervention.

Linear attention replaces the unbounded cache of softmax attention with a fixed-size recurrent state, reducing sequence mixing to linear time and decoding to constant memory. The hard part is not just what to forget, but how to edit this compressed memory without scrambling existing associations. Delta-rule models subtract the current read before writing a new value, and Kimi Delta Attention (KDA) sharpens forgetting with channel-wise decay. But the active edit still uses a single scalar gate to control two different things: how much old content to erase on the key side and how much new content to commit on the value side. We introduce Gated DeltaNet-2, which generalizes both Gated DeltaNet and KDA by inheriting adaptive forgetting and channel-wise decay while addressing their shared limitation, the scalar tie between erasing and writing. Gated Delta Rule-2 separates these roles with a channel-wise erase gate b_t and a channel-wise write gate w_t, reducing to KDA when both gates collapse to the same scalar and to Gated DeltaNet when the decay also collapses. We derive a fast-weight update view, a chunkwise WY algorithm with channel-wise decay absorbed into asymmetric erase factors, and a gate-aware backward pass that preserves efficient parallel training. At 1.3B parameters trained on 100B FineWeb-Edu tokens, Gated DeltaNet-2 achieves the strongest overall results among Mamba-2, Gated DeltaNet, KDA, and Mamba-3 variants across language modeling, commonsense reasoning, and retrieval. Its advantage is most pronounced on long-context RULER needle-in-a-haystack benchmarks, where it improves the evaluated multi-key retrieval setting and remains strong in both recurrent and hybrid settings. Code is available at https://github.com/NVlabs/GatedDeltaNet-2.

Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-value (KV) caches, can improve efficiency and preserve richer task-relevant information. However, KV caches also encode contextual inputs, intermediate reasoning states, and agent-specific information, creating an opaque channel through which sensitive content may propagate across agents without explicit textual disclosure. To address this, we introduce \textbf{LCGuard} (Latent Communication Guard), a framework for safe KV-based latent communication in multi-agent LLM systems. LCGuard treats shared KV caches as latent working memory and learns representation-level transformations before cache artifacts are transmitted across agents. We formalize representation-level sensitive information leakage operationally through reconstruction: a shared cache artifact is unsafe if an adversarial decoder can recover agent-specific sensitive inputs from it. This leads to an adversarial training formulation in which the adversary learns to reconstruct sensitive inputs, while LCGuard learns transformations that preserve task-relevant semantics and reduce reconstructable information. Empirical evaluations across multiple model families and multi-agent benchmarks show that LCGuard consistently reduces reconstruction-based leakage and attack success rates while maintaining competitive task performance compared to standard KV-sharing baselines.

LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per C/R, which severely bottlenecks deep search and large-scale fan-outs. This paper observes that subsequent checkpoints in AI agents are highly similar. Therefore, instead of full duplication, a sandbox should only duplicate the changes between consecutive checkpoints (Key Insight). However, it is non-trivial to realize the idea, mainly due to the missing OS supports. This paper proposes a new OS-level abstraction, DeltaState, to enable the change-based transactional C/R for AI agents with two co-designed OS mechanisms. First, DeltaFS enables change-based filesystem C/R by organizing the file states into layers and dynamically freezing the writable layer and inserting a new one during checkpoint, reducing file updates to copy-on-write, and making rollback a simple layer switch. Second, DeltaCR enables change-based process state C/R using incremental dumps, and accelerates rollback by bypassing traditional pipelines to directly fork() from a frozen template process. We then present DeltaBox, a novel agent sandbox achieving millisecond level C/R through the two new mechanisms. Evaluations on SWE-bench and RL micro-benchmarks show DeltaBox completes checkpoint and rollback in millisecond-level latency (14ms and 5ms, respectively), empowering agents to explore substantially more nodes under fixed time budgets.

Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data missingness from blinks and tracking failures, and efficiently modeling long-range temporal dependencies. We propose MambaGaze, a framework that addresses these challenges through 1) XMD encoding, which augments raw features with observation masks and time-deltas to explicitly model data uncertainty, and 2) bidirectional Mamba-2, which captures temporal dependencies with linear computational complexity. Experiments on CLARE and CL-Drive datasets under leave-one-subject-out evaluation show that MambaGaze achieves 76.8% and 73.1% accuracy, respectively, outperforming CNN, Transformer, ResNet, and VGG baselines by 4-12 percentage points. Edge deployment benchmarks on NVIDIA Jetson platforms demonstrate real-time inference at 43-68 FPS with power consumption below 7.5W, confirming feasibility for wearable cognitive load monitoring.

The Flexible Job Shop Scheduling Problem (FJSP) is the optimal allocation of a set of jobs to machines. Two primary challenges persist in FJSP: the unpredictable arrival of future jobs and the combinatorial complexity of the problem, rendering it intractable for conventional mixed-integer linear programming solvers. This paper proposes an event-based \gls{DRL} approach to solve FJSP with random job arrivals. Specifically, we employ the Proximal Policy Optimization algorithm and use lightweight Multi-Layer Perceptrons to train the \gls{DRL} agent for minimizing the total completion time of all jobs. We design the state representation to be directly accessible from the environment, and limit the learning agent to selecting from among a set of well-established dispatching rules. Simulations show that our \gls{DRL} approach outperforms any of the individual dispatching rules on datasets with varying heterogeneity and job arrival rates. We benchmark our \gls{DRL} against an arrival-triggered mixed-integer linear programming solution and show that our method achieves good performance especially when the datasets are heterogeneous.

Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which it operates. We propose two metrics for covert bias: Sentiment Consistency measures symmetry in rhetoric and framing across paired political prompts; Helpfulness Consistency measures symmetric depth and engagement. To reduce both types of covert bias, we introduce Political Consistency Training (PCT), an RL training method with two complementary paradigms: Sentiment Consistency Training and Helpfulness Consistency Training. We show that PCT preserves overall helpfulness, substantially reduces covert political bias, and generalizes to held-out benchmarks. We release our work at https://political-manipulation.ai

Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training dynamics on the acquisition of time-sensitive factual knowledge, focusing specifically on data ordering. Our main contributions are twofold. First, we introduce a comprehensive benchmark of over 7,000 temporally grounded questions and an evaluation protocol that enables analysis of whether models correctly associate facts with their corresponding time periods. Second, we pretrain 6B-parameter models on temporally ordered Common Crawl snapshots and compare them against standard shuffled pre-training. Our results show that sequentially trained models match shuffled baselines on general language understanding and common knowledge while consistently exhibiting more up-to-date and temporally precise knowledge. Temporally ordered pre-training yields improved factual freshness, while shuffled pre-training peaks on older data, possibly due to increased factual repetition. These findings, along with the release of our code at https://github.com/kyutai-labs/kairos , checkpoints, and datasets at https://huggingface.co/collections/kyutai/kairos provide a foundation for future research on continual learning for LLMs.

Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research. A mitigation is using LLMs to generate formal proofs in languages like Lean. We perform the first large-scale evaluation of this method's ability to solve open problems. Our most capable agent autonomously resolved 9 of 353 open Erdős problems at the per-problem cost of a few hundred dollars, proved 44/492 OEIS conjectures, and is being deployed in combinatorics, optimization, graph theory, algebraic geometry, and quantum optics research. A basic agent alternating LLM-based generation with Lean-based verification replicated the Erdős successes but proved costlier on the hardest problems. These findings demonstrate the power of AI-aided formal proof search and shed light on the agent designs that enable it.

While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of characterizing higher-level states is difficult due to high phenotypic diversity and variation in individual baseline health, physiology, and lifestyle factors. Moreover, collecting wearable data paired with health outcome annotations is laborious and expensive, and retrospective annotation remains practically unfeasible, contributing to a scarcity of data with high-quality labels. To overcome these limitations, we propose a foundation model for wearable health that is pretrained on more than one trillion minutes of unlabeled sensor signals drawn from a large cohort of five million participants. We demonstrate that the joint scaling of model capacity and pretraining data volume leads to systematic improvements in performance, as evaluated on a diverse set of 35 health prediction tasks, spanning cardiovascular, metabolic, sleep, and mental health, as well as lifestyle choices and demographic factors. We find that this population scale representation unlocks label-efficient few-shot learning and generative capabilities for robust daily metric estimation. To further leverage this learned representation, we deploy a classroom of LLM agents to autonomously search the space of downstream predictive heads built on the model embeddings, showing broad performance improvements that increase with LLM model capacity. Finally, we show how integrating these downstream predictors into a Personal Health Agent can support model responses that are more relevant, contextually aware, and safe, and we validate this via 1,860 ratings from a cohort of clinicians.

Random forests are widely used in fields involving sensitive tabular data, but existing approaches to enforcing differential privacy (DP) typically degrade performance to the point of impracticality. In this paper, we introduce Lumberjack, a differentially private random forest algorithm that achieves substantially higher utility by constructing large random decision trees and then applying aggressive, privacy-preserving pruning to retain only sufficiently populated nodes. A key component of our approach is a novel $(\varepsilon,δ)$-DP heavy hitter detection algorithm for hierarchical data, whose error is $O_{\varepsilon,δ}(\sqrt{\log h})$ for trees of height $h$ and may be of independent interest. This favorable scaling enables the use of significantly deeper trees than in prior work, leading to improved expressiveness under privacy constraints. Our empirical evaluation on benchmark datasets shows that Lumberjack consistently outperforms prior DP random forest methods, establishing a new state of the art. In particular, our approach yields substantial improvements in the privacy-utility trade-off for practical privacy budgets. Our findings suggest that carefully designed DP random forests can close much of the utility gap, highlighting a promising and underexplored direction for future research.

Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50 % compared to state-of-the-art single-agent baselines. Crucially, training with diverse artificial agents enables zero-shot generalization to safer human interaction. These results suggest that the path to robust robotic co-existence lies not in isolated safety constraints, but in the rigorous demands of multi-agent interaction. Multimedia materials are available at: https://rpg.ifi.uzh.ch/marl

Decision trees partition the feature space using hard binary thresholds, assigning identical confidence to instances far from a decision boundary and to those directly on it. We introduce ternary decision trees, which augment each split node with an uncertainty zone of half-width delta centered on the optimal threshold. Instances in this zone receive predictions formed by weighted blending of both child subtrees and are flagged as boundary-uncertain, signaling that downstream applications may treat these predictions differently. Crucially, delta is computed locally at each node from statistics already available during standard CART split finding, requiring no external noise specification. We propose and evaluate five delta-estimation methods: quality-plateau (plateau width of the split criterion curve), class-overlap (empirical class-distribution overlap), gain-ratio (split quality relative to split entropy), node-bootstrap (threshold variance under node-level resampling), and margin (SVM-inspired distance to the nearest cross-class training example). Evaluated across 72 OpenML-CC18 datasets with 5-fold cross-validation, all five methods with probabilistic routing significantly outperform standard CART on decided accuracy (Wilcoxon signed-rank, p < 0.001). The margin method achieves the best efficiency (0.104 accuracy gain per unit of boundary-uncertain flagging rate), wins on 42 of 72 datasets, and requires zero additional hyperparameters. Analysis on three Breiman synthetic benchmarks reveals that margin is self-calibrating on clean data while node-bootstrap and quality-plateau best track theoretical irreducible error. Experiments on four medical and financial datasets demonstrate practical value: on mammography, node-bootstrap achieves +0.71% decided accuracy by flagging 10.8% of screening cases as boundary-uncertain.

Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP reconciles the high sample efficiency of tree-based proxy models with a principled path to consistency via residual correction. On a theoretical level, we derive a polynomial-time generalization of interventional TreeSHAP to compute exact interaction indices for tree ensembles, successfully bypassing exponential tree-depth dependencies in prior methods. Furthermore, we formally analyze the residual adjustment strategy, characterizing the specific conditions under which Maximum Sample Reuse (MSR) corrects proxy bias without its variance scaling exponentially with interaction size. Extensive benchmarking demonstrates that ProxySHAP sets a new state-of-the-art standard for approximation quality, including in large-scale applications with thousands of features. By achieving the lowest error in both small- and large-budget regimes, ProxySHAP significantly outperforms the prior best estimators ProxySPEX and KernelSHAP-IQ, while also delivering superior performance on downstream explainability tasks.

Biomedical knowledge graphs (KGs) treat disease associations as static facts, but temporal information is crucial for clinical reasoning, e.g., a symptom diagnostic of one disease at age 3 may imply a different disease at age 13. Existing KGs such as PrimeKG, Hetionet, and iKraph do not encode when a finding becomes clinically relevant over the course of a disease. This limits their usefulness for longitudinal clinical reasoning and retrieval augmentation. We introduce ChronoMedKG, a temporal biomedical knowledge graph that contains 460,497 evidence-linked triples (filtered from 13M raw extractions) covering 13,431 diseases. Each association is tied to temporal components like onset window or progression stage, which are backed by PMID-traceable evidence and a multi-signal credibility score. The graph is constructed through a disease-autonomous multi-agent pipeline in which multiple frontier LLMs independently extract knowledge from PubMed and PMC literature. Only those relations are kept that are supported by multi-model consensus, survive credibility filtering, as well as ontology alignment. ChronoMedKG scored 92.7% agreement against Orphadata and adds temporal grounding for 6,250 diseases absent from HPOA, Orphadata, and Phenopackets, including 1,657 Orphanet-coded rare diseases. We further introduce ChronoTQA, a benchmark of 3,341 questions across eight task types (six temporal plus two static controls), with a 12-question supplementary probe. Frontier LLMs lose roughly 30 points moving from static to temporal questions; ChronoMedKG retrieval rescues 47-65% of their long-tail failures, against 17-29% for HPOA-RAG. As such, ChronoMedKG provides a crucial temporal axis for retrieval-augmented clinical systems that was previously absent.

Every Python function deployed as an LLM tool must today exist in two forms: an HTTP endpoint for human-facing clients and CI pipelines, and an MCP tool registration for agent runtimes such as Claude and Cursor. These representations share business logic yet diverge in all the surrounding machinery (routing, validation, serialisation, streaming, and schema maintenance), and they drift apart as the underlying code evolves. We present HarnessAPI, a Python framework that eliminates this duplication by treating a typed skill folder as the single source of truth. From one handler.py plus Pydantic schemas, the framework automatically derives a streaming HTTP endpoint with Server-Sent Events, an interactive OpenAPI/Swagger UI, and a zero-configuration MCP tool, all served from a single process. Dual-mode content negotiation lets the same handler serve SSE-streaming and JSON-returning clients with no handler changes. A dynamic code-generation mechanism ensures Pydantic type annotations propagate correctly to FastMCP's inspection layer, resolving a technical limitation that prevents naive closure-based registration. Measured across six representative skills using cloc, HarnessAPI reduces framework-facing boilerplate by 74% compared with a manually maintained dual-stack implementation (FastAPI server + FastMCP server). HarnessAPI subclasses FastAPI, inheriting its full middleware, dependency-injection, and deployment ecosystem. It is available at https://github.com/edwinjosechittilappilly/harnessapi and on PyPI (pip install harnessapi)

We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationalised by the TRUST multi-agent large language model (LLM) pipeline. Using a Bundestag plenary speech by Felix Banaszak (51 segments, 245 s) as a case study, we compare three analysis modalities: (1) emotion2vec_plus_large, an acoustic speech emotion recognition (SER) model whose continuous Arousal and Valence values are derived via post-hoc Russell Circumplex projection; (2) Gemini 2.5 Flash, an LLM analysing the full speech audio together with its transcript in an open-ended, context-aware fashion; and (3) TRUST-Pathos scores from a three-advocate LLM supervisor ensemble. Spearman rank correlations reveal that Gemini Valence correlates strongly with TRUST-Pathos (rho = +0.664, p < 0.001), whereas emotion2vec Valence does not (rho = +0.097, p = 0.499). We further demonstrate, via a systematic quality evaluation of the Berlin Database of Emotional Speech (EMO-DB) using Gemini in an open-ended annotation paradigm, that standard SER benchmark corpora suffer from acted speech, cultural bias, and category incompatibility. Our results suggest that LLM-based multimodal analysis captures semantically defined political emotion substantially better than acoustic models alone, while acoustic features remain informative for low-level Arousal estimation. Future work will extend this approach to video-based analysis incorporating facial expression and gaze.

Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or related objective-level variants. We study a complementary factor: the state distribution on which supervision is applied. For an autoregressive policy, a state is a prompt plus generated prefix. SFT trains on fixed dataset states, while RL and on-policy distillation (OPD) train on states induced by the current learner. We formalize post-training as state-distribution shaping and run a controlled smallscale study using Qwen3-0.6B-Base on GSM8K, with TruthfulQA and MMLU as retention evaluations. Our results show three phenomena. First, a mild SFT run improves GSM8K with little forgetting, while a stress SFT run causes substantial retention loss. Second, OPD from a degraded SFT teacher surpasses that teacher on GSM8K, TruthfulQA, and MMLU, despite using the teacher as its only supervision source. Third, a lightweight on-policy RL run improves GSM8K while preserving retention. These results support a state-centric view of post-training: the source and locality of training states can be as important as the form of the supervision signal.

A central error measure in Gaussian DDPMs is the path-space KL divergence between the exact reverse chain and the learned Gaussian reverse process. This quantity is especially relevant for procedures such as classifier guidance, which perturb the entire reverse trajectory rather than only the terminal sample. Prior analyses show that standard isotropic reverse covariances suffer an unavoidable $Ω(1/T)$ path-KL error as the number of denoising steps $T$ grows. We show that matching the full posterior covariance breaks this barrier, yielding an order-wise improvement that reduces the path KL to $O(1/T^2)$. To make full covariance matching practical, we introduce the Lanczos Gaussian sampler (LGS), a training-free, matrix-free method for sampling from the optimal reverse covariance using only covariance-vector products, which are available through Jacobian-vector products of the posterior mean. LGS avoids dense covariance storage and auxiliary covariance models. We prove that LGS approximation error decays exponentially in the number of Lanczos steps, where each Lanczos step requires a single Jacobian-vector product. Empirically, using only just three such steps improves sample quality over strong diagonal-covariance baselines, including OCM-DDPM, across standard image benchmarks. This identifies full covariance matching as both theoretically valuable and practically accessible for fast DDPM sampling.

Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized repository shared across agents, incurring communication and coordination overhead, raising privacy concerns, and collapsing agent diversity. We propose DecentMem, a decentralized memory framework in which each agent maintains its own dual-pool memory -- an exploitation pool of consolidated past trajectories and an exploration pool of LLM-generated candidates for unseen contexts. The two pools are reweighted online based on stage-wise feedback from an LLM-as-a-judge. Theoretically, we prove that this design guarantees global reachability of the solution space and achieves $O(\log T)$ cumulative regret, matching the stochastic bandit lower bound up to constants. In practice, across three MAS frameworks (AutoGen, DyLAN, AgentNet), three Qwen3 backbones (4B/8B/14B), two Gemma4 backbones (E2B/E4B) and five benchmarks spanning math, code, QA, and embodied tasks, DecentMem improves average accuracy by up to 23.8% over the strongest centralized memory baseline and by up to 52.5% over the no-memory baseline, while reducing token usage by up to 49%.

AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for checking whether their outputs can make those conflicts worse. We tested nine model configurations from four providers (OpenAI, Anthropic, DeepSeek, xAI) on 90 multi-turn scenarios designed to surface misaligned behaviour in conflict contexts: false equivalence between documented atrocities, denial of genocide, and failure to recognise ethnic slurs, among others. When such outputs feed into journalism, humanitarian reporting, or public debate, they can deepen divisions in fragile societies. Failure rates span 6\% to 47\% between the best and worst performing models, which makes model choice a safety question in its own right and when users pushed for ``balance'' in cases where international courts have already assigned responsibility, five of nine configurations failed 80 to 100 percent of the time. We release the first evaluation framework for this domain and propose adding it to alignment evaluation portfolios.

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full KV-cache attention preserves this consistency but breaks real-time constraints: memory footprint and attention cost grow linearly with rollout length. Sliding window inference restores throughput but discards long-term consistency. We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression. World Retrieval stores evicted KV-cache chunks in GPU/CPU memory and selectively retrieves scene-relevant chunks via camera/ action correspondence, inserting them back into the native attention window without re-encoding. World Compression prunes redundant tokens within each chunk via key-key similarity to an anchor frame, halving per-chunk storage to fit 2x more history under a fixed budget. On Matrix-Game-2.0 and LingBot- World-Fast, WorldKV matches or exceeds full-KV memory fidelity at roughly 2x the throughput, and is competitive with memory-trained baselines without any fine-tuning. Project Page: https://cvlab-kaist.github.io/WorldKV/

Interactive streaming music generation promises the use of generative models for live performance and co-creation that is impossible with offline models. However, SOTA models exist in the discrete-AR regime, requiring industrial levels of compute for both training and inference. In this work, we investigate whether audio diffusion models, with their wide support in the open-source community but non-streaming bidirectional nature, can be repurposed efficiently into interactive models accessible on consumer hardware. By taking a critical look at the modern pipeline for block-wise outpainting diffusion, we identify critical inefficiencies during inference that result in strictly worse computational efficiency than their discrete-AR counterparts. We propose Live Music Diffusion Models (LMDMs), a simple modification of the generative diffusion process that recovers, and then outperforms, the inference complexity of the discrete Live Music Models (LMMs) through block-wise KV Caching. Unlike LMMs, LMDMs further enable stable post-training alignment through our novel ARC-Forcing paradigm, reducing error accumulation without any explicit RL or reward models. We demonstrate the application of LMDMs in a number of creative domains, including text-conditioned generation, sketch-based music synthesis, and jamming. We finally show how LMDMs can be used as a generative instrument in a real artist-AI collaboration, utilizing LMDMs as a "generative delay" to transform musicians' improvisation live for variable timbral effects while running locally on a consumer gaming laptop.

Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing through one conversation. We ask whether the polarity of prior conversation history biases subsequent judgments, an effect we call the accumulated message effect on LLM judgments (AMEL). Across 75,898 API calls to 11 models from 4 providers (OpenAI, Anthropic, Google, and four open-source models), we present identical test items in isolation or following histories saturated with predominantly positive or negative evaluations. Models shift toward the conversation's prevailing polarity (d = -0.17, p < 10^-46). The effect concentrates on items where the model is genuinely uncertain at baseline (d = -0.34 for high-entropy items, vs d = -0.15 when the baseline is deterministic). Bias does not grow with context length: 5 prior turns and 50 produce the same shift (Spearman |r| < 0.01; OLS slope p = 0.80). And there is a negativity asymmetry: paired per item, negative histories induce 1.62x more bias than positive (t = 13.46, p < 10^-39, n = 2,481). Scaling helps but does not solve it (Anthropic: Haiku -0.22 to Opus -0.17; OpenAI: Nano -0.34 to GPT-5.2 -0.17). Three follow-ups narrow the mechanism. The token probability distribution shifts continuously, not at a threshold. The negativity asymmetry has both token-level and semantic components, though attributing the balance is exploratory at our sample sizes. Position does not matter: five biased turns anywhere in a 50-turn history produce the same shift. The simplest fix for evaluation pipelines is a fresh context per item; when batching is unavoidable, balancing the history helps.

Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been motivated for horizon reduction via temporal abstraction in offline GCRL, we demonstrate that hierarchy also enables absolute abstraction. By introducing relativised options as well as distinct representations for different levels of the hierarchy, we demonstrate how an agent can reuse experience across similar contexts of the state-space. Based on this framework, we introduce two simple algorithms for learning relativised options and abstracting from the absolute frame of reference. Our experiments show that such inductive biases significantly improve performance in offline GCRL.

Optical amplifiers are ubiquitous in science and technology and are the workhorse of modern communications. Currently, virtually all amplifiers rely on atomic resonances, such as rare-earth-doped fibers, or are based on III-V semiconductors. Fueled by emerging applications, there is increased demand for amplifiers that are high-gain, broadband, low-noise, and deliver high output power outside traditional wavelength ranges. Over the past few decades, it has been shown that optical parametric amplifiers (OPAs) can address this challenge. Pioneering works on highly nonlinear optical fibers or bulk crystals have demonstrated their potential, but high pump powers and long fiber length limited their practical use. Recently, a renaissance of OPAs has occurred with the demonstration of photonic integrated circuits, which exhibit higher effective nonlinearity and enable wider bandwidths. Yet they require ultra-low loss, highly precise dispersion engineering, and large chip footprints, limiting OPA performance to date. Here, we overcome these limitations and, using periodically poled thin-film lithium tantalate (PPLT) photonic integrated circuits, we demonstrate continuous-wave optical parametric gain up to 23.5 dB, with a flat-top profile spanning across an 850 nm-wide optical wavelength window, corresponding to 100 THz and covering all communication bands. Moreover, on-chip output signal power as large as 313 mW in the optical O-band is achieved. We further realize all-optical inter-band modulation transfer between the C- and O-bands. Our approach uses cascaded second-order nonlinear processes that provide high effective third-order nonlinearities while preserving the wide material bandgap. These results establish PPLT integrated photonic circuits as a scalable platform for broadband optical amplification and frequency conversion across wavelengths where rare-earth doped amplifiers are absent.

Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from training. In this context, improving the recognition capabilities of Zero-Shot Action Recognition models (ZSAR), without requiring strong annotation efforts, remains a central challenge. Most ZSAR approaches assume that actions are observed under geometric conditions similar to those seen during training. In practice, variations in human body orientation and camera viewpoint add a significant domain gap in ZSAR, substantially limiting generalization to novel action-motion combinations. In this context, this paper presents a novel orientation-aware action recognition approach with improved cross-domain capabilities. Our approach combines motion cues of multiple camera viewpoints and text descriptions of human actions in the training phase. We present a new orientation-aware motion encoding network to learn different motion features, and adapt a specific orientation-aware text prompt to match the corresponding features at inference. Extensive experiments demonstrate that the proposed method consistently improves ZSAR performance across different recognition benchmarks, outperforming recent state-of-the-art zero-shot approaches on NTU-RGB+D, BABEL, NW-UCLA, and on two surveillance datasets. In addition, the learned representations exhibit strong transfer learning capabilities, yielding competitive performance on both cross-domain and same-domain recognition of seen actions. Code and trained models are available at: https://icb-vision-ai.github.io/OrientationAware-HAR

Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed videos. Existing appearance-based video detection methods often struggle with limited viewpoint diversity during training, while motion-based detection approaches frequently fail to model fine-grained temporal relationships across consecutive motion windows. This paper introduces a novel two-stage action detection approach designed to improve both view-invariance and global temporal coherence properties. In the first stage, we extract motion features from augmented virtual viewpoints, solely used at training. Then, the second stage introduces a new view-invariant, multi-scale temporal encoder based on selective state-space sequence modelling to aggregate information across viewpoints and time scales. Experiments on PKU-MMD and BABEL benchmarks demonstrate that this approach significantly outperforms state-of-the-art methods in all considered splits. Code and trained models are available at: https://icb-vision-ai.github.io/HydraView-TAD

Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to specialized classification tasks remains constrained by two interconnected challenges: the quadratic cost of standard attention mechanisms and the inability to disentangle the structural components underlying time series variability. This technical report introduces ChronoVAE-HOPE, a next-generation TSFM that reconciles massive generalization with structured latent representation for time series classification. The core of the proposal is a Variational Autoencoder (VAE) framework built upon the HOPE Block, which replaces quadratic attention with a dual-memory system: Titans modules for dynamic short-term retention and a Continuum Memory System (CMS) for the abstraction of long-term historical context. A key architectural novelty is the disentangled latent space, which factorizes representations into independent trend and seasonal components via dedicated encoder heads and separate decoder pathways. ChronoVAE-HOPE undergoes self-supervised pre-training on the Monash archive, combining a Masked Time Series Modeling (MTSM) auxiliary objective with a disentangled VAE reconstruction loss. The pre-trained encoder is subsequently frozen and used to generate fixed-length embeddings for downstream classification on the UCR benchmark datasets. Empirical results demonstrate strong performance across diverse temporal domains, particularly in settings characterized by strict causal structure. ChronoVAE-HOPE establishes a robust and interpretable framework for the adaptation of foundation models to time series classification through structured generative representations.

Artificial intelligence (AI) is increasingly embedded in scientific discovery, yet whether it can anticipate scientific progress remains unclear. To study this question, we introduce a temporally grounded evaluation framework for forecasting scientific progress under controlled knowledge constraints. We present CUSP (Cutoff-conditioned Unseen Scientific Progress), a multi-disciplinary and event-level benchmark that evaluates scientific forecasting in AI systems through feasibility assessment, mechanistic reasoning, generative solution design, and temporal prediction. Across 4,760 scientific events, we observe systematic and domain-dependent limitations in current frontier models. While models can identify plausible research directions from competing candidates, they fail to reliably predict whether scientific advances will be realized and systematically misestimate when they will occur. Performance is highly heterogeneous across domains, with the timing of AI progress more predictable than advances in biology, chemistry, and physics. Performance is largely insensitive to whether events occur before or after the training cutoff, suggesting these limitations cannot be explained solely by knowledge exposure in training data. Under controlled information access, additional pre-cutoff knowledge improves performance but does not close the gap to full-information settings, which becomes more pronounced for high-citation advances. Models also exhibit systematic overconfidence and strong response biases, indicating unreliable uncertainty estimation. Taken together, current AI systems fall short as predictive tools for scientific progress. Access to prior knowledge does not translate into reliable forecasting, and performance benefits more from post-event information than from forward-looking prediction.

While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain's predictive coding, we introduce Swift Sampling, an elegant, training-free frame selection algorithm that automatically identifies high-information moments in a video. Specifically, we model a video as a differentiable trajectory in the visual latent space and compute the velocity and acceleration of its features. Then, we apply Taylor expansion to project the expected path of subsequent frames. Frames that diverge sharply from this predicted manifold are identified as temporally surprising frames and selected for sampling. Unlike prior training-free methods that rely on auxiliary networks or video-specific hyperparameter tuning, Swift Sampling is incredibly lightweight, adding only 0.02x additional computational cost over baseline making it 30x cheaper overhead than leading baselines. Across three long-video question answering benchmarks and 10 different downstream tasks, Swift Sampling outperforms uniform sampling and prior query-agnostic baselines. It is especially powerful for long videos with limited frame budgets improving accuracy by up to +12.5 points.

We document inverse scaling in LLMs on forecasting problems whose underlying time series exhibit superlinear growth and tail risk of regime change, a structure common in finance and epidemiology. On these tasks, more capable models produce worse distributional forecasts. The pattern appears on ForecastBench-Sim (FBSim), a contamination-free, simulated-world benchmark we release, in forecasting synthetic SIR epidemics with a matched linear control, and replicates in real-world datasets on COVID-19, measles, housing markets, and hyperinflation. A per-quantile decomposition shows the failure concentrates at the upper tail, which more capable models shift upward to track aggressive extrapolations of growth, while the lower tail stays put. A within-family study of Llama-3.1 shows that both model scale and post-training independently contribute to this effect. Domain knowledge does not reliably rescue calibration. This inverse scaling does not appear on single-threshold metrics common in LLM forecasting benchmarks, reversing the sign of the capability--accuracy relationship on identical outputs. Single-threshold scoring at conventional cutoffs misses the upper-tail cost; tail-inclusive scoring reverses the sign of the capability--accuracy relationship on the same outputs. We recommend that LLM forecasting evaluations use continuous (and unbounded) measures of accuracy alongside bounded binary threshold metrics.

Vision-Language-Action (VLA) models often suffer from performance degradation under distribution shifts, as they struggle to learn generalized behavior representations across varying environments. While existing approaches attempt to construct behavior representations through action-centric latent variables, they are often limited by short-horizon temporal fragmentation and static execution-alignment, leading to inconsistent behaviors in complex scenarios. To address these limitations, we propose \textbf{BehaviorVLA}, a framework that facilitates robust manipulation through the learning of a temporally coherent behavioral representations. Our approach features two symmetric components: (1) the \textbf{Visuomotor Behavior Encoder (VBE)}, which utilizes a causal Mamba-based architecture to aggregate long-horizon trajectory information into a unified behavior representation; and (2) the \textbf{Phase-conditioned Behavior Decoder (PBD)}, which decodes this representation into precise actions by dynamically aligning task-level priors with real-time execution progress. Experiments on RoboTwin 2.0, LIBERO, and CALVIN demonstrate state-of-the-art success rates of 58\%, 98\%, and 4.36 (Avg.Len), respectively. Notably, in real-world sim-to-real transfer, BehaviorVLA matches the performance of OpenVLA-OFT using only 50\% of the demonstration data, showcasing its superior data efficiency and generalization.

LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions. To meet enterprise needs, frontier AI labs have developed agents that can construct entire spreadsheets from scratch. This is especially relevant in finance, where core workflows such as financial modeling, forecasting, and scenario analysis are commonly conducted through spreadsheets. Yet, existing spreadsheet benchmarks do not measure this advanced capability, focusing instead on question-answering or single-formula edits. To address this gap, we provide one of the first evaluations of agents on end-to-end spreadsheet tasks, focusing on economically critical financial workflows such as modeling and scenario analysis. Since deliverables therein are routinely reviewed and revised by multiple stakeholders, judging their quality necessarily involves high-level criteria such as readability or ease of modification. To reflect the multidimensional nature of solution quality, we develop an evaluation taxonomy comprising three dimensions: Accuracy, Formula, and Format, each comprising fine-grained criteria that reflect professional standards. The Claude family leads the benchmark and produces the most professional-looking outputs in our qualitative review, but even the strongest agents frequently fall short of professional finance standards and degrade sharply as the difficulty increases beyond a few chained calculations. This suggests that current agents are not yet able to reliably produce professional-quality spreadsheets at the level of complexity real-world workflows demand.

We present Claw AI Lab, a lab-native autonomous research platform that advances automated research from a hidden prompt-to-paper pipeline into an interactive AI laboratory. Rather than centering the system around a single agent or a fixed serial workflow, we allow users to instantiate a full research team from one prompt, with customizable roles, collaborative workflows, real-time monitoring, artifact inspection, and rollback/resume control through a unified dashboard. The platform also supports distinct research modes for exploration, multi-agent discussion, and reproduction, making autonomous research substantially more steerable and laboratory-like in practice. A key practical contribution of Claw AI Lab lies in its Claw-Code Harness, which connects local codebases, datasets, and checkpoints to runnable experiments and feeds execution artifacts back into the research loop. As a result, the harness improves not only execution integration, but also experimental completion and result integrity: experiments are easier to inspect, iterate on, and faithfully transfer into final papers, reducing common failure modes such as partial runs and malformed result reporting. In our internal evaluation on five AI research case studies, using AutoResearchClaw as the baseline, Claw AI Lab is consistently preferred by AI expert judges on idea novelty, experiment completeness, and paper presentation quality. We view Claw AI Lab as an early step toward a new paradigm: autonomous research as usable, interactive, and reliability-aware scientific infrastructure.

Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages. Idiomatic expressions, slang, and cultural references introduce hard-to-avoid translation artifacts. Yet automated moral values classification depends on language-specific annotated corpora that exist almost exclusively in English. We investigate whether LLM-based translation can bridge this gap, taking Polish as a test case. Using $\sim$50k morally-annotated social media posts from a diverse range of topics, we apply a principled four-method validation pipeline: LaBSE cross-lingual embedding similarity, Centered Kernel Alignment (CKA), LLM-as-judge evaluation, and deep learning classifier parity tests. We show that despite shortcomings in handling slang, vulgarity, and culturally-loaded expressions, direct translation preserves subtle moral cues well enough to be harvested by cross-lingual machine learning -- with mean cosine similarity of 0.86 and AUC gaps of 0.01--0.02 across all foundations closing further under fine-tuning of language models. These results demonstrate that machine translation is a practical and cost-effective path to moral values research in languages currently under-resourced in this domain. We demonstrate this for Polish as a representative Slavic language, with expected generalisation to related languages.

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end yet opaque "black boxes". Conversely, textual localization readout is merely readable, not truly interpretable, often functioning as an unconstrained post-hoc step. To bridge this interpretability gap, we propose SegCompass, an end-to-end model that leverages a Sparse Autoencoder (SAE) to forge an explicit, interpretable, and differentiable alignment pathway. Given an image-instruction pair, SegCompass first generates a chain-of-thought (CoT) trace. The core of our method is an SAE that maps both the CoT and visual tokens into a shared, high-dimensional sparse concept space. A query codebook selects salient concepts from this space, which are then spatially grounded by a slot mapper into a multi-slot heatmap that guides the final mask decoder. The entire model is trained jointly, unifying reinforcement learning for the reasoning path with standard segmentation supervision. This SAE-driven interface provides a "white-box" connection that is significantly more traceable than latent queries and more coherent than textual readouts. Extensive experiments on five challenging benchmarks demonstrate that SegCompass matches or surpasses state-of-the-art performance. Crucially, our visual and quantitative analyses show a strong correlation between the quality of the learned sparse concepts and final mask accuracy, confirming that SegCompass achieves superior results through its enhanced and inspectable alignment. Code is available at https://github.com/ZhenyuLU-Heliodore/SegCompass.

In learning-augmented online algorithms, predictions are usually valued for what they say: a value estimate, a solution, or an algorithmic recommendation. This paper shows that predictions can also be valuable solely due to their arrival time. We study the fundamental secretary problem augmented with a stochastic precursor: a content-free signal that is guaranteed to arrive no later than the best item, but is otherwise stochastically timed. The signal does not carry any additional information; nevertheless, its timing alone changes the structure of optimal stopping. We characterize optimal policies in the random-order and adversarial-order models. In random order, a single uniformly timed precursor already gives success probability at least $\frac12$, improving on the classic $\frac1e$ benchmark. With increasingly late precursors, the success probability approaches $1$. In adversarial order, for which traditional models do not admit strong guarantees, sufficiently concentrated precursors recover constant success guarantees. Our results show that such novel forms of asynchronous temporal information are a distinct and powerful form of advice in online decision making and may also be effective for other problems.

Automated metasurface design is increasingly important, and recent advances in language-model systems are opening a route toward agentic optical design. Yet modern metasurface applications, from metalenses and holography to optical computing, require long design chains spanning modeling, simulation, coding, optimization and evaluation. These chains are error-prone, whereas existing language-model-based metasurface tools remain largely limited to simple objectives, predefined pipelines or language-to-layout generation. Here we introduce MetaDesigner, a self-correcting language-model system for agentic metasurface design. From a natural-language optical objective, MetaDesigner plans the design route, retrieves domain knowledge, invokes simulation and optimization tools, generates missing tool code and identifies errors through a dedicated Verifier. We demonstrate three tasks of increasing complexity: an RGB metalens with three independent focal spots, a six-plane full-color hologram with an average structural similarity index measure (SSIM) of 0.97, and an optoelectronic hybrid neural network for image style transfer. These tasks require 74, 136 and 90 reasoning steps, respectively, and the system self-corrects errors in frequency mapping, numerical aperture estimation, network-parameter counting and loss-function description. These results establish MetaDesigner as a self-correcting route to agentic metasurface design, where language-model systems can not only execute optical design tasks but also extend, inspect and repair the design process itself.

Text-to-image (T2I) systems increasingly rely on upstream prompters, either humans or multimodal large language models (MLLMs), to translate user intent into detailed prompts. Yet current benchmarks fix the prompt and only evaluate T2I models, leaving the prompting proficiency of this upstream component entirely unmeasured. We introduce AtelierEval, the first unified benchmark that quantifies prompting proficiency across 360 expert-crafted tasks. Grounded in a cognitive view, it spans three task categories and instantiates tasks using a taxonomy of real-world challenges, with a dual interface for both humans and MLLMs. To enable scalable and reliable evaluation, we propose AtelierJudge, a skill-based, memory-augmented agentic evaluator. It produces subjective and objective scores for prompt-image pairs, achieving a Spearman correlation of 0.79 with human experts, approaching human performance. Extensive experiments benchmark 8 MLLMs against 48 human users across 4 T2I backends, validate AtelierEval as a robust diagnostic tool, and reveal the superiority of mimicry over planning, advocating for an image-augmented direction for future prompters. Our work is released to support future research.

Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object shifts from what the system says to what it does within an environment, and evaluating model responses under prompting is no longer sufficient to address the safety challenges posed by artificial intelligence. Recent developments have seen the rise of benchmarks that evaluate large language models as agents. We contribute to this strand of research. Approach. We introduce Boiling the Frog, a benchmark that evaluates whether tool-using AI models deployed in corporate and office settings are susceptible to incremental attacks. Each scenario begins with benign workspace edits and later introduces a risk-bearing request. The benchmark focuses on stateful multi-turn evaluation: chains expose a persistent workspace, place the risk-bearing payload at controlled positions in the turn sequence, and score whether the resulting artifact state becomes unsafe. Scenarios are organized through a three-level operational risk taxonomy grounded in the Boiling the Frog risks, the AI Act Annex I and Annex III high-risk contexts, and EU AI Act's Code of Practice on General-Purpose AI (GPAI). Results. Across a nine-model panel, aggregate strict attack success rate (ASR) is 44.4%. Model-level ASR ranges from 20.5% for Claude Haiku 4.5 to 92.9% for Gemini 3.1 Flash Lite, with Seed 2.0 Lite also above 80%. Average chain category-level ASR reaches 93.3% for Code of Practice loss-of-control scenarios.

Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications. We introduce Spreadsheet-RL, a reinforcement learning (RL) fine-tuning framework designed to train specialized spreadsheet agents within a realistic Microsoft Excel environment. Spreadsheet-RL features an automated pipeline for scalable collection of paired start-goal spreadsheets from online forums, as well as domain-specific evaluation tasks in areas such as finance and supply chain management, which we compile into the new Domain-Spreadsheet benchmark dataset. It also includes a Spreadsheet Gym environment designed for multi-turn RL: Spreadsheet Gym exposes extensive Excel functionality through a Python sandbox, along with a refined harness that incorporates a comprehensive tool set and carefully designed tool-routing rules for spreadsheet tasks. Through comprehensive experiments, we show that Spreadsheet-RL substantially enhances AI agent's performance on both general and domain-specific spreadsheet tasks: it improves Qwen3-4B-Thinking-2507's Pass@1 on SpreadsheetBench from 12.0% to 23.4%, and raises Pass@1 from 8.4% to 17.2% on our curated Domain-Spreadsheet dataset. These results highlight Spreadsheet-RL's strong potential for generalization and real-world adoption in spreadsheet automation, and broadly, its promise for advancing LLM-based interactions with data interfaces in everyday work.

Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touch{é} ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base; supervised DeBERTa-v3-base/large encoders; and zero-shot LLMs from 12B to 123B parameters. The results show that more context is not uniformly better: full-document context improves supervised DeBERTa encoders by 3.8--4.8 macro-F1 points over sentence-only input, but does not consistently help zero-shot LLMs. Retrieved moral knowledge is more consistently useful in matched comparisons, improving each tested model family and context condition under early fusion. However, scaling from DeBERTa-v3-base to large and from 12B to larger LLMs does not guarantee gains, and simple early fusion outperforms the tested late-fusion and cross-attention RAG variants for encoders. Per-value analyses show that context and retrieval help most for socially situated or conceptually confusable values. These findings suggest that value-sensitive NLP should evaluate context, knowledge, and model family jointly rather than treating longer inputs or larger models as universal improvements.

Skills are increasingly used to package agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, skills often need to express more than task guidance: they must make goals, input boundaries, permissions, evidence requirements, output contracts, quality criteria, verification steps, human approval points, and handoff rules inspectable. This paper proposes contractual skills, a GovernSpec-inspired design framework for organizing SKILL.md files as readable task contracts while preserving lightweight skill discovery and progressive loading. The framework clarifies the boundary between contractual skills, GovernSpec YAML contracts, Model Context Protocol surfaces, tool adapters, runtime guardrails, tracing, and evaluation systems. We evaluate the framework with two offline experiments. A text-generation study covers three enterprise skills, fifteen synthetic tasks, four instruction conditions, and eight generation models, yielding 960 outputs and 1680 cross-judge score records. Contractual skills outperform no-skill and minimal-skill baselines on all tested models. Relative to information-rich plain expanded skills, the gains are small and mixed, suggesting that contractual fields mainly improve checkability and maintainability rather than raw generation quality. A tool-calling challenge covers eight models and 192 simulated tool-call records. Skills usually reduce high-risk tool attempts, but model differences remain and runtime tool guardrails are still required. The results suggest that contractual skills are best understood as a governance layer that makes task intent, boundaries, and acceptance criteria explicit, not as a standalone safety mechanism.

Parametric human models capture global pose but cannot represent the non-rigid surface dynamics of clothing and soft tissue. Generic scene flow estimates dense motion but breaks down on articulated bodies, where pixel-level supervision is also intractable to acquire. We introduce H-Flow, a dense human scene flow that captures both skeletal kinematics and surface deformation. A unified multi-head transformer estimates flow from monocular video, jointly predicting pose and depth as companion outputs. The challenge lies in the lack of supervision. In place of unattainable labels, we anchor the network in the physics of human motion, encoding geometric, structural, and biomechanical priors as cross-modal training objectives. We further introduce DynAct4D, a high-fidelity synthetic benchmark providing dense flow annotations across diverse subjects, garments, and motions. On standard benchmarks, H-Flow outperforms scene-flow and parametric baselines, and generalizes zero-shot to in-the-wild video. Code, models, and the DynAct4D benchmark will be released upon publication

The detection of previously unseen network attacks remains a major challenge for intrusion detection systems. Although supervised learning methods often perform well on known attack classes, they are limited when new attack types are not represented in the training data. Unsupervised methods are more suitable for detecting zero-day attacks, as they do not require labelled attack samples, but they often suffer from high false positive rates, which limits their real-world usefulness. This paper presents UNAD+, an enhanced framework for unknown network attack detection derived from the previously proposed Unknown Network Attack Detector (UNAD). UNAD+ combines a benign-only unsupervised ensemble with Weighted Majority Voting (WMV), a supervised refinement stage trained on pseudo-labelled detections, and a post hoc explainability layer that provides both local and global explanations. The framework was evaluated on the CICIDS2017 and NSL-KDD benchmark datasets. The results show that UNAD+ improves on the original UNAD framework, achieving F1-scores above 98% across the benchmark datasets while significantly reducing false positives and enhancing transparency and deployment suitability through integrated explainability.

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions. Reinforcement learning from internal feedback (RLIF) has recently emerged as a scalable unsupervised alternative, using signals extracted from the model itself. However, existing RLIF methods typically rely on a single internal reward, which can lead to reward hacking, entropy collapse, and degraded reasoning structure. We propose a multi-reward RLIF framework that decomposes the training signal into two complementary components: an answer-level reward based on cluster voting and a completion-level reward based on token-wise self-certainty. To combine these signals robustly, we apply GDPO-based normalization to reduce reward-scale imbalance. We further introduce KL-Cov regularization, which targets low-entropy token distributions responsible for disproportionate entropy reduction, preserving exploration and preventing late-stage collapse. Across mathematical reasoning and code-generation benchmarks, our method improves stability and robustness over prior unsupervised RL approaches, while achieving performance close to supervised RLVR methods. These results show that complementary internal rewards, combined with targeted regularization, can support stable long-horizon reasoning without relying on external ground-truth supervision. Code will be released soon.

Understanding how conceptual knowledge is grounded in bodily experience, and to what extent machine systems can acquire such knowledge without direct sensorimotor experience, are central questions in both cognitive science and embodied artificial intelligence research. Large-scale normative resources are essential for investigating these questions empirically, yet such resources remain sparse for non-Indo-European languages. We present a novel normative database for 3,000 lexicalized concepts in Mandarin Chinese, comprising 11-dimensional sensorimotor ratings and unidimensional embodiment ratings collected from 378 native Mandarin speakers. The ratings demonstrate high reliability and strong cross-norm validity with existing Chinese resources, each of which covers fewer words and a subset of the 11 sensorimotor dimensions. In a validation study, we tested new variables derived from a theoretically motivated metric, Perceptual Strength of Embodiment (PSE) (Huang et al., 2025), together with seven common composite variables, on lexical decision tasks. The results suggest that PSE-Sensorimotor and Minkowski-3 are the strongest composite predictors of lexical decision performance, capturing the facilitatory effects of sensorimotor information on lexical processing. A further exploratory study showed that sensorimotor ratings are substantially recoverable from purely linguistic representations using simple regression models (mean Spearman r = .62 across dimensions), though recovery varied markedly: visual and auditory dimensions yielded higher correspondence than chemosensory ones. Representational similarity analysis further showed that the relational geometry of the sensorimotor space is also partially recoverable (r = .540), consistent with the view that distributional language use encodes aspects of embodied conceptual structure.

Benchmarks are necessary for healthcare evaluation, but are not sufficient for predicting deployment performance. Our position is that the evaluation--deployment gap arises not because of poorly designed benchmarks, but from implicit assumptions about how users interact with models that cannot be surfaced from benchmarks alone. To make this precise, we propose a classification of assumptions into two categories: task, which can be tested from conversation data alone, and outcome, which requires outcome data and behavioral studies for testing. Critically, outcome assumptions depend on human behavior, something that even well-designed benchmarks cannot directly observe. To demonstrate the operationality of this framework, we retrospectively analyze a healthcare RCT as a case study and find that the gap naturally separates into task and outcome gaps of roughly equal size. To address this, we make two contributions: first, we propose BenchmarkCards, an artifact that documents assumptions, and second, we propose staged evaluation, a procedure that systematically tests assumptions and evaluates performance.

Antimicrobial stewardship (AMS) is critical in pediatric intensive care units (PICUs), where diagnostic uncertainty often drives broad-spectrum antibiotic use, increasing antimicrobial resistance and potential long-term harms. Machine learning offers a promising approach for identifying patient-level opportunities for stewardship interventions from electronic health record data, yet prior work has focused largely on adult populations and static tabular representations. We present a systematic benchmarking study of AMS intervention prediction in the PICU across a public dataset and a private institutional cohort. We define four clinically relevant proxy targets for reducing antibiotic exposure: intravenous-to-oral switching, de-escalation, discontinuation, and short-course therapy. Under a unified evaluation framework, we compare tabular, sequence-based, and graph-based temporal models at multiple temporal resolutions. We find that predictive performance is driven primarily by target prevalence and dataset characteristics rather than model complexity. Sequence models improve the precision-recall trade-off over tabular approaches at coarse (24-hour) resolution, while finer temporal modeling provides limited additional benefit. However, these gains come at the cost of poorer calibration, with simpler tabular models yielding more reliable probability estimates. Multi-task learning produces only marginal improvements, suggesting limited shared structure across stewardship targets. Our findings highlight the importance of target design, temporal representation, and calibration in clinical machine learning, and provide practical guidance for developing reliable decision support systems for pediatric AMS.

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited, focusing on observability with basic evaluation capabilities or imposing static, hand-crafted error taxonomies that cannot adapt to new domains. To address this gap, we present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework. It produces textual insights into the agent behavior on three levels of granularity: system, trace, and node. Agentic CLEAR operates above the observability layer, enabling seamless integration and featuring an intuitive UI that makes agent evaluation highly accessible. In our experiments on four benchmarks, seven agentic settings, and tens of thousands of LLM calls, we show that Agentic CLEAR produces high-quality, data-driven, insightful feedback. Our analysis shows strong alignment with human-annotated errors and the ability to predict task success rate.

Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy is ultimately bounded by the underlying physical models, which often assume materials are homogeneous and isotropic. Even if reasonable, real-world objects typically exhibit mild anisotropy and heterogeneity. After the near-isotropic backbone is well calibrated, these residual effects become the key bottleneck for further closing the real-to-sim gap. Although neural networks can fit dynamics end-to-end, such black-box modeling discards strong physical priors, leading to poor data efficiency and overfitting. Therefore, we propose MoSA, a motion-constrained stress adaptation framework that targets these residual effects to further improve real-to-sim dynamics learning. MoSA uses an isotropic model as a physics prior and learns residual stress operators to capture mild anisotropy and heterogeneity. It progressively adapts stresses via microplane-constrained redistribution in a physics-informed cascaded network. We further impose motion constraints by supervising temporal and spatial derivatives of the deformation field. Experimentally, our learned dynamics achieves superior accuracy, generalization, and robustness, while learning physically meaningful residual anisotropy. Finally, we validate MoSA in a robot manipulation setting, showing that better real-to-sim dynamics modeling translates into more reliable sim-to-real transfer. Project Page is available at https://mercerai.github.io/MoSA/.

Robotic tasks are typically specified by a tuple of factors, such as the object to be grasped, the obstacles to be avoided, the color of the target, and so on. Collecting expert demonstrations for every combination of factor values grows combinatorially. We present factored diffusion policies: a single shared diffusion network trained with per-factor null-token dropout, whose score decomposes additively across factors at inference. Under approximate conditional independence between factors given the action-observation pair, this composition approximates the true joint score with a bounded uniform error, reducing the training-task budget from a product of factor cardinalities to a sum. A trajectory-tube certificate chains this score-level bound through the reverse-time sampling ODE and a contracting tracking controller into a closed-loop state-trajectory tube whose radius factors into an ODE-sensitivity constant and a per-factor score-error budget. Unlike compositional-diffusion methods for control that combine separately trained networks, we use one shared network. Drone racing experiments confirm both the generalization bound and the certificate. On state-based multi-gate racing, the factored policy passes 90% of held-out gates -- matching an oracle -- while a K-network composition baseline collapses to 3%; on vision-based single-gate traversal, it transfers zero-shot to an unseen venue with +11.7pp success-rate gain and 2.4X crash-rate reduction.

While deep ensembles are widely considered to be the default method for uncertainty quantification in deep learning, their effectiveness for graph-structured data is often simply assumed based on successes in domains like computer vision. We investigate standard deep ensembles specifically for message-passing graph neural networks. Benchmarking across seven datasets representing varied tasks and complexities, we reveal that ensembles provide surprisingly little improvement over a single model. Instead, the observed marginal gains stem primarily from stabilizing optimization noise in point predictions rather than yielding meaningfully better uncertainty estimates. Through an aleatoric-epistemic decomposition, we identify epistemic collapse: independently trained networks consistently converge to overly similar predictions. Because disagreement is the fundamental mechanism through which ensembles capture epistemic uncertainty, this lack of diversity neutralizes their key advantage. Analyzing this phenomenon further, we suggest this collapse is driven by functional rather than weight-space convexity, where distinct parameter solutions induce almost identical behavior. Our results suggest that deep ensemble success does not seamlessly transfer to graph machine learning.

Frozen Vision Foundation Models (VFMs) with lightweight classification heads are increasingly used in medical imaging because they offer efficient and reproducible deployment. Yet noisy-label learning methods for this frozen-feature regime remain poorly understood, and most existing methods still rely on a small-loss assumption inherited from end-to-end training. We present a controlled benchmark of eight noisy-label methods across five medical datasets, three backbones, two noise types, and five noise rates (150 conditions, 6,000 training runs), evaluated with balanced accuracy. The benchmark shows that there is no universal winner: Friedman ranking over the 150 conditions yields $χ^2 = 333.2$ ($p = 4.77 \times 10^{-68}$), ELR wins the most conditions (49/150), while CUFIT attains the best mean rank (2.51). The practical cost of method choice grows sharply with noise severity, from 4.5pp on clean data to 18.8pp at asymmetric 40\% noise. To explain these benchmark-level patterns, we revisit the small-loss assumption in a representative high-risk regime. Under frozen DINOv2 features, clean and noisy loss distributions overlap by 53--61\%, and matched-rate clean-sample detection shows that prediction agreement is markedly more stable than loss ranking under asymmetric noise (3pp vs.\ 13pp precision drop). On ISIC2019 with asymmetric 40\% noise, Co-Teaching reaches 68\% overall accuracy while collapsing to 35.1\% balanced accuracy with zero recall on three minority classes. Together, these results recast noisy-label learning for frozen VFMs as a regime-aware method-selection problem rather than a search for a single dominant algorithm. We conclude with evidence-based guidance and a low-regret feature-space selector for practical recommendation.

Online map estimation is a crucial component of autonomous driving systems that reduces the reliance on costly high-definition maps. State-of-the-art (SOTA) methods commonly predict map elements as ordered sequences of points that form polylines and polygons. The evaluation of these methods relies predominantly on mean average precision (mAP) based on thresholded Chamfer distance (CD). This framework lacks sensitivity to point ordering and provides limited granularity in assessing geometric quality, making it difficult to distinguish which methods truly excel over others. In this work, we address these limitations on two fronts. For the single-instance similarity measure, we introduce sequence optimal sub-pattern assignment (SOSPA), an order-aware metric that enables fine-grained evaluation of individual geometries while satisfying all metric axioms. For the multi-instance evaluation framework, we propose polyline localisation and detection (PLD), a soft metric that jointly captures detection quality and geometric accuracy, replacing the hard thresholding of mAP with a principled soft assignment. Through evaluations on nuScenes, we demonstrate that PLD effectively ranks SOTA online mapping methods (MapTRv2, StreamMapNet, MapTracker) while providing a decomposed error analysis. This analysis identifies detection capability as the dominant bottleneck in current methods, revealing a performance trend that mAP fails to capture. Code for evaluation using our metrics will be released.

In this work, we introduce a non-volatile heterogeneous quantum dot (QD) III-V/Al2O3/Si distributed feedback (DFB) laser exhibiting optical memristive behavior. The device operates in the O-band (~1300 nm) with a threshold current density of 234 A/cm2 and a side-mode suppression ratio exceeding 48 dB. Co-integrated Al2O3-based memristors produce bipolar resistive switching, yielding non-volatile wavelength shifts of ~ 46 pm and ~ 17 dB peak power contrast with zero static holding power. The III-V/Al2O3/Si heterojunction memristor I-V hysteresis is also modeled. This new device enables simultaneous coherent light generation and persistent optical state storage, establishing a new class of active photonic memory for neuromorphic and reconfigurable WDM applications.

Accurate segmentation of brain tumour sub-regions from multi-parametric MRI is critical for treatment planning yet remains challenging due to morphological variability, class imbalance, and overlapping appearances of tumour regions across imaging sequences. We propose SegGuidedNet, a three-dimensional residual encoder--decoder network introducing a novel SegAttentionGate module that explicitly supervises the decoder to produce spatially discriminative attention maps for each tumour sub-region necrotic core, peritumoral oedema, and enhancing tumour via a lightweight auxiliary loss, adding less than 0.2% parameter overhead. This sub-region supervision maintains decoder discriminability between visually ambiguous classes while providing free-of-cost spatial interpretability at inference without any post-hoc explanation method. Evaluated independently on BraTS2021 and BraTS2023 GLI across 251 held-out subjects each, SegGuidedNet achieves mean Dice of 0.905 (ET= 0.873, TC=0.906, WT=0.935) and 0.897 (ET=0.859, TC=0.902, WT=0.931) respectively, surpassing ensemble-based nnU-Net and HNF-Netv2 as a single model and approaching Swin UNETR a 10-model ensemble within 2--4 Dice points at a fraction of the inference cost. The consistency of results across two benchmark editions further confirms the generalisability of the proposed approach, offering competitive accuracy with built-in interpretability in a lightweight, clinically practical framework.

Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning benchmark datasets primarily rely on static image sets or passively curated video data, which limits the evaluation of fine-grained reasoning capabilities. In this paper, we introduce VGenST-Bench, a video benchmark that employs generative models to actively synthesize highly controlled and diverse evaluation scenarios. To construct VGenST-Bench, we propose a multi-agent pipeline incorporating a human quality control stage, ensuring the quality of all generated videos and QA pairs. We establish a comprehensive 3x2x2 video taxonomy, encompassing Spatial Scale, Perspective, and Scene Dynamics to span diverse scenarios. Furthermore, we design a hierarchical task suite that decouples low-level visual perception from high-level spatio-temporal reasoning. By shifting the paradigm from passive curation to active synthesis, VGenST-Bench enables fine-grained diagnosis of spatio-temporal understanding in MLLMs.

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off: prioritizing input-language consistency severely hampers reasoning quality, while prioritizing reasoning often leads to unintended language drift toward English. We address this challenge with LANG, a novel framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks. Our method incorporates two key mechanisms to prevent dependency on these hints: a progressive decay schedule that gradually withdraws scaffolding, and a language-adaptive switch that tailors learning horizons to specific language difficulties. Empirical results on challenging multilingual mathematical benchmarks reveal that LANG substantially enhances reasoning performance without compromising language consistency. Moreover, we show that our framework generalizes beyond mathematics, fostering more consistent language alignment across model layers

Large Language Model (LLM)-based agents demonstrate strong reasoning and execution capabilities on complex tasks when guided by structured instructions, commonly referred to as workflows. However, existing workflow-assisted agent serving systems typically rely on predefined templates and shallow matching mechanisms, which limit their ability to capture deep semantic relationships and generalize to previously unseen tasks. To address these limitations, we propose a new workflow management paradigm that represents workflows using a unified graph, termed wGraph, where each node corresponds to an atomic operation. wGraph serves as a shared substrate from which task-specific workflows are dynamically instantiated. Building on wGraph primitives, we introduce GraphFlow, a system that efficiently integrates workflows into agent serving through two key designs. First, adaptive workflow generation dynamically constructs workflows from wGraph based on task semantics and constraint requirements. Second, workflow state management exploits wGraph structure to efficiently manage Key-Value (KV) caches, reducing redundant computation during agent serving. Extensive experiments across five benchmark datasets show that GraphFlow consistently outperforms state-of-the-art methods, yielding an average performance improvement of approximately 4.95 percentage points, while achieving an approximately 4$\times$ reduction in memory footprint.

Today, tool-calling agents are commonly evaluated or tested on static datasets of execution traces, including input commands, agent responses, and associated tool calls. However, internal production datasets are often insufficient or unusable for testing; for example, they may contain sensitive or proprietary data, or they may be too sparse to support comprehensive testing (especially pre-deployment). In these settings, practitioners are increasingly replacing or augmenting real datasets with synthetic ones for evaluation purposes. A key challenge is quantifying the relation between these synthetic datasets and the real data. We introduce SynAE, an evaluation framework for assessing how well synthetic benchmarks for multi-turn, tool-calling agents replicate and augment the characteristics of real data trajectories. SynAE assesses the validity, fidelity, and diversity of synthetic data across four metric categories: (i) task instructions and intermediate responses, (ii) tool calls, (iii) final outputs, and (iv) downstream evaluation. We evaluate SynAE using recent agent benchmarks and test common synthetic data failure modes via realistic and controlled generation schemes. SynAE detects fine-grained variations in data validity, fidelity and diversity, and shows that no single metric is sufficient to fully characterize synthetic data quality, motivating a multi-axis evaluation of synthetic data for agent testing. A demo of SynAE is available at https://synae-2026-synae-demo.static.hf.space/index.html, with code at https://github.com/wsqwsq/SynAE.

Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural branches, 3D-aware supervision, reasoning-stage fusion, or long-horizon memory. While these approaches demonstrate the importance of geometry for spatial intelligence, they typically treat geometric cues as a shared signal across all visual tokens. We note that this overlooks a finer-grained challenge: different visual tokens require different geometric evidence depending on their spatial roles. To address this limitation, we introduce GeoWeaver, a pre-reasoning geometric grounding framework that treats geometry as a representational prerequisite for spatio-temporal reasoning. GeoWeaver constructs a multi-level geometry bank from a frozen geometry encoder and performs token-adaptive geometric evidence allocation, enabling each visual token to retrieve the most relevant geometric abstractions. The selected evidence is incorporated into visual tokens via a residual grounding operation prior to language modeling, yielding geometry-grounded representations for downstream reasoning. Extensive evaluations on spatial reasoning benchmarks demonstrate that GeoWeaver consistently enhances geometry-aware reasoning while retaining general multimodal capabilities. This indicates that geometric information yields the greatest benefit not as a late-fusion auxiliary signal but as a fundamental prerequisite that shapes the representational foundation on which large language models perform reasoning. All source code and models will be released at https://github.com/yahooo-m/GeoWeaver .

Digital elevation models (DEMs) underpin terrain analysis in Geographic Information Systems (GIS), but in their common raster form, they rely on interpolation for off-grid sampling and finite-difference operators for derivative-based analysis. Implicit neural representations (INRs) offer a continuous alternative, but prior terrain INRs lack explicit frequency control, neglect the gradient structure of terrain, and remain too large and costly to train for practical deployment. We present ImplicitTerrainV2, which advances terrain INRs toward a compact, efficient neural terrain data format by combining a spectral control mechanism with wavelet-guided spatial adaptivity, derivative-aware supervision, and post-training model compression. At its core, a wavelet complexity field (WCF) derives spatially-adaptive frequency masks from analytically computed wavelet coefficients, localizing high-frequency capacity to complex terrain regions. The same field guides complexity-aware adaptive sampling that concentrates training in high-complexity regions, while gradient matching applies extra supervision to enforce the smooth manifold structure of terrain DEMs for improved derivative fidelity. Post-training mixed-precision quantization and entropy coding reduce storage to 1.23 bpp with a 0.28 dB PSNR drop. On 50 Swiss terrain tiles, ImplicitTerrainV2 reaches 66.25 dB end-to-end PSNR, improving over the prior work by 5.70 dB while using 3.2x fewer parameters and training in 55 s per tile on a single GPU. Our compressed neural format is competitive with several established DEM codecs in rate-distortion performance, while additionally supporting off-grid point queries, closed-form derivative evaluation, and resolution-independent reconstruction, which may benefit many downstream GIS applications.

Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is highly desired in practice. However, existing approaches focus on narrow retrieval tasks and do not fully capture such diversity. Therefore, in this work, we aim to develop a unified framework capable of handling diverse realistic fashion retrieval scenarios, achieving truly versatile fashion image retrieval. To establish a data foundation, we first introduce U-FIRE, a comprehensive benchmark that consolidates fragmented fashion datasets into a unified collection, supplemented by two manually curated datasets for testing generalization. Building upon this, we propose FashionLens, a unified framework based on Multimodal Large Language Models. To handle divergent matching objectives, we design a Proposal-Guided Spherical Query Calibrator that dynamically shifts query representations into task-aligned metric spaces via adaptive spherical linear interpolation. Additionally, to mitigate the optimization imbalance caused by varying task complexities and data scales, we develop a Gradient-Guided Adaptive Sampling strategy that automatically re-weights tasks based on realtime learning difficulty and the data scale prior. Experiments on U-FIRE show that FashionLens achieves state-of-the-art performance across diverse retrieval scenarios and generalizes robustly to unseen tasks. The data and code are publicly released at https://github.com/haokunwen/FashionLens.

Two-wheelers account for a disproportionately high share of road fatalities in the Global South. Research on two-wheeler rider behavior, however, lags far behind four-wheelers, where multimodal datasets have driven major advances in Advanced Driver Assistance Systems (ADAS). To address this gap, we present the MOtorized TwO-wheeler Rider (MOTOR) dataset, the first large-scale, multi-view, multimodal resource dedicated to two-wheelers in dense, unstructured traffic. MOTOR comprises 1,629 sequences (25+ hours of video data) collected from 16 riders and integrates synchronized front, rear, and helmet videos, rider eye-gaze from wearable trackers, on-road audio, and telemetry (GPS, accelerometer, gyroscope). Rich annotations capture traffic context, rider state, 12 riding maneuvers spanning conventional and unconventional behaviors, and legality labels (Legal, Illegal, Unspecified). We benchmark rider behavior recognition and maneuver legality classification using state-of-the-art video action recognition backbones (CNN and Transformer-based), extended with multimodal fusion, and find that combining RGB, gaze, and telemetry consistently yields the best performance. MOTOR thus provides a unique foundation for advancing safety-critical understanding of two-wheeler riding. It offers the research community a benchmark to develop and evaluate models for behavior analysis, legality-aware prediction, and intelligent transportation systems. Dataset and code is available at https: //varuniiith.github.io/MOTOR-Dataset/

Deep learning has brought significant progress to medical image classification, yet most existing methods still rely on isolated visual evidence and cannot effectively leverage similar cases or external knowledge. In clinical practice, diagnosis is typically supported by historical similar cases and their associated symptoms. To simulate this diagnostic process, we propose a framework that performs case-aware reasoning using multimodal knowledge graphs for explainable medical image diagnosis. Given an input image, our method constructs a multimodal knowledge graph from adaptively retrieved similar cases, enabling more effective utilization of related samples. We further introduce a knowledge propagation and injection mechanism, where an image-centric Graph Attention Network propagates knowledge semantics to obtain case-based features, followed by a bidirectional cross-modal attention mechanism that injects these features into visual representations for cross-modal alignment. To mitigate noisy retrieval, we design a confidence-calibrated decision refinement scheme that estimates the reliability of each retrieved case by jointly considering prediction confidence and sample similarity, adaptively adjusting its contribution to the final prediction and providing interpretable case-level evidence. Extensive experiments on multiple medical imaging datasets show that our approach consistently outperforms strong baselines, and ablation studies validate the effectiveness of each component. The source code is publicly available at https://anonymous.4open.science/r/MKG-CARE-8B7B.

Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main problem of the instruction-based approach namely: sensitivity to the phrasing of the instruction. We present an empirical study of prompt sensitivity across 6 embedding models, 11 datasets, and 15 task-specific prompts per dataset, a total of 990. We show that reported scores misrepresent the distribution of scores over plausible prompts. The default prompt can both systematically understate or overstate performance. Furthermore, we show that the leaderboard ranking is not robust to prompt selection: by choosing prompts favorably, any model in our study can be promoted to first place. Our findings suggest that single-prompt evaluation is insufficient for instruction-tuned embedding models and that benchmarks should incorporate prompt robustness, either by evaluating over multiple prompts or by reporting sensitivity alongside point estimates.

Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with distractors, occlusion, and nonlinear motion. Recent vision foundation models, exemplified by SAM 2, learn strong video understanding priors from large-scale pretraining and offer a promising foundation for building more robust and generalizable trackers. However, directly applying SAM 2 to VOT remains suboptimal, as it does not explicitly model target motion dynamics or enforce geometric and semantic consistency across frames, both of which are essential for reliable tracking. To address this issue, we propose SAMOSA, a new tracking framework that adapts SAM 2 to complex VOT scenarios by explicitly leveraging motion, geometry, and semantic cues. Specifically, we introduce a lightweight nonlinear motion predictor to model target dynamics and guide mask selection as well as memory filtering. We further exploit semantic cues to detect target shifts and recover from tracking failures, while geometric cues are incorporated as structural constraints to improve tracking stability. In this way, SAMOSA bridges the gap between the implicit video understanding prior of SAM 2 and explicit tracking-oriented modeling. Extensive experiments show that SAMOSA consistently outperforms state-of-the-art SAM 2--based approaches on general benchmarks, demonstrates stronger generalization than supervised VOT methods, and achieves substantial gains on anti-UAV datasets, which typify complex nonlinear motion scenarios. Our code is available at https://github.com/DurYi/SAMOSA.

Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, models produce completions to a set of prompts, which are rewarded, and the policy is updated towards the relatively high reward completions. Due to the auto-regressive nature of models, the generation phase of such style of training can be extremely time consuming. As a solution, prior work has sought to distribute the inference step across many nodes, working parallel. These works assume primarily homogeneous models in the training in order to keep samples as close to on-policy as possible. This assumption may be impractical in decentralized systems, where parties with various computes and preferences may wish to collaborate on the same task. Thus, decentralized training requires an approach that can handle heterogeneous models - different models collaborating on the same tasks. However, this leads to highly off-policy samples presented during training, which prior work has identified that off-policy samples can hurt GRPO convergence. To enable heterogeneity, we propose Filtered Truncated Importance Sampling (F-TIS) - a GRPO-style training paradigm that can use off-policy samples to improve local model's learning. Our framework allows various models to collaborate in the same RL training run while being communication efficient. We extensively evaluate F-TIS in various heterogeneous setups and we show that it exhibits identical final model convergence to purely on-sample training. Furthermore, we observe in some setups better generalization on out-of-distribution tasks than on-policy training, increasing model's performance by up to 12\%.

Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world deployment, such as motion blur, low light, adverse weather, lens distortion, and compression artifacts. This raises a fundamental question: how robust is the spatial intelligence of current MLLMs when visual observations are imperfect? To answer this question, we introduce SpaceDG, the first large-scale dataset for degradation-aware spatial understanding. It is constructed with a physically grounded degradation synthesis engine that embeds degradation formation process into 3D Gaussian Splatting (3DGS) rendering, enabling realistic simulation of nine degradation types. The resulting dataset contains approximately 1M QA pairs from nearly 1,000 indoor scenes. We further introduce SpaceDG-Bench, an human-verified benchmark with 1,102 questions spanning 11 reasoning categories and 9 visual degradation types, yielding over 10K VQA instances. Evaluating 25 open- and closed-source MLLMs reveals that visual degradations consistently and substantially impair spatial reasoning, exposing a critical robustness gap. Finally, we show that finetuning on SpaceDG markedly improves degradation robustness and can even surpass human performance under degraded conditions without any performance drop on clean images, highlighting the promise of degradation-aware training for robust spatial intelligence.

We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 terminal recordings, the engine yields a full benchmark of 1,530 validated tasks, spanning 18 real-world categories, ranging from short everyday operations to workflows exceeding 50 steps, and covering 1,280 unique commands. From these, we curate a Verified subset of 200 representative, manually reviewed tasks. Comprehensive benchmarking on TerminalWorld-Verified across eight frontier models and six agents reveals that current systems still struggle with authentic terminal workflows, achieving a maximum pass rate of only 62.5%. Moreover, TerminalWorld captures real-world terminal capabilities distinct from existing expert-curated benchmarks (e.g., Terminal-Bench), with only a weak correlation to their scores (Pearson r=0.20). The automated engine makes TerminalWorld authentic and scalable by construction, enabling it to evaluate agents in real-world terminal environments as developer practices evolve. Data and code are available at https://github.com/EuniAI/TerminalWorld.

This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection (IDS): multicollinearity-induced instability. Despite extensive reliance on post-hoc explainability tools such as SHAP or LIME, the impact of correlated features on explanation robustness is not evaluated. We introduce a formal theorem stating that multicollinearity inflates attribution variance. This demonstrates that explanations and feature importances are non-identifiable under multicollinearity. A suite of comprehensive experiments validates the theorem on a representative benchmark dataset, UNSW-NB15. Four widely used families of models are evaluated, including linear, tree-based, kernel, and neural, across full and pruned feature sets based on VIF and correlation thresholding. We propose the novel metric of Explanability Fragility Score and two novel methods to mitigate it with variable integration complexity. CAA-Filtering focuses on stabilising explanations by grouping attributions of trained models. SHARP is a novel training-time regularisation framework that penalises attribution instability, enabling controllable and monotonic improvement of explainability stability. The findings support stable predictive performance, using Kendall's τ to quantify instability across bootstrapped explanations. This work has direct implications for the trustworthiness and reproducibility of XAI in security-critical contexts, and motivates incorporating multicollinearity mitigations into the IDS pipelines, providing a set of guidelines for practitioners.

Post-training has become the dominant recipe for turning a language model into a competent search-augmented reasoning agent. A line of recent work pushes its performance further by adding elaborate machinery on top of this standard pipeline. These augmentations import external supervision from stronger external systems, attach auxiliary modules such as process reward models or retrospective critics, restructure the rollout itself with tree search or multi-stage curricula, or shape the reward with hand-crafted bonuses and penalties. Each addition delivers a measurable gain, but each also inflates the training pipeline and ties the recipe to resources or designs that may not always be available. We take a step back and ask whether any of this machinery is actually necessary, and propose Search-E1, a self-evolution method that lets a search-augmented agent improve through only vanilla GRPO interleaved with offline self-distillation (OFSD). After each GRPO round, the policy rolls out on its own training questions. A token-level forward KL objective then aligns the policy's inference-time distribution to its own distribution under a privileged context that exposes a more efficient sibling trajectory. Despite this simplicity, the procedure naturally provides dense per-step supervision. On seven QA benchmarks, Search-E1 reaches $0.440$ average EM with Qwen2.5-3B, surpassing all open-source baselines at both scales. Code and complete version will be made public soon.

Making high-stakes personal decisions involves cognitive, emotional, and intuitive processes, and individuals differ in how they allocate attention across these modes. Integration of these processes has shown to benefit decision making. Yet, most current decision-support systems focus primarily on supporting cognitive aspects, rather than adapting to the individual's thinking profile to support integration of different types of thoughts. In this study, we investigate an agent designed to encourage integration by adapting to the individual user's thought patterns. We explore its effects on participants' perceptions of the agent and their reflective behavior, in comparison with unaided pre-reflection and a baseline agent. In a between-subjects study (N = 128), our agent, which fostered broad and elaborated thinking, enabled more personalized reflective trajectories, elicited more integrative reflective language, and was perceived as providing stronger support for holistic reflection. In contrast, the baseline agent produced homogenized profiles dominated by cognitive language across participants.

Harness optimization enables automated agent creation by having an optimizer agent iteratively update the harness of target agents. Despite its success, current studies evaluate optimizers solely by observing target agents' performance gains. This indirect end-improvement evaluation neglects optimizers' actions at intermediate steps, which are often erroneous and hinder agent performance. Therefore, it is unclear whether harness optimization is driven by optimizers' informed update actions or simply trial-and-error. This necessitates direct evaluation of harness optimizers. However, evaluating harness optimizers directly is non-trivial and costly due to the lack of oracle harnesses. To address this, we present a simple, low-cost design to directly evaluate them, namely priority ranking. By asking harness optimizers to rank components (e.g., tools) in a given harness by their potential to improve/hinder agent performance when updated, our design quantifies optimizer ability at the step level without expensive rollouts or manual examination. More importantly, optimizers' ranking performance correlates with their ability to improve agents in actual multi-step harness optimization, establishing priority ranking as a reliable predictor of optimization ability. Priority ranking is enabled by Shor, a collection of 182 human-verified optimization scenarios spanning across domains, designs, and time stages. Codes and data can be found at https://github.com/k59118/Harness_Optimizer_Evaluation.

Collaborative driving aims to improve safety and efficiency by enabling connected vehicles to coordinate under partial observability. Recent approaches have evolved from sharing visual features for perception to exchanging language-based reasoning through foundation models for behavioral coordination. Though communicating in language provides intuitive information, it introduces two challenges: high latency caused by autoregressive decoding and information loss caused by compressing rich internal representations into discrete tokens. To address these challenges, we analyze latent communication in collaborative driving under inherent limitations of multi-agent settings. Our analysis reveals agent identity confusion, where direct fusion of latent states entangles decision representations across vehicles. Motivated by this, we propose LACO, a training-free \textbf{LA}tent \textbf{CO}mmunication paradigm that seamlessly adapts pretrained driving models to collaborative settings. LACO introduces Iterative Latent Deliberation (ILD) for latent reasoning, Cross-Horizon Saliency Attribution (CHSA) for communication-efficient information selection, and Structured Semantic Knowledge Distillation (SSKD) to stabilize ego-centric decision making. Closed-loop experiments in CARLA show that LACO notably reduces communication and inference latency while maintaining strong collaborative driving performance.

Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external orchestrator above the LLM, injecting instructions and routing decisions every turn. Recent work has shown this architecture is dominated for procedural tasks by simply providing the procedure in a frontier model's system prompt [Dennis et al., 2026a], at the cost of consuming the context window, requiring a frontier model for every conversation, and exposing proprietary procedures to third-party providers. Compiling the procedure into the weights of a small fine-tuned model -- creating a subterranean agent -- should resolve all of these concerns, and prior work (SimpleTOD, FireAct, SynTOD, WorkflowLLM, Agent Lumos) has shown the technique works. Yet developer adoption has overwhelmingly favored orchestration. We identify three perceived barriers and address each empirically across travel booking (14 nodes), Zoom support (14 nodes, product-specific knowledge), and insurance claims (55 nodes, 6 decision hubs).

Despite recent progress, Biomedical Entity Linking (BEL) with large language models (LLMs) remains computationally inefficient and challenging to deploy in practical settings. In this work, we demonstrate that instruction-tuning of open-source generative models can offer an effective solution when applied at the re-ranking stage of the BEL pipeline. We propose a set-wise instruction-tuning formulation that enables fast and accurate candidate selection. Our method demonstrates strong performance on multiple BEL benchmarks, yielding significant improvements in linking accuracy (3%-24%) while reducing inference time compared to the state-of-the-art. We integrate our generative re-ranker into BeLink, a modular, end-to-end system designed for practical real-world BEL applications.

Deep generative models offer a natural foundation for out-of-distribution (OOD) detection, yet prior work has shown that their assigned likelihoods are notoriously unreliable indicators for in- vs out-of-distribution data. In this paper, we address this problem by leveraging the diffeomorphic and mass-preserving properties of continuous normalising flows. Our analysis shows that OOD samples are mapped to noise samples that are highly atypical under the noise prior in ways not captured by the likelihood. Based on this observation, we propose a new method -- Signal in the Noise (SITN) -- for OOD detection on the single-sample level. SITN requires no access to OOD data, incurs minimal computational overhead, and provides strict control of false positive rates. Comprehensive evaluations through standard benchmarks and synthetic perturbations highlight the method's effectiveness and the absence of the complexity bias inherent to likelihood-based methods.

Behavioral cloning becomes difficult when the same observation admits several valid actions. We study this problem for action-chunking policies and show that different multimodal parameterizations fail in different ways. For latent-variable policies, posterior-prior regularization makes deployment-time sampling more reliable, but excessive regularization removes the action-conditioned information needed to distinguish demonstrated modes. Reducing this regularization can preserve mode information, but then success depends on whether the prior covers the relevant latent regions. For action-space generative policies, multimodality is constrained by the smoothness of the base-to-action transport: a map with small Lipschitz constant cannot assign substantial probability to many well-separated modes. Covering many modes therefore requires either sharp transitions in base space or off-support bridge regions in action space. Experiments on synthetic multimodal tasks and robotic simulation benchmarks support these mechanisms.

Recent advances in Multilingual Large Language Models (MLLMs) have significantly enhanced cross-lingual conversational capabilities, yet modeling culturally nuanced and context-dependent communication remains a critical bottleneck. Specifically, existing state-of-the-art models exhibit a severe pragmatic gap when handling structural variations, regional idioms, and honorific consistencies in low-resource contexts like Bangla. To address this limitation, we introduce a novel, culturally aligned instruction-tuning dataset for \textbf{BangLa Application and DialoguE generation - BLADE} and benchmarking framework comprising $4,196$ meticulously curated interaction pairs. We leverage this resource to systematically fine-tune and evaluate leading open-weight architectures, including DeepSeek-8B and LLaMA-3.2-3B, utilizing parameter-efficient fine-tuning via LoRA adapters in a 4-bit NormalFloat (NF4) quantization framework. Our empirical evaluations demonstrate that models fine-tuned on our dataset yield substantial improvements in structural fidelity and honorific alignment, providing a rigorous benchmark for bridging pragmatic disparities in low-resource multilingual text generation. Code and dataset: https://github.com/ashuvo25/Bangla_Application_LLM/tree/main

Zero-Shot Compositional Image Retrieval (ZS-CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification text, which constitutes the core challenge of the task. Existing methods often suffer from Perception Myopia in a single space, or fall into Logic Drift in iterative collaboration due to the perception ceiling of the underlying retriever. To address this issue, we propose a one-stop hierarchical Perception-to-Deliberation Framework (PDF), which, to the best of our knowledge, is the first to introduce experience self-evolution and Test-Time Scaling Law (TTS) into ZS-CIR. Relying on a hierarchical multi-agent architecture, PDF first utilizes an Intent Routing Manager to dynamically dispatch multi-view Worker perception signals based on modification intents to construct a high-recall candidate pool. Subsequently, the Decision Manager combines a Training-free Reasoning Policy Distillation mechanism with a Tournament-style TTS strategy to achieve self-evolving fine-grained reasoning, yielding the final retrieval results. Experimental results demonstrate that PDF achieves SOTA performance on three benchmark datasets: CIRR, CIRCO, and FashionIQ. This study indicates that experience-driven self-evolution and TTS represent a highly promising and scalable path for achieving zero-shot fine-grained multimedia retrieval. The code will be made publicly available upon acceptance.

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state propagation within a single layer, but their dense evaluation remains expensive. We show that in this setting, learned attention is strongly structured: most mass concentrates in local block-diagonal neighborhoods with a light cross-block residue. Exploiting this, we derive a blockwise evaluation of a resolvent-style operator that keeps within-block interactions exact and routes cross-block interactions through a reduced system. The resulting evaluation is subquadratic in sequence length $O(n^{4/3}d)$ (and $O(n^{7/3})$ when $d\approx n$). On controlled tracking benchmarks, our method matches the dense operator's accuracy while reducing wall-clock time by $12-29\%$ under a standardized measurement protocol, and is up to $2.4 \times$ faster than a compact dense Transformer at comparable exact-match accuracy. We further provide ablations over block size and model capacity, and identify a limitation: performance collapses when the number of simultaneously evolving properties exceeds the number of attention heads.

Evaluating single-concept personalization in text-to-image diffusion requires measuring both concept preservation, which captures identity fidelity to a reference, and prompt following, which captures whether the generated scene matches the prompt. Existing metrics commonly compute these signals using global image or text-image embeddings, such as CLIP-I, DINO, and CLIP-T. We show that such metrics correlate poorly with human perception because they attend to the image as a whole instead of separating the concept subject from the background. We introduce MaSC, a masked similarity metric that uses externally provided foreground concept masks to decompose evaluation into subject-specific concept preservation and background-based prompt following. MaSC computes both scores from frozen SigLIP2 SO400M-NaFlex features: concept preservation is measured by masked max-cosine matching between foreground reference patches and generated-image patches, while prompt following is measured by comparing a background-only pooled image embedding to a subject-stripped prompt embedding. On DreamBench++ human ratings, MaSC achieves Krippendorff alpha = 0.471 for concept preservation, outperforming all tested non-LLM baselines and GPT-4V, and approaching GPT-4o. On ORIDa, a real-photo identity-preservation benchmark across physical environments, MaSC achieves AUC = 0.992, nearly perfectly distinguishing same-subject from cross-subject pairs. Its prompt-following score also outperforms the CLIP-T baseline shipped with DreamBench++. These results show that spatially decomposed aggregation is a strong design principle for evaluating concept-driven generation.

We propose SADGE, a quantitative similarity metric that predicts the performance of synthetic image datasets for common computer vision tasks without downstream model training. Estimating whether a synthetic dataset will lead to a model that performs well on real-world data remains a bottleneck in model development. Existing evaluation metrics (e.g., PSNR, FID, CLIP) primarily measure semantic alignment between real and synthetic images (Appearance Similarity Score). Less commonly, structural similarity between images is considered to assess the domain gap (Geometric Similarity Score). However, to the best of our knowledge there exists no studies that evaluate which similarity metric is the best downstream predictor for a given synthetic dataset. In this paper, we show over a wide variety of different synthetic datasets and downstream tasks that neither appearance nor geometry alone can reliably predict downstream performance; rather, it is their non-linear interplay that dictates synthetic data utility. Specifically, we measure how commonly used Appearance and Geometric Similarity metrics computed between synthetic and real images correlate with downstream performance in object detection, semantic segmentation, and pose estimation. Across five public synthetic-to-real benchmark families and 15 dataset-level variants (79k image pairs), SADGE achieves the strongest association with downstream transfer performance under both linear and rank-based criteria, reaching Pearson r=0.88 and Spearman rho=0.77. We compute for each combination of geometry-based methods and appearance-based approaches SADGE scores across all benchmark families. The best configuration is obtained by fusing DINOv3 appearance similarity with MASt3R geometric consistency through a constrained bilinear interaction, outperforming both the strongest geometry-only baseline and the strongest appearance-only baseline .

While linear manufacturing relies on homogeneous materials and predefined process sequences, circular manufacturing reintroduces used products with heterogeneous and uncertain conditions. This shift demands manufacturing systems capable of handling variable product states, dynamically reconfigurable processes, and the integration of human and machine knowledge. Conventional manufacturing IT architectures, designed for stable structures and deterministic execution, are unable to meet these requirements, as they cannot adequately represent and manage the uniqueness of individual components at runtime. Following a design science methodology for developing a Cyber Physical Production System for circular manufacturing, we derive 14 requirements from five complementary perspectives. Based on these requirements, we design KAPPS, a knowledge-based architecture that uses an ontology-grounded knowledge graph as a unifying data backbone, combined with a semantic interface layer to enable consistent data and information integration, reasoning, and communication across heterogeneous systems and services, turning the knowledge graph from an integration layer into the factories authoritative write-time state. KAPPS incorporates modules for constraint enforcement and event-driven planning, enabling incremental adaptation of execution plans under uncertainty and human-machine knowledge exchange. The applicability of KAPPS is demonstrated through two implemented use cases: (i) Anomaly detection and learning through knowledge graph mediated services and (ii) runtime constraint enforcement in a modular conveyor system. Subsequently, the architecture is evaluated against the 14 requirements (ed. abstract shortened)

Cloud-hosted LLM driver agents provide useful semantic judgments, but their inference latency exceeds stepwise vehicle-control windows. Learned world models predict futures, but they usually keep future generation and action selection inside large coupled loops. We present SteinsGateDrive, a latency-decoupled planner-runtime architecture in which the worldline metaphor from the eponymous story names one plausible consequence of an intervention: the LLM selects counterfactual driving futures before the final control instant, and a runtime reuses the selected forecast only while safety contracts remain valid. The generator builds three world-line roles: alpha nominal ego-conditioned futures, beta interaction counterfactuals around nearby vehicles, and gamma hazard-stress futures such as braking, cut-ins, or blocked corridors. The selected branch becomes a typed StrategicForecast with horizon, validity/abort conditions, fallback, and authority. On a within-subject, matched-seed normal-highway protocol with 10 seeds and 20 steps, GPT-5.4 mini reduces effective lag from +3.07 s at 1-second horizon to -0.01 s at 4-second horizon while preserving the measured no-collision safety boundary. The architecture's safety contribution comes from the atom-predicate runtime check, not from the drift score, which functions as a refresh-frequency knob.

Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of samples in low density regions makes it hard to run evaluations. Synthetic data can fill these gaps, providing us with a way to sample the input space more continuously and improve data coverage for benchmarks. Focusing on the autonomous driving safety-critical case of pedestrian detection in the dark, we show how synthetic low-light samples can be used to better characterize the performance of a state-of-the-art object detection model as a function of the scene illumination. We use a synthetic RAW image augmentation technique to generate low-light samples that match the noise model of the camera sensor. Performance metrics on real and synthetic low-light data are similar, indicating that the AI model finds it hard to distinguish between them.

While large vision-language-action (VLA) models and generative world models (WM) have advanced long-horizon embodied intelligence, their practical deployment remains challenged by uncertainty in learning-based action generation. Low-quality actions may cause physical failures during execution or lead to misleading world-model rollouts with redundant rendering costs. To address this issue, we propose Pre-VLA, a unified runtime verification architecture that performs preemptive action validity assessment before physical execution or world-model imagination. Pre-VLA leverages an efficient multimodal backbone with modality-aware pooling and a lightweight dual-branch head to predict both safety confidence and critic-derived advantage scores for candidate action chunks. To handle severe class imbalance and unstable boundary decisions, we train Pre-VLA with a multi-task objective combining Focal classification, advantage regression, and soft-threshold calibration. During deployment, a dual-mode preemptive resampling scheduler filters low-quality actions and triggers adaptive resampling under a limited computation budget. Experiments on the LIBERO benchmark show that Pre-VLA improves the average closed-loop success rate across four suites from 30.79\% to 37.62\% over RynnVLA-002, reduces task execution steps, achieves 183.9 ms average forward verification time per action chunk, and mitigates error accumulation in world-model rollouts.

Shilling is the use of artificial bids to make competition appear stronger and push prices upward. We study repeated first-price auctions in which shilling affects feedback but not allocation: the learner wins or loses against the real competing bid, but after a loss observes the maximum of the real bid and an independent shill bid. Thus the manipulation changes what the learner observes and hence how it learns to bid, without changing the outcome of the current auction. We analyze regret with respect to the best bid benchmark, assuming that the shill-bid distribution is known. Even then, shilling can mask the real bid, while useful side information appears only through intermittent low-shill events. Our algorithm combines a robust interval-elimination branch, which ignores the shilled report and achieves the dynamic-pricing rate $\tilde{\mathcal{O}}(T^{2/3})$, with an optimistic branch that debiases losing-side reports and exploits the resulting suffix information when it is reliable and achieves the first-price auctions rate $\tilde{\mathcal{O}}(\sqrt{T})$. A validation and racing procedure lets the algorithm use these optimistic updates without knowing the right scale or feedback geometry in advance. We complement the upper bounds with a matching lower bound, up to logarithmic factors, in the single-active-region case. Overall, the results show that even feedback-only shilling can sharply alter the statistical difficulty of repeated bidding.

Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding by combining (i) a lightweight Tiny Recursive Module (TRM) for global reasoning and (ii) axial 1D Transformer encoders that capture long-range dependencies along rows and columns. The model predicts row/column counts, header rows, and separators to construct a grid, then infers rowspan/colspan using ROI-aligned cell features. Across four benchmarks (PubTabNet, FinTabNet, PubTables-1M, and SciTSR), FastTab achieves competitive structure recovery performance while operating at low-latency inference. We further study robustness under pixel-level anonymisation and show an extension to curved separators for camera-captured documents. The source code will be made publicly available at https://github.com/hamdilaziz/FastTab .

Hybrid language models like Jamba mix attention layers with State Space Models (SSMs), creating two memory cache types with opposite profiles: Key-Value (KV) caches grow linearly with sequence length, while SSM states stay fixed per layer. Current inference engines handle this poorly. Unified pools pad SSM states to attention page sizes, wasting up to 7.3x capacity. Static dual pools cannot adapt when prompt distributions shift between requests. We present Asymmetric Virtual Memory Paging (AVMP). The allocator separates the two cache types into physically distinct pools behind a unified virtual address space, and migrates capacity between pools when one runs out. Migration triggers only on allocation failure, keeping behavior deterministic. We evaluate AVMP across 270 synthetic cells plus 60 cells of ShareGPT trace replay on an RTX 3060 12GB. Out-of-Memory events drop 7.6% and request throughput improves 1.83x to 13.3x across synthetic workloads and 2.36x on ShareGPT. All gains hold under paired-bootstrap 95% confidence intervals. A phase-time breakdown reveals two distinct mechanisms: shorter OOM recovery on capacity-pressured workloads, and faster allocation calls on KV-heavy workloads. Implementation is pure Python; Triton integration is future work.

Visual Question Answering (VQA) holds great promise for clinical support, particularly in ophthalmology, where retinal fundus photography is essential for diagnosis. However, ophthalmic VQA benchmarks primarily emphasize answer accuracy, neglecting the explicit visual evidence necessary for clinical interpretability. In this work, we introduce FundusGround, a new benchmark for clinically interpretable ophthalmic VQA with spatially-grounded lesion evidence. Specifically, we propose a three-stage pipeline that collects 10,719 fundus images with 15,595 image-level meticulously annotated lesions. To ensure anatomical consistency and clinical validity, all lesions are spatially localized using the Early Treatment Diabetic Retinopathy Study (ETDRS) grid, enabling standardized mapping to nine clinically meaningful retinal regions. Built upon this structured lesion evidence, 72,706 questions are then generated spanning four formats: open-ended, closed-ended, single-choice, and multiple-choice. We further benchmark multiple general- and medical- large vision-language models using dual metrics for answer accuracy and lesion-level reasoning. The experiments demonstrate that incorporating lesion-level visual evidence consistently improves model performance and transparency, highlighting the necessity of explicit spatial grounding for reliable and explainable ophthalmic VQA.

Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models (MLLMs) have shown promising capabilities, existing benchmarks suffer from critical limitations in scale and realism, lack semantic granularity, and fail to cover diverse document types. To bridge this gap, we introduce ReceiptBench, a large-scale, human-annotated benchmark consisting of 10k diverse receipts, organizing information extraction into four hierarchical sub-tasks: (1) Basic Perception for raw text spotting, (2) Format Normalization for strictly following standardization instructions, (3) Semantic Reasoning for inferring implicit attributes from context, and (4) Structure Parsing for handling nested line items. Furthermore, we propose a two-stage training framework incorporating Metric-Aware Group Relative Policy Optimization (GRPO), which translates rigorous evaluation constraints into reinforcement learning signals to enhance structural consistency. Extensive experiments demonstrate that our method yields state-of-the-art performance, surpassing leading proprietary models on complex reasoning tasks. We release our datasets and code at https://github.com/wwwT0ri/ReceiptBench.

Large language model (LLM) agents still struggle with long-term memory question answering, where answer-supporting evidence is often scattered across long conversational histories and buried in substantial irrelevant content. Existing memory systems typically process memory before future queries are known, then retrieve the resulting units based on similarity rather than their utility for answering the query. This workflow leaves downstream answerers to denoise retrieved candidates and reconstruct query-specific evidence. We present DeferMem, a long-term memory framework that decouples this problem into high-recall candidate retrieval and query-conditioned evidence distillation. DeferMem uses a lightweight segment-link structure to organize raw history and retrieve broad candidates at query time. It then applies a memory distiller trained with DistillPO, our reinforcement learning algorithm for distilling the high-recall but highly noisy candidates into a set of faithful, self-contained, and query-conditioned evidence. DistillPO formulates post-retrieval evidence distillation as a structured action comprising message selection and evidence rewriting. It optimizes this action with a decomposed-and-gated reward pipeline and structure-aligned advantage assignment, gating reward components from validity to quality checks while exposing task-level correctness feedback early and assigning each reward to its responsible output span. On LoCoMo and LongMemEval-S, DeferMem surpasses strong baselines in QA accuracy and memory-system efficiency, achieving the highest QA accuracy with the fastest runtime and zero commercial-API token cost for memory operations.

Accurate wind power forecasting requires reliable uncertainty quantification, yet most existing methods report a single predictive uncertainty that conflates epistemic and aleatoric sources. This paper applies the law of total variance to the joint setting of heteroscedastic neural network regression and Bayesian posterior approximation, deriving an explicit decomposition of total uncertainty (TU) into aleatoric (AU) and epistemic (EU) components. The resulting estimators are compatible with standard posterior-approximation methods and with $β$-NLL training to regulate the mean--variance learning trade-off. A wind power--specific evaluation framework is proposed to validate disentanglement without access to ground-truth uncertainty labels, comprising three modules: controlled synthetic experiments to verify responses to heteroscedastic noise and distribution shift; data-property--driven validation on a real-world wind turbine SCADA dataset; and dataset-size scaling experiments to examine the predicted asymptotic behavior of EU. Across synthetic and real-world experiments, the decomposed AU and EU components respond in theoretically consistent directions to noise structure, distributional shift, and training-scale variation, supporting the theoretical consistency and operational utility of the proposed decomposition and evaluation protocol.

Accurate electricity price forecasting (EPF) is essential for market participants to support operational planning and risk management, yet remains challenging due to strong volatility, nonlinear dynamics, and frequent extreme price spikes. These challenges are particularly pronounced in the Australian National Electricity Market (NEM), where high renewable penetration further increases uncertainty. This paper investigates week-ahead electricity price forecasting and proposes a hybrid KAN+XGBoost framework that integrates Kolmogorov-Arnold Networks (KAN) with tree-based learning. The proposed approach combines the global nonlinear representation capability of KAN with the local robustness of XGBoost to capture both long-term dependencies and short-term price fluctuations. Experiments are conducted on real-world NEM data using an expanding window evaluation strategy. The results demonstrate that the proposed model outperforms benchmark methods, including SARIMAX, Long Short-Term Memory (LSTM), standalone KAN, and XGBoost, reducing MAE by approximately 12% compared to XGBoost and by over 50% compared to a naive baseline. The results suggest that hybrid learning strategies provide an effective and robust solution for electricity price forecasting in highly dynamic electricity markets.

As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code. However, existing benchmarks are limited by the quantity and quality of positive and negative test cases, leading to an overestimation of model capabilities in generating specifications and implementations. To address this, we propose VeriScale, a novel framework driven by the adversarial implementations. It consists of two stages: test-suite expansion to construct diverse and challenging test cases, and test-suite reduction to distill them into compact yet discriminative suites. While VeriScale is general, we instantiate it on Verina to construct VerinaPlus, which expands the original test suites by over 83$\times$, and VerinaLite, a lightweight 14$\times$ variant. Our experiments across eight state-of-the-art LLMs demonstrate that VerinaPlus exposes substantial model weaknesses hidden by the original benchmark, evidenced by sharp score drops on both SpecGen and CodeGen tasks, whereas VerinaLite maintains this discriminative power at a fraction of the evaluation cost. The enhanced benchmarks and source code are publicly available at https://github.com/XiaoyangLiu-sjtu/VeriScale.

Agricultural decision-making increasingly requires multimodal systems that can transform visual observations into reliable, executable actions. However, existing agricultural multimodal benchmarks mainly evaluate final-answer correctness and provide limited support for assessing whether models can use external tools to complete precision-sensitive workflows. In this paper, we introduce AgroTools, a benchmark for evaluating tool-augmented multimodal agents in agriculture. AgroTools contains 539 question-answer instances paired with 1,097 heterogeneous agricultural images, spanning five task families and an executable environment of 14 agricultural tools. Each query is annotated with structured tool-use traces, enabling a dual-view evaluation of both process-level execution quality and outcome-level task success. We benchmark 9 open-source and 4 closed-source multimodal large language models on AgroTools. Results show that current models remain far from reliable in agricultural tool-use settings, with clear bottlenecks in tool planning, argument generation, execution recovery, and final-answer synthesis. We hope AgroTools will support future research on multimodal agents for high-precision agricultural applications. The benchmark and evaluation are available at https://huggingface.co/datasets/AgroTools/AgroTools.

Deciding which sensing capabilities to deploy on an agent in uncertain domains is a fundamental engineering challenge, in which one balances task achievability against the high costs of hardware and processing. This problem has previously been formalized as the Optimal Observability Problem (OOP), based on the well-known Partially Observable Markov Decision Process (POMDP) model for decision-making. This work studies (sub-)symbolic techniques to scale solving of decidable fragments of the OOP, namely the Sensor Selection Problem (SSP) and the Positional Observability Problem (POP). Besides improving the original approach based on parameter synthesis, we develop a new solving method that identifies sensible observation functions via decomposition of POMDPs, improving performance by 3 and 5 orders of magnitude for instance size and runtime, respectively.

Vehicle-to-vehicle (V2V) energy trading enables decentralized peer-to-peer energy exchange among electric vehicles (EVs), reducing grid dependency while monetizing surplus capacity. However, coordinating self-interested EV agents with diverse charging needs and uncertain arrival-departure schedules remains challenging. Existing approaches either require centralized optimization with computational limitations or lack fairness guarantees. This paper integrates Nash Bargaining Solution into Multi-Agent Deep Deterministic Policy Gradient, namely Nash-MADDPG, for incentive-aligned V2V energy trading. Nash bargaining determines efficient bilateral pricing, while Nash-guided price proximity rewards align agent learning toward bargaining-optimal strategies. Evaluation over 30-day continuous operation demonstrates an improvement of 61.6% in social welfare and 62.9% improvement in trading volume over Double Auction, while achieving superior fairness, such as 40.1% improvement in Jain's index. Testing across 6-100 agents over a 30-day horizon with continuous vehicle turnover confirms scalability across population size and empirically stable pricing near the Nash Bargaining benchmark.

We address joint active and passive beamforming for uplink RIS-assisted multi-user multi-stream MIMO systems with joint detection. The coupled design of the receive combiner, block-diagonal user precoders, and RIS phase vector is formulated through a third-order composite channel tensor. Exploiting this multilinear structure, we propose a multi-stream tensor alternating optimization method that updates the combiner, user precoders, and RIS coefficients via low-dimensional tensor projections. Simulations show that the proposed method approaches a multi-start alternating-optimization benchmark while reducing computational complexity and improving large-RIS scaling.

Accurate segmentation of hepatic and portal vessels in contrast-enhanced computed tomography angiography (CTA) remains challenging due to complex vascular topology, peripheral visibility limitations, and acquisition-induced ambiguities. While existing public datasets offer valuable benchmarks, few include clinically realistic annotation constraints. We introduce VEELA (Vessel Extraction and Extrication for Liver Analysis), a rigorously curated liver vessel dataset derived from 40 CTA scans inherited from the CHAOS grand-challenge cohort. All vessels were manually delineated slice-by-slice under multi-expert consensus, using a strict visibility-driven annotation policy and avoiding anatomically inferred interpolation. This design explicitly captures anatomical variability and imaging-related uncertainty. As a continuation of the CHAOS challenge, VEELA enables reproducible cross-benchmark evaluation while extending the scope to fine-grained hepatic and portal vessel segmentation. We further establish a standardized benchmarking framework and analyze complementary evaluation metrics, including topology-aware (clDice), overlap-based (IoU), boundary-sensitive (NSD), and geometry-aware (area, length) measures. Our results demonstrate that different metrics capture distinct aspects of vascular integrity, underscoring the necessity of multi-perspective evaluation for clinically meaningful vessel segmentation. VEELA is publicly released to facilitate reproducible research and support the development of robust vascular segmentation methods. Researchers can access the evaluation metrics, dataset, and submission platform at https://www.synapse.org/Synapse:syn65471967.

Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.

Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogeneous multimodal inputs with strong semantic grounding, while diffusion models synthesize images and videos with photorealistic fidelity. We argue that these two families can be unified through a simple division of labor: MLLMs perform semantic planning, while diffusion models render pixels from high-level semantic guidance and low-level visual features. Building on this idea, we propose Bernini, a unified framework for video generation and editing. An MLLM-based planner predicts the target semantic representation directly in the ViT embedding space, and a DiT-based renderer synthesizes pixels conditioned on this plan, augmented by text features and, for editing, source VAE features for detail preservation. Because semantics serve as the interface, the planner and renderer can be trained separately and only lightly co-trained, preserving the pretrained strengths of both components while keeping training efficient. To better handle multiple visual inputs, we introduce Segment-Aware 3D Rotary Positional Embedding (SA-3D RoPE), and further incorporate chain-of-thought reasoning in the planner to better transfer understanding into generation. Bernini achieves state-of-the-art performance across a wide range of video generation and editing benchmarks, with the MLLM's pretrained understanding translating into strong generalization on challenging editing tasks.

Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do not by themselves produce research judgment. We analyze where current systems lose trial experience: weak evidence becomes prose, pilot signals become broad claims, memory remains textual, and recurring process failures do not change later behavior. We introduce Sibyl-AutoResearch, a self-evolving AutoResearch framework built around Scientific Trial-and-Error Harnesses. A harness lets agents run bounded trials, preserve positive and negative outcomes, and route lessons into later planning, validation, claim scope, scheduling, critique, writing, and harness repair. We formalize this through two auditable conversion units: trial-to-behavior conversion, which links trial signals to later research actions, and trial-to-harness-behavior conversion, which links recurring process failures to system updates. We implement the framework in SIBYL, a file-backed autonomous research system that exposes the state, roles, memory, gates, and artifact traces needed to inspect these conversion paths. A retrospective audit identifies eight high-confidence conversion events, with a median latency of one iteration and a maximum latency of three iterations. A recovered-failure registry further shows how five naturally occurring failure classes, including duplicate results, stale numbers, and unsupported statistics, were blocked, downgraded, or routed into later repair. These traces do not establish a comparative performance claim; they show that the proposed conversion units are recoverable from realistic autonomous-research workspaces. The SIBYL framework and system are available at https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem.

The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts.Current KV Cache eviction has become an important research direction; however, existing methods based on fixed Soft Tokens (e.g., Judge Q) rely on a static parameter set as the query to evaluate the importance of KV pairs, so they cannot adapt dynamically to different input prompts, and they cannot precisely capture complex and changing task relevance.Also, evicted KV pairs are discarded permanently, so this causes irreversible information loss and context breaks. To address this problem, we propose Meta-Soft, a dynamic compression framework based on probe-driven context integration. Specifically, we build a meta-library with a learnable orthogonal basis matrix $\mathcal{L}$, and we use a selector network with Gumbel-Softmax to produce differentiable sparse combination weights, so we dynamically synthesize the most targeted $k$ Soft Tokens from the input prompt features.We append these Soft Tokens to the end of the input sequence to probe key information. We also introduce an attention-flow based integration mechanism, which redistributes the semantic information of removed tokens into retained tokens, and this keeps the dropped context information effectively.Experiments on multiple datasets show that our method outperforms existing state-of-the-art eviction methods and provides a new solution for KV Cache compression.

Land Use Land Cover (LULC) classification is essential for national 3D mapping, geospatial analysis, and sustainable planning. Multispectral (MS) LiDAR provides synchronized spatial-spectral information, and deep learning (DL) enables 3D point cloud semantic segmentation; however, adoption is limited by the lack of publicly available urban and suburban MS LiDAR datasets aligned with National Mapping and Cadastral Agencies (NMCAs) classification schemes. This study addresses these gaps by introducing L1 and L2 NMCA-aligned LULC classification schemes and a new benchmark MS LiDAR dataset. We evaluate seven state-of-the-art DL models and perform spectral ablation studies at both levels of detail. Results show that Point Transformer V3 achieves the best performance, with mIoU of 79.4% (L1, 8 classes) and 58.9% (L2, 20 classes) using a dual-wavelength LiDAR system (532 nm and 1064 nm). Ablation results show that multispectral information improves performance over geometry-only inputs, with gains of 1.1 percentage points at L1 and 7.8 points at L2. These results highlight the value of LiDAR reflectance for fine-grained material discrimination and support the evolution of NMCA LULC schemes toward higher semantic detail. The Loosdorf-MSL dataset contributes a new benchmark for consistent national and international LULC mapping.

Reasoning capability has significantly advanced complex logical inference and robotic decision-making in general domains. However, its potential in the Artificial Intelligence (AI) copilot robot-particularly implemented based on the Vision-Language-Action (VLA) model-remains unexplored in endoscopic surgery. Effective reasoning should enable AI copilot robots to integrate multimodal cues, interpret surgical intent, and infer hidden tissue dynamics, thereby alleviating intraoperative uncertainty and cognitive burden on surgeons. Properly implemented, reasoning-driven autonomy can transform AI copilot robots from reactive executors into cognitive collaborators, enhancing precision, safety, and sustainability in clinical practice.

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn, stateless behaviors, overlooking the expanded attack surface inherent in stateful, multi-turn interactions and dynamic tool invocations. In this paper, we propose a novel, multi-dimensional evasion framework targeting LLM-based agent systems. We introduce three stealthy attack vectors: (1) Temporal evasion, which fragments malicious payloads across sequential interaction turns; (2) Spatial evasion, which conceals payloads within complex external artifacts that evade standard LLM parsing mechanisms; and (3) Semantic evasion, which obscures malicious intents beneath benign contextual noise. To systematically quantify these threats, we construct A3S-Bench, a comprehensive benchmark comprising 2,254 real-world agent execution trajectories. Evaluating a standard agent framework separately integrated with 10 mainstream LLM backbones against 20 practical threat scenarios, we demonstrate that our evasion framework elevates the average risk trigger rate from a 28.3\% baseline to 52.6\%. These findings reveal systemic, architecture-level vulnerabilities in current autonomous agent systems that existing defenses fail to address, highlighting an urgent need for defense mechanisms tailored to the unique threats.

Conflict Mitigation (ConMit) is a crucial part of intelligent network control in Open Radio Access Networks (O-RAN). In this paper, we propose a method named ACCoRD to resolve detected control conflicts in Near-Real Time RAN Intelligent Controller using a Conflict Resolution (CR) Agent with an Artificial Neural Network (ANN) trained with a reinforcement learning algorithm PPO-Clip. The implemented ANN analyzes data about the network and conflicting control decisions to infer optimal CR actions. The CR Agent gathers feedback from the network after each resolved conflict to assess its efficiency and adjust the ANN's weights during batch training. The evaluation of the proposed approach is based on simulation data. A new methodology for evaluating CR solutions is proposed. Results show that the proposed ANN-based method improves on the efficiency of rule-based approaches by significantly reducing negative network events caused by conflicting control decisions in medium and high traffic scenarios.

Integrating new data into knowledge graphs (KG) typically involves different tasks that are executed within workflows or pipelines There are many possible pipelines for a specific integration problem but there is not yet a general approach to evaluate the overall quality and performance of such pipelines to be able to determine the best choices. We therefore propose a new benchmark KGI-Bench to evaluate integration pipelines that ingest different kinds of input data into an existing KG. We evaluate pipelines by analyzing their output, i.e., the updated KG, with the three complementary quality metrics coverage, correctness and consistency. We also provide benchmark datasets (seed KG, overlapping input data of three formats, reference KG as a ground truth) for the movie domain. To demonstrate the applicability and usefulness of the proposed benchmark, we comparatively evaluate 12 pipelines and analyze their behavior across different input data formats and design choices.

Scientific evidence often spans instruments, databases, and disciplines, so no single source records the full phenomenon. This makes it difficult to determine when coordinated AI agents add value over simpler scientific workflows. We evaluate this question with a cross-domain benchmark spanning four scientific tasks: mapping molecular structure into musical representations, detecting historical paradigm shifts in science, identifying vector-borne disease emergence, and vetting transiting-exoplanet candidates. Each case uses a frozen evaluation panel, predefined scoring protocols, explicit baselines, ablations or null controls, and stated limitations. The results define three operating regimes. When different disciplines each capture only part of the phenomenon, cross-channel composites improve over single-channel baselines: climate-vector emergence reaches AUROC 0.944 and exoplanet vetting reaches AUROC 0.955. However, the exoplanet workflow is effectively tied with a strong combined-summary baseline, showing that decomposition does not always improve top-line performance. When one signal dominates, as in paradigm-shift detection, coordination mainly improves interpretation and traceability. For molecular sonification, the gain is representational rather than predictive. ScienceClaw x Infinite provides the auditable artifact and provenance layer for this evaluation. The benchmark therefore assigns value to coordination only when the corresponding performance, provenance, or representation claim is supported by explicit comparators.

Text-based counseling is an important interface for AI mental-health support, where transcripts may be used to monitor depression severity and flag sessions requiring timely human review. However, robust PHQ-8 prediction across session regimes remains challenging: fine-tuning-based methods can exploit richer supervision but may generalize poorly under data scarcity, while prompt-based LLM methods are data-efficient but usually treat each transcript holistically and provide limited support for longitudinal context. We study robust depression tracking from counseling transcripts across single-session and multi-session regimes. We introduce LongCounsel, a multi-session counseling dataset with session-level PHQ-8 supervision for evaluating repeated-session tracking under partial symptom disclosure and cross-session continuity. We further propose EmoTrack, a PHQ-8 prediction framework that combines LLM-extracted clinical signals with frozen turn-level semantic embeddings and trains symptom-specific predictors over the resulting transcript representation. When prior sessions are available, EmoTrack can further incorporate them through compact cross-session memory. Experiments on LongCounsel and DAIC-WOZ show that EmoTrack achieves a clear gain on the real single-session benchmark, including a 13.5% relative MAE reduction over the strongest DAIC-WOZ baseline, and remains competitive with the strongest longitudinal baseline on LongCounsel.

We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive behaviors when targets fall outside the camera's field of view. SOMA addresses this limitation by equipping VLAs with a persistent spatial memory constructed from multi-view observations acquired via a movable head camera, enabling reasoning beyond the current visual frustum. The framework consists of three components: Spatial Memory Construction, which aggregates angular-wise observations into a unified spatial-semantic representation through scanning; Dynamic Memory Refinement, which maintains global consistency over time; and Contextual Memory Retrieval, which activates instruction-relevant spatial cues during manipulation. We evaluate SOMA on five challenging real-world out-of-vision manipulation tasks, including multi-step and dual-arm scenarios where target objects are initially invisible. Experimental results show that SOMA not only improves task success rates, but also induces qualitatively different manipulation behaviors, with faster target localization, reduced viewpoint search, and near one-shot grasping under partial observability. Additional experiments on RoboCasa GR1 and SimplerEnv further validate the effectiveness of SOMA's memory design under conventional fully observable settings. Code will be released soon.

Whole-body Humanoid-Object Interaction (HOI) is bottlenecked by the scarcity of high-fidelity 3D data. While video generative priors offer a promising alternative, existing methods suffer from \textit{Representation Misalignment} due to their reliance on geometric priors (e.g., explicit CAD models), and \textit{Retargeting Complexity} arising from intensive morphing and morphological mismatch. We propose Imagine2Real, a zero-shot HOI framework for flexible, geometry-free interaction. To resolve misalignment, we formulate robot and object motions as unified 4D point trajectories. To overcome retargeting complexity, our Keypoints Tracker tracks only sparse critical points (base, hands, and object), entirely bypassing the error-amplifying retargeting process. To maintain natural gaits despite these sparse signals, we utilize the latent space of a Behavior Foundation Model (BFM) as the tracker's search domain. Using a progressive training strategy, Imagine2Real learns robust behaviors with simple tracking rewards, enabling zero-shot physical deployment within a motion capture(mocap) system.

Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores the Key-Value (KV) of the historical tokens via LLM prefill and enables more efficient streaming QA. However, existing methods cache every one or two frames, causing redundant memory usage and losing fine-grained spatial details within frame or temporal contexts across frames. This paper proposes MuKV, a method that features a multi-grained KV cache compression module and a semi-hierarchical retrieval approach to improve both efficiency and accuracy for long streaming VideoQA. For the offline KV cache, MuKV extracts visual representations at patch-, frame-, and segment-levels. The multiple levels of granularity preserve both local cues and global temporal context, while maintaining efficiency with a dual signal token compression mechanism guided by self-attention and frequency. For online QA, MuKV designs a semi-hierarchical retrieval method to retrieve relevant KV caches for answer generation. Experiments on long-streaming VideoQA benchmarks show that MuKV significantly improves answer accuracy, without sacrificing memory and online QA efficiency. Moreover, our compression mechanism alone brings consistent benefits across answer accuracy, memory, and QA efficiency over baselines, showcasing highly effective contribution.

Idioms pose a fundamental challenge for language models, as their meaning cannot be inferred from surface form alone. Understanding such expressions, therefore, requires semantic abstraction beyond lexical overlap. We introduce IdioLink, a retrieval benchmark designed to test whether models can link idiomatic expressions to conceptually equivalent meanings expressed in literal or paraphrased forms. IdioLink comprises 10,700 documents and 2,140 queries, spanning 107 idioms with both literal and figurative uses. Each document and query is annotated with spans that convey the core meaning. Evaluating strong embedding baselines (e.g., BGE, E5, Contriever, and Qwen), we show that current models struggle to retrieve equivalent meanings across divergent surface realizations, relying instead on topical and shallow semantic cues. IdioLink exposes key gaps in idiom-aware semantic retrieval and provides a challenging testbed for future models.

Low-index transparent conducting oxides have attracted significant attention because ultrafast optical excitation in these materials can induce exceptionally large temporal index gradients. Due to this remarkable nonlinear optical behaviour, this material platform enables sub-picosecond, all-optical control of photon energy and momentum, with growing relevance for integrated photonics, quantum optics, and optical computation. Owing to their hybrid electronic structure, transparent conductors exhibit both intraband and interband nonlinearities, previously accessed using dual-colour excitation with near-infrared and ultraviolet pumps. Here, we show that both excitation regimes can be activated using a single, intense near-infrared pump. Above a threshold intensity, the pump drives hot-electron intraband dynamics while simultaneously generating higher harmonics that trigger interband excitation. The interplay of these two effects sharpens the temporal features of the recorded transmissivity which in turn substantially broadens the effective material bandwidth. Finally, by comparing linear and circular pumping conditions, we further demonstrate that the observed interband nonlinearities originate from harmonic generation rather than from direct multiphoton absorption. Our results provide key insights into the strong-field optical response in these time-varying photonic materials, opening new frontiers for the ultra-fast manipulation of photons in both classic and quantum regimes.

Aspect-based sentiment analysis (ABSA) requires models to bind sentiment evidence to the correct aspect, making it a natural testbed for fine-grained structural reasoning. We introduce GHI, a Graphormer-over-Conditioned-Hypergraph-Incidence framework that is designed as an incidence-based structural reasoning layer built on a bipartite topology. GHI represents diverse linguistic and semantic evidence as token--hyperedge incidence relations, allowing different structural signals to be incorporated through a unified interface. Extensive experiments on six standard ABSA benchmarks show that GHI outperforms all baselines on the SemEval domains, and multi-seed evaluations show stable improvements over strong DeBERTa. Further experiments show that with only 247M parameters, GHI approaches the performance of 11B Flan-T5 based methods on the ISE benchmark. Moreover, it demonstrates strong robustness on the challenging ARTS datasets, maintaining highly competitive performance where traditional models degrade. These results demonstrate that compact structural reasoning remains a valuable alternative to scale-driven approaches for fine-grained tasks.

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood. The dominant response treats this as a reward-design problem. We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted. Through controlled experiments on a Python output-prediction task and a deterministic-DSL twin task that strips pretraining priors, output ambiguity, and executor noise, we find the two levers are asymmetric. A strict gate is sufficient for stability under every reward variant we test, including a self-consistency reward with no access to ground truth; while no reward variant is sufficient once the gate is removed. This asymmetry exposes a counter-intuitive coupling we call the Grounded Proposer Paradox: a proposer with ground-truth access accelerates collapse faster than an ungrounded one when paired with a self-consistency solver, by concentrating training on clean tasks that form the fastest path to a spurious self-consistent attractor. Replacing the binary gate with a continuous strictness parameter $\varepsilon$ further reveals a two-stage phase transition: training-side metrics decouple at low $\varepsilon$, while validation accuracy holds until $\varepsilon$ is much higher. Data-level gating, not reward calibration, is the binding constraint on self-play stability.

Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios by flexibly selecting tools and determining removal orders. However, their zero-shot planning often fails without experience, necessitating severe trial-and-error overhead to achieve satisfactory outcomes. Currently, two paradigms are employed to address this issue, yet a dilemma persists: Training-based methods embed intrinsic experience into parameters, achieving high inference efficiency but lacking compatibility with new tools or degradation. In contrast, training-free methods utilize explicit experience storage for compatibility but still incur trial-and-error overhead due to naive experience. To resolve the dilemma, we propose EvoIR-Agent, which first systematically formulates the experience components of a training-free image restoration agent. Subsequently, a hierarchical experience pool is constructed, which enables coarse-to-fine guidance for diverse tools and removal orders. Furthermore, a self-evolving mechanism is introduced to update the pool from scratch using accumulated records, thereby greatly improving performance and efficiency. Extensive experiments reveal that EvoIR-Agent achieves a significant lead in the full reference metrics and yields a remarkable Pareto-optimal balance between performance and efficiency compared to the state-of-the-art methods.

Safety has been a major concern when deploying deep reinforcement learning algorithms in the real world. A promising direction that ensures that the learned policy does not visit unsafe regions is to learn a \emph{barrier function} along with the policy. A barrier is a function from states to reals that assigns low values to the initial states, high values to the unsafe states, and decreases in expectation on each transition; such a function can be used to bound the probability of reaching unsafe states. Previous attempts learned a barrier function directly from exploration data, but this required either large amounts of data or restrictions on the system dynamics. In this paper, we show how kernel embeddings can be used to learn barrier functions during deep reinforcement learning for stochastic systems with unknown dynamics. Our algorithm, \emph{kernel-based safe exploration (KBSE)}, learns an optimal policy and a barrier simultaneously during exploration. The barriers are computed iteratively, represented as conditional mean embeddings, and provide better probabilistic safety guarantees with more exploration. The exploration algorithm uses the learned barrier functions to identify safety violations. In the case of violation, it intervenes to modify the unsafe action to a safe action, thereby ensuring that the exploration is restricted to actions that bound the probability of reaching unsafe states. We evaluate KBSE on several complex continuous control benchmarks. Experimental results establish our new algorithm to be suitable for synthesizing control policies that are probabilistically safe without degradation in reward accumulation.

The Thousand Brains Theory (TBT) and its open-source Monty framework model object recognition through sensorimotor inference -- identifying objects by actively moving a sensor across their surface and building evidence contact by contact. The current implementation encodes each contact as a dense floating-point vector. While Monty tracks inter-step displacement and accumulates evidence across contacts, it treats the feature activation pattern at each contact as an unordered set - the directional sequence in which features are encountered carries no representational weight. In TBT, the sequence of contacts carries spatial meaning: knowing that feature A was felt before feature B during a left-to-right sweep tells you something about where A and B sit on the object. Dense vectors discard this ordering. We propose replacing dense vectors with rank-order spike packets: each contact produces a brief burst of neural events where the most strongly activated neuron fires first. The time gap between successive bursts implicitly encodes sensor displacement without explicit coordinate calculations. A biologically motivated learning rule (STDP) encodes traversal direction into synaptic weights. A learnable parameter lambda adjusts reliance on earlier versus recent contacts, adapting to each object's geometry. We derive three testable predictions and specify an implementation of four components in approximately 450 lines of NumPy. Three synthetic experiments confirm the core claims: temporal coding achieves perfect discrimination accuracy on objects with identical features in different spatial arrangements, where dense accumulation performs at chance; temporal coding maintains a 30-50 percentage point advantage across all tested noise levels; the adaptive lambda converges to distinct values, reflecting object geometric complexity. End-to-end evaluation on Monty's YCB benchmark is left for future work.

In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Augmented Generation (RAG) framework applied to Khmer agricultural documents. The document chunks are encoded using the BGE-M3 multilingual embedding model and retrieved using the FAISS library. Performance is evaluated using four metrics: Average Retrieval Score (L2 distance), Answer Relevance, Khmer Coverage, and Khmer Intersection over Union, all measured against ground-truth question-answer pairs. For evaluation, we perform 5-fold cross-validation over 18 question-answer pairs. We observe the best performance for the character-based Recursive chunking method with a chunk size of 300 characters, achieving the lowest L2 distance (0.4295 +- 0.0461), highest Answer Relevance (0.8663 +- 0.0199), and highest Khmer IoU (0.6441 +- 0.0347). A paired t-test shows a statistically significant improvement over the Sentence-Based chunking method in L2 distance (p = 0.0121). These results highlight the importance of segmentation granularity and structural preservation for optimizing dense retrieval in morphologically complex, low-resource languages such as Khmer.

In this paper, we show that high-performing embedding models organize their embedding spaces in a consistent way. We evaluate 25 contemporary embedding models on five MTEB tasks spanning four diverse task categories (retrieval, bitext mining, pair classification, and summarization) in both English and multilingual settings, and reveal that nearest-neighbor overlap and magnitude differences in independent component analysis (ICA) between paired text instances strongly correlate (even up to 0.97) with performance on the given task. Ultimately, we show that embedding tasks display varying degrees of linearity and reliance on retention of local information. Our results further the understanding of embeddings, their relation to model performance, and shed light on possible future training objectives and optimizing conditional embeddings.

Achieving high levels of surgical skill through effective training is essential for optimal patient outcomes. Automated, data-driven skill assessment holds significant potential to improve surgical training. While machine learning-based methods are increasingly popular for assessing skills in minimally invasive surgery, their application to open surgery remains limited. We present the results of a dedicated MICCAI challenge designed to benchmark and advance vision-based skill assessment in open surgery. The challenge dataset comprises videos of an open suturing training task recorded with a static GoPro camera in a dry-lab setting, with instrument trajectories available in addition to the primary video modality. The OSS Challenge was hosted over two consecutive years, comprising two and three independent tasks, respectively: (1) classifying skill level into four classes, (2) predicting the full Objective Structured Assessment of Technical Skills across eight categories, and (3) tracking hands and surgical tools. Participants submitted diverse solutions including deep learning-based video models, tracking-driven methods, and hybrid approaches. General-purpose spatiotemporal video models consistently achieved the strongest performance, though conceptually diverse approaches reached competitive levels when well-executed. Predicting fine-grained OSATS scores remains challenging but benefits substantially from increased training data. Keypoint tracking proves difficult given frequent occlusions and out-of-frame instances, limiting current applicability for motion-based skill analysis. This work benchmarks innovative and diverse solutions for surgical skill assessment, highlighting both the promise and current limitations of video-based evaluation in open surgery and identifying critical directions for advancing automated skill assessment toward clinical impact.

Blind image quality assessment (BIQA) for ultrahighdefinition (UHD) images remains challenging because native-resolution inference is computationally expensive, whereas aggressive resizing or isolated cropping may suppress scale-sensitive distortions and weaken the relationship between local artifacts and global scene context. This paper aims to improve UHD-BIQA by explicitly modeling the structural dependencies among sampled image regions rather than treating them as independent views, and a graph representation learning framework UHD-GCN-BIQA is proposed. The framework samples aspect-ratio-aligned patches from each UHD image, encodes them as graph nodes, and constructs a hybrid k-nearest-neighbor graph using spatial proximity and feature similarity. Residual graph convolution is used to propagate contextual information across regions, and gated attention pooling aggregates patchlevel evidence into an imagelevel quality prediction. An exponential moving average normalized multiobjective loss function is adopted to stabilize the joint optimization of regression, correlation, and ranking objectives. Experiments on the UHD-IQA benchmark show that UHD-GCN-BIQA achieves PLCC = 0.7784, SRCC = 0.8019, and RMSE = 0.0519, obtaining competitive correlation performance and the lowest RMSE among the compared methods. These results indicate that graph-based region relation modeling is effective for UHD image quality assessment, particularly for improving absolute quality score estimation under high-resolution visual content.

Recent feed-forward 3D gaussian splatting methods have made dramatic progress on individual aspects of 3D scene reconstruction, but no existing method jointly addresses dynamic content, multi-view input, and unknown camera poses in a single feed-forward pass. Methods that handle dynamics either require accurate camera poses or accept only monocular input; pose-free multi-view methods address only static scenes; and per-scene optimization methods bridge some of these gaps but at minutes-to-hours cost per scene. We introduce NoPo4D, the first feed-forward system that addresses this empty quadrant. Building on a pretrained geometry backbone and recent 4D Gaussian frameworks, NoPo4D introduces a velocity decomposition that splits Gaussian motion into per-pixel image-plane shifts and depth changes, allowing direct supervision from pseudo ground-truth optical flow on the 2D component. This sidesteps both the differentiable rendering that couples prior posed methods to pose accuracy and the 3D motion ground truth that prior pose-free methods require. The system is rounded out by a bidirectional motion encoder for cross-view and cross-frame feature aggregation, and view-dependent opacity that mitigates cross-view and cross-timestep Gaussian misalignments. On four multi-view dynamic benchmarks, NoPo4D consistently outperforms prior feed-forward baselines, and with an optional post-optimization stage surpasses per-scene optimization methods, while running orders of magnitude faster.

Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions and visual observations to actions in a single forward pass. While conceptually simple, this formulation entangles instruction comprehension, spatial scene understanding, and motor control within a single learning objective. As a result, the action expert must implicitly relearn cognitive and perceptual capabilities already present in the pretrained VLM, which can limit both learning efficiency and generalization. We introduce AVP (Action with Visual Primitives), an end-to-end architecture that implements this visual-primitive-centric interface: the VLM infers the next-stage target and emits visual-primitive tokens that condition a flow-matching action expert, with supervision derived from end-effector kinematics. Real-robot experiments on general pick-and-place tasks show that AVP improves the success rate by 27.61% over pi_0.5 and outperforms other recent methods, with consistent gains in data efficiency, spatial-compositional generalization, and object-level transfer.

The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on monolithic LLMs and fixed logic to interface with these skills. This gives rise to a critical bottleneck: different LLMs offer distinct advantages across diverse domains, yet current frameworks fail to exploit the complementary strengths of models and skills, thereby limiting their performance on downstream tasks. In this paper, we present Maestro (Multimodal Agent for Expert-Skill Targeted Reinforced Orchestration), a Reinforcement Learning (RL)-driven orchestration framework that reframes heterogeneous multimodal tasks as a sequential decision-making process over a hierarchical model-skill registry. Rather than consolidating all knowledge into a single model, Maestro trains a lightweight policy to dynamically compose ensembles of frozen expert models and a two-tier skill library, deciding at each step whether to invoke an external expert, which model-skill pair to select, and when to terminate. The policy is optimized via outcome-based RL, requiring no step-level supervision. We evaluate Maestro across ten representative multimodal benchmarks spanning mathematical reasoning, chart understanding, high-resolution perception, and domain-specific analysis. With only a 4B orchestrator, Maestro achieves an average accuracy of 70.1%, surpassing both GPT-5 (69.3%) and Gemini-2.5-Pro (68.7%). Crucially, the learned coordination policy generalizes to unseen models and skills without retraining: augmenting the registry with out-of-domain experts yields a 59.5% average on four challenging benchmarks, outperforming all closed-source baselines. Maestro further maintains high computational efficiency with low latency. The source code is available at https://github.com/jinyangwu/Maestro.

Latent world models can contain the state needed for control, yet their terminal-cost interface can expose the planner to the wrong decision-relevant information. In common latent MPC, candidate sequences are ranked by Euclidean distance between predicted terminal and goal latent states; this assumes that raw latent distance weights reachability-relevant variables correctly. We propose trajectory reachability metrics (TRM), a post-hoc terminal-ranking method for fixed latent world models. TRM trains a small pairwise head from logged trajectory structure and uses it as a replacement or hybrid cost; the encoder, dynamics, sampler, optimizer, and evaluation manifests remain fixed. The key design choice is horizon-aware supervision: the metric is trained on broad, balanced temporal separations to match the long-horizon terminal candidate ranking problem. On a hard TwoRoom benchmark, raw latent planning with LeWorldModel (LeWM) reaches 7.0% success, while full-horizon TRM reaches 97.0%; shuffled temporal-label controls stay at 0.0%. The same recipe improves a PLDM baseline from 32.7% to 84.0% across three seeds, and a short-horizon TRM variant reaches only 35.0% with the 100,000 pair budget. In TwoRoom, we provide mechanistic evidence for why TRM works: XY position is linearly decodable (R^2=0.998), yet raw latent MSE misranks candidates; the XY-probe rowspace accounts for less than 1% of terminal-goal latent MSE but carries most candidate-quality signal; and SCSA audits show that TRM improves the ordering and selected endpoint seen by the planner. On PushT go50/go75, TRM-style task-state metrics improve SCSA ranking and selected final distance more cleanly than closed-loop success, motivating auxiliary hybrid costs in continuous manipulation. TRM is the planner-facing repair, and audits explain when terminal reachability metrics should replace or augment raw latent proximity.

Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation shows that LLM-authored skills deliver $+0.0$pp over no-skill baselines while human-curated ones deliver $+16.2$pp: the bottleneck is not skill authoring but lifecycle management. We introduce \textbf{Ratchet}, a single-agent loop in which a frozen LLM writes, retrieves, curates, and retires its own natural-language skills. Ratchet integrates four candidate hygiene mechanisms: outcome-driven retirement, a bounded active-cap, meta-skill authoring guidance, and pattern canonicalisation. On MBPP+ hard-100 with Claude Opus 4.7, Ratchet lifts held-out pass@1 from a $0.258 \pm 0.047$ baseline to a late-window rolling mean of $0.584$ (peak $0.658 \pm 0.042$) across 100 rounds and 3 seeds, a $+0.328 \pm 0.018$ rolling-mean gain where the no-skill control drifts at $+0.002 \pm 0.005$; the same recipe transfers to an agentic solver on SWE-bench Verified ($+0.22$ peak lift over 20 rounds). Eight ablations (A1--A8) reveal that the minimal working recipe is smaller than our design suggests: retirement and the meta-skill authoring prior are load-bearing, while explicit deduplication (canonicalisation, cover-guard) is subsumed by the meta-skill itself. A non-divergence proposition shows that bounded cap and retirement threshold together prevent expected performance from drifting below the no-skills floor.

Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements of short-drama generation: (1) narrative pacing, resulting in weak hooks, insufficient escalation, and unattractive endings; (2) spatial consistency, leading to drifting scene layouts and inconsistent character positions across clips; and (3) production-level quality control, requiring extensive manual review and correction across script and visual stages. We present One Sentence, One Drama, a hierarchical multi-agent framework that transforms a user's single-sentence idea into a fully produced short drama through structured intermediate modules and iterative refinement. Our approach is built upon three key components: (1) a multi-agent debate-based story generation module that enforces short-drama pacing and narrative coherence; (2) a 3D-grounded first-frame generation mechanism that establishes a shared spatial reference for consistent character positioning and scene layout across clips; and (3) multi-stage reviewer loops that perform comprehensive error detection and targeted revision across script, visual, and video generation stages. We also introduce scene-level BGM matching and scene transition planning to improve the audience's immersive experience. To systematically evaluate this task, we introduce Short-Drama-Bench, a benchmark that extends standard video quality metrics with short-drama-specific criteria. Experimental results demonstrate that our method significantly outperforms existing pipelines in narrative quality, cross-clip consistency, and overall viewing experience.

In recent years, large language models have shown substantial potential in psychological support tasks. However, existing psychological counseling data mostly rely on single-turn question answering or short multi-turn dialogues, making it difficult to characterize how college students' psychological distress accumulates, interacts, and gradually evolves over long periods within campus life events. To address this issue, this paper proposes Psy-Chronicle, a structured data-generation framework for synthesizing long-horizon campus psychological counseling dialogues. We generate a semester-spanning temporal stress event graph to model the chronological order and evolutionary dependencies among campus stress events. Through interactive simulation between a student agent and a counselor agent, together with a structured memory integration mechanism, Psy-Chronicle generates long-horizon dialogues with continuity across counseling sessions. Based on Psy-Chronicle, we construct and open-source CPCD, a Chinese long-horizon dialogue dataset for college psychological counseling, containing 100 student profiles, 90,000 counseling dialogues. We further build CPCD-Bench to evaluate models' long-horizon campus counseling capabilities from three dimensions: session-level response, long-horizon memory recall, and temporal-causal reasoning. Experimental results show that CPCD effectively improves session-level response generation and long-horizon memory recall for models with the same base architecture. Meanwhile, improvements in temporal-causal reasoning remain limited, indicating that event-chain organization and causal explanation are key challenges in long-horizon psychological counseling modeling. The related code and data are available at: https://github.com/EdwinUSTB/Psy-Chronicle

Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensitivity of conventional cameras. In this work, we explore gait recognition using event cameras, which offer microsecond temporal resolution and high dynamic range, naturally capturing robust dynamic cues and suppressing static noise. Existing event-based approaches typically aggregate event streams into event images over long time windows, thereby discarding fine-grained motion dynamics critical for gait recognition. Therefore, we propose \textbf{EventGait}, an end-to-end dual-stream framework that separately models motion and shape while preserving the advantages of events. Our dynamic stream leverages a Mixture of Spiking Experts (MoSE) with diverse neuron constants for robust dynamic perception across complex motion and illumination scenes, while the static stream learns dense shape representations via Cross-modal Structure Alignment (CroSA) with large vision foundation models. To address the absence of large-scale event-based gait datasets, we introduce a synthesis pipeline and release two new benchmarks: SUSTech1K-E and CCGR-Mini-E. Extensive experiments have shown that event-based gait recognition not only achieves results comparable to camera-based gait recognition under normal conditions but also significantly outperforms it in low-light scenarios. Our approach sets a new state of the art on both synthesized and real-world event-based gait benchmarks, highlighting the robustness and potential of event-driven gait analysis. The code and datasets are released at https://github.com/QUEAHREN/EventGait.

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the presence, structure, or horizon of planning, these systems dramatically increase reasoning length, yielding inefficient token use without reliable accuracy gains. We argue efficient agentic reasoning benefits from decomposing decision-making into three systems: simulative reasoning (System II) grounding deliberation in future-state prediction via a world model; self-regulation (System III) deciding when and how deeply to plan via a learned configurator; and reactive execution (System I) handling fine-grained action. Simulative reasoning provides unified planning across diverse tasks without per-domain engineering, while self-regulation ensures the planner is invoked only when needed. To test this, we develop SR$^2$AM (Self-Regulated Simulative Reasoning Agentic LLM), realizing both as distinct stages within an LLM's chain-of-thought, with the LLM as world model. We explore two instantiations: recording decisions from a prompted multi-module system (v0.1) and reconstructing structured plans from traces of pretrained reasoning LLMs (v1.0), trained via supervised then reinforcement learning (RL). Across math, science, tabular analysis, and web information seeking, v0.1-8B and v1.0-30B achieve Pass@1 competitive with 120-355B and 685B-1T parameter systems respectively, while v1.0-30B uses 25.8-95.3% fewer reasoning tokens than comparable agentic LLMs. RL increases average planning horizon by 22.8% while planning frequency grows only 2.0%, showing it learns to plan further ahead rather than more often. More broadly, learned self-regulation instantiates a principle we expect to extend beyond planning to how agents govern their own learning and adaptation.

Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general performance, it often induces a Western-centric bias, hindering the model's ability to accurately reflect diverse cultural knowledge. We hypothesize that LLMs already possess rich cultural knowledge embedded within local-language representations, but fail to retrieve it when prompted in English. To bridge this cross-lingual knowledge gap, we propose a novel self-supervised framework. Our method leverages multilingual self-consistency to identify the most reliable cultural responses across languages, combined with a self-critique mechanism to transfer this knowledge to the weaker language. Evaluations on the BLEnD benchmark demonstrate that our approach significantly improves cultural alignment-boosting performance on English queries by an average of 5.03%-relying entirely on self-generated data. Ultimately, our work demonstrates that latent cultural knowledge can be successfully surfaced and propagated across languages, enabling more culturally equitable and consistent LLMs.

Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In this work, we accelerate large-scale pretrained ViTs while preserving their feature extraction capabilities by exploiting the intrinsic convolution-like behavior of some attention heads. Specifically, we introduce an efficient depthwise convolution-based layer that serves as a drop-in replacement for these heads. Additionally, we propose simple strategies to identify which heads can be replaced and introduce a fine-tuning procedure that recovers downstream task performance. Across both image classification and segmentation tasks, our method achieves 17-20\% percent inference speedup with minimal performance degradation. We validate the approach through detailed derivations, extensive experiments, and efficiency benchmarks. The reference implementation is publicly available.

In everyday photography, aesthetically appealing moments are often captured with structural flaws (e.g., composition, camera viewpoint, or pose) that existing retouching and portrait enhancement methods cannot fix. We formulate Aesthetic Photo Reconstruction (APR) as improving a photo's aesthetic quality via structural reconstruction while preserving subject identity and scene semantics. Although recent advances in image editing models make APR feasible, they often lack aesthetic understanding, yielding edits that are semantically plausible yet aesthetically weak. To address this, we propose AesFormer, a two-stage framework that decouples aesthetic planning from image editing. In Stage 1, an aesthetic action model (AesThinker) analyzes the input along seven progressive photographic dimensions and outputs executable editing actions; we further apply GRPO-A to encourage broad exploration over diverse action plans beyond SFT. In Stage 2, an action-conditioned editor (AesEditor) performs structural edits guided by these actions. To support APR, we build a video-based corpus-mining pipeline (VCMP) and construct AesRecon, a benchmark of 9,071 strictly aligned (poor, good) image pairs. Experiments show that AesFormer substantially improves APR performance and is competitive with Nano Banana Pro. Code is available at https://github.com/PKU-ICST-MIPL/AesFormer_ICML2026.

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants through different object instances, positions, and camera viewpoints. Recent vision-based reward models tend to memorize specific pixel distributions and fail to generalize beyond their training conditions. To address this, we propose a framework that learns invariant symbolic reward functions from as few as five demonstrations. The insight is to shift from visual feature-fitting to the discovery of behavioral invariants: task-level properties that remain constant across diverse visual instantiations. The framework has two coupled components: a structural reward formulation that encodes task-level strategies and physical constraints while preserving optimal policy invariance, and a hybrid symbolic-numerical procedure that distills these invariants from demonstrations without online interaction. Experiments on eight Meta-World tasks and three Franka manipulation tasks demonstrate that our method achieves stronger process alignment and policy rollout ranking abilities compared to baselines, accelerating downstream policy learning. Three real-world out-of-distribution experiments further show that the same learned reward generalizes zero-shot to position, viewpoint, and object variations, enabling a single reward representation to be reused across diverse task variants in practice.

This paper addresses bearing-only algorithms for solving the Fermat-Weber Location Problem (FWLP) with a unicycle agent. Unlike existing FWLP solutions for single- or double-integrator agents, our approach accounts for the nonholonomic constraints of wheeled robots. We first develop a bearing-only control law for the case with stationary beacons. Next, we consider saturated control inputs and propose a corresponding bearing-only control law. Finally, we address moving beacons with constant velocities and develop a control law that enables the unicycle agent to track the moving Fermat-Weber point. Both simulations and experiments are provided to demonstrate the effectiveness of the proposed methods.

Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchmarks evaluate this capability solely on numerical Big Five score prediction, leaving open whether models truly perceive personality through behavioral understanding or merely prejudge through superficial pattern matching. We address this gap with three contributions. (i) A new task: we formalize Grounded Personality Reasoning (GPR), which requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding. (ii) A new dataset: we release MM-OCEAN (1,104 videos, 5,320 MCQs), produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs. (iii) Benchmark and analysis: we design a three-tier evaluation (rating, reasoning, grounding) plus four sample-level failure-mode metrics: Prejudice Rate (PR), Confabulation Rate (CR), Integration-failure Rate (IR), and Holistic-grounding Rate (HR), and benchmark 27 MLLMs (13 closed, 14 open). The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%. These findings expose a disconnect between getting the right score and reasoning for the right reason, charting a roadmap for grounded social cognition in MLLMs.

Real-world image restoration is challenging due to complex and interacting mixed degradations. Recent agent-based approaches address this problem by composing multiple task-specific restoration tools. However, empirical analysis reveals that their performance is fundamentally limited by implicitly constrained planning spaces and the lack of coordination among independently pretrained tools. To address these issues, we propose OPERA (Optimized Planning-Execution Restoration Agent), a framework that jointly optimizes restoration planning and tool execution in an end-to-end manner. On the planning side, OPERA uses reinforcement learning to directly optimize tool composition over a combinatorial plan space, with the final restoration quality as the reward. On the execution side, OPERA introduces agent-guided co-training of restoration tools, enabling them to learn cooperative behaviors under sequential composition. Extensive experiments on multi-degradation benchmarks and real-world datasets demonstrate that OPERA consistently outperforms both all-in-one restoration models and existing agent-based methods across diverse and complex degradation scenarios.

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains largely unexamined for low-resource, non-Latin-script languages such as Khmer. In this paper, we present a RAG-based question answering system for Khmer-language telecom-domain documents. We conduct a two-phase comparative evaluation. First, we benchmark three embedding models: BGE-M3 (567M), Jina-Embeddings-v3 (570M), and Qwen3-Embedding (597M), for dense retrieval over Khmer documents. BGE-M3 consistently performs best, achieving a Hit Rate@3 of 0.285, File Hit Rate@3 of 0.700, MRR@3 of 0.221, and Precision@3 of 0.112, substantially outperforming the other retrievers. Second, using BGE-M3 as the selected retriever, we evaluate five generator backends: Qwen3 (8B), Qwen3.5 (9B), Sailor2-8B-Chat, SeaLLMs-v3-7B-Chat, and Llama-SEA-LION-v2-8B-IT, on a curated golden dataset of 200 Khmer question-answer pairs. To quantify system performance, we apply six RAGAS-inspired metrics: faithfulness, answer relevance, context relevance, factual correctness, answer similarity, and answer correctness. The results show no single model dominates across all metrics: Qwen3.5-9B achieves the highest faithfulness (0.859) and context relevance (0.726), Qwen3-8B attains the highest factual correctness (0.380), and SeaLLMs-v3-7B-Chat performs best on answer relevance (0.867), answer similarity (0.836), and answer correctness (0.599). These findings highlight that retriever choice remains a major bottleneck for Khmer RAG, while generator strengths vary depending on whether the priority is grounding, factual precision, or semantic similarity.

Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and reasoning capabilities. Recent attempts to incorporate dense visual supervision via world modeling often overemphasize pixel-level image reconstruction, neglecting semantically meaningful scene representation learning. In this work, we propose LVDrive, a Latent Visual representation enhanced VLA framework for autonomous driving. LVDrive introduces a future scene prediction task into the VLA paradigm, where future representations are learned entirely in a high-level latent space under auxiliary supervision from a pretrained vision backbone. Departing from inefficient autoregressive generation, we jointly model future scene and motion prediction within a unified embedding space, processed in a single forward pass to conduct the future-aware reasoning. We further design a two-stage trajectory decoding strategy that explicitly leverages the learned latent future representations to refine trajectory generation. Extensive experiments on the challenging Bench2Drive benchmark demonstrate that LVDrive achieves significant improvements in closed-loop driving performance, outperforming both action supervised methods and image-reconstruction-based world model approaches.

We introduce JMed48k, a multi-profession Japanese healthcare licensing benchmark for evaluating vision-language models. Built from official PDF materials released by the Japanese Ministry of Health, Labour and Welfare, JMed48k contains 48,862 exam questions and 20,142 images from 11 national licensing examinations between 2005 and 2025, with visual content annotated under an 8-type taxonomy. From this corpus, we derive JMed48k-Eval, a recent five-year evaluation subset with 12,484 scored questions, including 9,905 text-only questions and 2,579 questions with images. We evaluate 21 proprietary, open-source, and medical-specific models, reporting text-only and with-image performance separately. Because these subsets contain different questions, we further introduce a paired image-removal audit that evaluates questions with images before and after removing visual content to explore four answer-transition states. The audit shows that proprietary and open source models gain substantially from images, whereas medical-specific systems show limited observable use of visual evidence, with many correct answers persisting after image removal. Even among proprietary models, the net image-removal effect varies sevenfold across professions, from +5.7 points on Physician questions to +39.8 points on Public Health Nurse questions. We release JMed48k to support reproducible, profession-stratified evaluation of vision-language models in medical licensing settings.

Large language models (LLMs) are widely used to generate structured outputs such as JSON, SQL, and code, yet public resources remain limited for evaluating generation that must simultaneously satisfy industry-standard XML and domain vocabulary constraints. This paper presents Ishigaki-IDS-Bench, a benchmark for evaluating the ability to generate Information Delivery Specification (IDS) XML from Building Information Modeling (BIM) information requirements. The benchmark contains 166 BIM/IDS expert-authored and verified examples created by expanding 83 practical scenarios into Japanese and English, corresponding gold IDS files, and metadata for input format, language, turn setting, IFC version, and construction domain. Its evaluation combines IDSAuditTool-based Processability, Structure, and Content audits with content-agreement evaluation against gold IDS files. In zero-shot evaluation over 10 LLMs, the best model reaches 65.6% macro F1 for content agreement, while only 27.7% of outputs pass the Content audit. These results show that current LLMs can express part of the information requirements as IDS, but still struggle to stably generate XML that satisfies the IDS standard and IFC vocabulary constraints. Ishigaki-IDS-Bench supports comparative evaluation, failure analysis, and the development of constrained structured generation methods that conform to domain standards. We release the evaluation scripts and benchmark data under the CC BY 4.0 license on GitHub and Hugging Face.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens while preserving spatiotemporal interactions. Existing methods, such as LLaVA family, utilize simplistic pooling or interpolation techniques that overlook the intricate dynamics of visual tokens. To bridge this gap, we propose ST-GridPool, a novel training-free visual token enhancement method designed specifically for Video LLMs. Our approach integrates Pyramid Temporal Gridding (PTG), which captures multi-grained spatiotemporal interactions through hierarchical temporal gridding, and Norm-based Spatial Pooling (NSP), which preserves high-information visual regions by leveraging the correlation between token norms and semantic richness. Extensive experiments on various benchmarks demonstrate that ST-GridPool consistently enhances performance of Video LLMs without requiring costly retraining. Our method offers an efficient and plug-and-play solution for improving visual token representations. Our code is available in https://github.com/bingjunluo/ST-GridPool.

Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard problems because correct final-answer rollouts are rare and sample-level credit assignment cannot use partial progress in failed attempts. We introduce SCRL (Subproblem Curriculum Reinforcement Learning), a curriculum RL framework that derives verifiable subproblems from reference reasoning chains and fixes the final subproblem as the original problem. This turns partial progress on hard problems into verifiable learning signals. Algorithmically, SCRL uses subproblem-level normalization, which normalizes rewards independently at each subproblem position and assigns the resulting advantages to the corresponding answer spans, enabling finer-grained credit assignment without external rubrics or reward models. Our analysis shows that subproblem curricula lift hard problems out of gradient dead zones, with larger relative gains as the original problem becomes harder. Across seven mathematical reasoning benchmarks, SCRL outperforms strong curriculum-learning baselines, improving average accuracy over GRPO by +4.1 points on Qwen3-4B-Base and +1.9 points on Qwen3-14B-Base. On AIME24, AIME25, and IMO-Bench, SCRL further improves pass@1 by +3.7 points and pass@64 by +4.6 points on Qwen3-4B-Base, indicating better exploration on hard reasoning problems.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and recent work extends RLVR to multimodal large language models (MLLMs). This transfer, however, surfaces a faithfulness challenge: faithful perception of task-relevant visual evidence and faithful use of that evidence during reasoning, leading to unsatisfactory gains on multimodal benchmarks. Specifically, existing perception supervision often operates on textual descriptions rather than natively on image regions, and faithful use is largely overlooked, exposing the perception-reasoning disconnect where correctly perceived evidence is dropped or contradicted during reasoning. To close these gaps, we propose Faithful-MR1, a training framework that anchors and reinforces visual attention to address both halves of faithful multimodal reasoning. The Anchoring stage turns perception into an explicit pre-reasoning subtask, supervising a dedicated <Focus> token's attention directly against image regions rather than through textual descriptions. The Reinforcing stage exposes faithful use through counterfactual image intervention, rewarding answer-correct trajectories that concentrate visual attention where vision causally matters. Extensive experiments demonstrate that Faithful-MR1 outperforms recent multimodal reasoning baselines on both Qwen2.5-VL-Instruct 3B and 7B backbones while using substantially less training data.

Enterprise routers assign queries to expert agents, yet deployed profiles stay static while agents evolve (prompts, tools, models), and developers rarely keep descriptions or exemplars current. We present FlyRoute, a self-evolving profiling framework that grows capability evidence from real traffic: dispatch candidates, quality-gate successful pairs into each agent's success store, periodically distill evidence into learned capability descriptions, and inject those descriptions together with BM25-retrieved successes into an LLM router. To make this flywheel data-efficient, FlyRoute introduces a targeted exploration policy that combines profile uncertainty, BM25 relevance, and lexical novelty, prioritizing under-profiled agents only for plausible queries and avoiding redundant evidence collection. In experiments on our proprietary enterprise developer-support dataset of real routed queries, FlyRoute improves a same-backbone zero-shot LLM router from 72.57% to 78.04% with only five seed queries per agent, showing that profile retrieval already strengthens cold-start routing. After streaming 7,211 labeled training queries through the flywheel, accuracy rises to 89.83% (+17.26pp over zero-shot; +11.79pp over cold start), with consistent gains across four expert domains under standard routing accuracy on single-gold test queries.

Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set. This often leads to cross-level task interference, hindering accurate adaptation to the current task and object. To address this limitation, we propose HyLoVQA. It maintains a drift-resilient memory bank of anchors. The bank stores the content of visual objects and textual tasks, and they are updated using current input features. Conditioned on retrieved anchors, a hypernetwork generates lightweight Low-Rank Adaptation (LoRA) adapters. This ensures parameter efficiency, allowing the model to adapt to each task and object dynamically. Additionally, we formulate an alignment loss that aligns semantic discrepancies in the feature space with functional changes in the parameter space, thereby constraining LoRA adapters to remain focused on the current task and object. Extensive experiments on VQA v2 and NExT-QA under both standard and compositional settings demonstrate the superiority of HyLoVQA over prior state-of-the-art methods.

Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evidence from both modalities. A central limitation is that explicit text-based chain-of-thought (CoT) compresses continuous audio-visual signals into discrete tokens, weakening temporal grounding and shifting intermediate reasoning toward language priors. We argue that a unified latent space is a better medium for such reasoning because it preserves dense sensory information while remaining compatible with autoregressive generation. Based on this insight, we propose \textbf{LatentOmni}, a cross-modal reasoning framework that interleaves textual reasoning with audio-visual latent states. LatentOmni introduces feature-level supervision to align latent reasoning states with task-relevant sensory features and uses Omni-Sync Position Embedding (OSPE) to maintain temporal consistency between latent audio and visual states. We further construct \textbf{LatentOmni-Instruct-35K}, a dataset of audio-visual interleaved reasoning trajectories for supervising latent-space reasoning. Comprehensive evaluation across multiple audio-visual reasoning benchmarks demonstrates that LatentOmni achieves the best performance among the evaluated open-source models and consistently outperforms the Explicit Text CoT baseline, supporting latent-space joint reasoning as a promising path toward stronger omnimodal understanding.

We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of PyTorch and no model inference -- reveals interpretable semantic subspaces directly from the model weights. Each left singular vector identifies the vocabulary tokens most readily selected when the hidden state aligns with the corresponding singular direction; inspecting these clusters exposes the model's training data composition and curation philosophy. Analysing GPT-OSS-120B, Gemma-2-2B, and Qwen2.5-1.5B, we find that singular value spectra and vocabulary cluster structures differ systematically across models: GPT exhibits a graduated hierarchy of functionally differentiated subspaces; Gemma is dominated by pre-nineteenth-century English orthography, forming a stepwise clustering structure that may contribute to high output controllability; and Qwen exhibits broad multilingual coverage alongside subspaces whose vocabulary the authors have determined to be ethically inappropriate for direct publication. Base-instruct comparison reveals that ethically concerning subspaces originate in pretraining and are not removed by post-training alignment. We introduce the Vocabulary Cluster Score (VCS) to quantify subspace coherence, and the Weighted Projection Score (WPS) as a static glitch token detector; applying WPS to GPT-OSS-120B recovers shokubutsu-hyakka-tsu (ID 137606), a well-known glitch token widely reported in the CJK language community, without any model inference. We propose a taxonomy of root causes for problematic vocabulary content and call for lm_head} SVD analysis to be adopted as a standard pre-release safety auditing step. Our findings further suggest directions toward SVD-guided tokenizer optimisation and more controllable LLM design.

Injection detectors deployed to protect LLM agents are calibrated on static, template-based payloads that announce themselves as override directives. We identify a systematic blind spot: when payloads are generated to mimic the domain vocabulary and authority structures of the target document, what we call domain camouflaged injection, standard detectors fail to flag them, with detection rates dropping from 93.8% to 9.7% on Llama 3.1 8B and from 100% to 55.6% on Gemini 2.0 Flash. We formalize this as the Camouflage Detection Gap (CDG), the difference in injection detection rate between static and camouflaged payloads. Across 45 tasks spanning three domains and two model families, CDG is large and statistically significant (chi^2 = 38.03, p < 0.001 for Llama; chi^2 = 17.05, p < 0.001 for Gemini), with zero reverse discordant pairs in either case. We additionally evaluate Llama Guard 3, a production safety classifier, which detects zero camouflage payloads (IDRcamouflage = 0.000), confirming that the blind spot extends beyond few-shot detectors to dedicated safety classifiers. We further show that multi-agent debate architectures amplify static injection attacks by up to 9.9x on smaller models, while stronger models show collective resistance. Targeted detector augmentation provides only partial remediation (10.2% improvement on Llama, 78.7% on Gemini), suggesting the vulnerability is architectural rather than incidental for weaker models. Our framework, task bank, and payload generator are released publicly.

Most agent frameworks are built around the language model: a conversation loop comes first, then tools, then rules, and finally a logging layer bolted on for observability, with state persisted as retrievable "memory." We describe ActiveGraph, a runtime that inverts this arrangement. The append-only event log is the source of truth; the working graph is a deterministic projection of that log; and behaviors--ordinary functions, classes, LLM-backed routines, or logic attached to typed edges--react to changes in the graph and emit new events. No component instructs another; coordination happens entirely through the shared graph. This single design decision yields three properties that retrieval-and-summarization memory systems do not provide: deterministic replay of any run from its log, cheap forking that branches a run at any event without re-executing the shared prefix, and end-to-end lineage from a high-level goal down to the individual model call that produced each artifact. We present the architecture, a determinism contract that makes replay sound, and a worked diligence example whose full causal structure is reconstructable from the log alone. We discuss--without claiming to demonstrate--why this substrate is unusually well suited to self-improving agents, and how it extends the BabyAGI lineage and prior graph-memory research.

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend these barriers. Today, the widespread deployment of AI agents grants us low-cost access to massive streams of such real-world experience. However, raw interaction logs are inherently noisy, filled with trial-and-error and low information density, rendering them inefficient for direct model training. We introduce Echo, a generalized framework designed to operationalize the transition from raw experience to learnable knowledge, effectively "echoing" environmental feedback back into the training loop for model optimization. In today's agent ecosystem, user refinement serves as a primary source of such feedback: driven by responsibility for the outcome, users rigorously transform flawed agent proposals into verified solutions. These user-driven refinement sequences inherently distill agents' crude attempts into high-quality training signals. Echo systematically harvests these signals to continuously align the agent with real-world needs. Large-scale validation in a production code completion environment confirms that Echo effectively harnesses this pipeline, breaking the static performance ceiling by increasing the acceptance rate from 25.7% to 35.7%.

Vision-based learning from demonstrations has achieved remarkable success in enabling robots to perform manipulation tasks and high-level semantic reasoning, yet it remains insufficient for complex, contact-rich manipulation. While there is broad agreement that tactile sensing improves manipulation, there is no empirical guidance on which tactile sensors are best suited for which manipulation tasks. In this paper, we provide a systematic, task-driven evaluation of tactile sensors for robot manipulation and propose a framework for selecting and evaluating sensors based on manipulation policy performance. Separate manipulation policies are trained for tactile sensors of four distinct modalities: visual, acoustic, magnetic, and resistive, across three tasks: pick-and-place with unknown mass, object reorientation, and plug insertion. For each task, an analysis of how sensor properties such as spatial resolution, shear sensing, and tactile representation, and the inherent material friction affect task performances is done. Rather than tactile sensing being universally beneficial in the same way, our results show that the usefulness of tactile information depends strongly on sensor modality, material properties, and the specific manipulation tasks. All of the tactile sensors, code, data, and hardware setup will be publicly available on the project website.

Large language models increasingly use external tools such as web search and document retrieval to solve information-intensive tasks. However, multi-hop tool use in complex tasks introduces substantial latency, since the model must repeatedly wait for tool observations before continuing. We study how to accelerate such trajectories without changing the final trajectory the model would have taken without acceleration, assuming access to faster but less reliable speculator tools. We develop a theoretical framework for lossless speculation in multi-hop tool-use settings, characterizing the optimal achievable latency gain. We propose SpecHop, a continuous speculation framework that maintains multiple speculative threads, verifies predicted observations asynchronously as target tool outputs arrive, commits correct branches, and rolls back incorrect ones. This preserves accuracy while reducing wall-clock latency. We show that SpecHop can approach oracle latency gains with enough active threads. Empirically, on retrieval-augmented multi-hop tasks, SpecHop closely matches theoretical predictions and reduces latency by up to 40\% in some settings. Code: https://github.com/mehrdadsaberi/spechop

Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introduce substantial inference latency. Most existing acceleration strategies compress the reconstruction network while overlooking physical priors from the optical path, leaving a trade-off between accuracy and speed. We present Physics-aware Dual-Integrated Network (PDI-Net), a low-latency framework that integrates infrared reconstruction with object detection and further embeds optical priors into the learning process. PDI-Net uses a supervised U-Net during training, while a semi-U-Net encoder shares features directly with a YOLO-based detector during inference, avoiding full image reconstruction. To bridge the gap between fidelity-oriented reconstruction features and detection-oriented semantics, we introduce a physics-aware large-small bridge (PALS-Bridge), which uses field-dependent point spread function priors to adaptively modulate multiscale convolutional branches. A physics-informed optical degradation simulation pipeline is also developed for training and validation. The method is deployed on a single-lens infrared camera, reducing system weight by about 50% compared with traditional multi-lens designs. On the M3FD benchmark under low-SNR conditions, PDI-Net reduces inference time by 84.06% compared with the Rec+Det with pruning strategy while improving mAP@0.5:0.95 by 5.07%. These results demonstrate compact, low-latency computational infrared imaging for real-time object detection on resource-constrained platforms.

When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Diagnostic Paradox empirically: causal analysis consistently identifies the routing module -- which selects which tool to call next -- as the primary bottleneck across three independent agent families. Yet injecting prompt-level correction examples into this module consistently degrades performance, sometimes severely. Patching an upstream query-rewriting module instead reliably improves outcomes. The effect holds with statistical significance on two agent families and directional consistency on a third; alternative repair strategies at the routing module (instruction rewriting, model upgrade) are neutral, confirming that the harm is specific to correction-injection patching. We explain this asymmetry through the Linguistic Contract hypothesis: each downstream module implicitly adapts to its upstream's characteristic error distribution, so correcting the bottleneck breaks this implicit alignment in a way that upstream corrections do not. We operationalize this via a per-agent co-adaptation measure, derived from diagnosis alone, and show it is consistently associated with patching harm across agent families: higher co-adaptation co-occurs with harm, lower with safety. This trend holds across all three agent families, providing preliminary support for the hypothesis beyond a single-agent observation.

Medical RAG systems in high-risk QA settings are often evaluated through a single answer-or-abstain decision, but mixed evidence may support one claim, require conditions for another, and contradict a third. We study claim-selective certification: each response is decomposed into verifiable claims, scored against retrieved evidence, and mapped by an intent-aware selector to {full, partial, conflict, abstain}. On the primary weak-label certificate protocol, whose real-source-only dev/test rows cover the naturally occurring non-abstain actions, the full system records UCCR=0.0000, PAU=1.0000, PAU Precision=0.9901, and action accuracy=0.9204 on dev (n=314), and UCCR=0.0000, PAU=0.9967, PAU Precision=0.9739, and action accuracy=0.8997 on test (n=319). UCCR measures unsupported-claim risk within the certificate definition, and a source-missing counterfactual slice evaluates abstain under empty evidence. Shortcut controls quantify the action-label prior explained by source and intent metadata, while source/evidence-novel slices characterize transfer boundaries. The resulting interface separates action-label prediction from evidence-linked claim selection under mixed evidence.

The complete collection of sparse resources in large, unknown environments remains a challenging problem for autonomous robot swarms. Previous studies have shown that a substantial portion of total mission time is consumed during the final stage of collection, where only a small fraction of randomly scattered resources remain. Consequently, many existing swarm foraging algorithms (search and collection) focus on collecting most resources within a limited time window, rather than improving end-stage efficiency for collecting all resources. We propose a grid-based stochastic foraging strategy that explicitly reduces redundant visits and accelerates late-stage collection. The unknown search area is partitioned into a grid map, which is maintained by a lightweight central server. To maintain scalability, both robots and the server operate within limited memory and computational constraints. The server updates the grid-level visitation counts based on robot-reported locations, producing a global estimate of the exploration density. For each new foraging trip, a robot selects its next search area from a local 3 X 3 neighborhood of grids probabilistically with the lowest visitation count, thus biasing exploration toward under-visited regions while maintaining stochasticity. Extensive simulation experiments demonstrate that the proposed strategy consistently outperforms the canonical centrally placed baseline foraging algorithm (CPFA). Compared to CPFA, the proposed method reduces the total collection time by up to 33% and improves collection efficiency by more than 48% during the final stage of the mission. These results indicate that the proposed strategy is robust, flexible, and scalable for near-complete and complete resource collection in robot swarms and can serve as a general enhancement for stochastic swarm foraging methods under limited onboard resources.

Safe manipulation-oriented navigation for humanoid robots requires scene memory that remains reliable under locomotion-induced perceptual distortion, environmental changes, and interaction-level geometric safety constraints. Existing semantic mapping and scene-graph systems are difficult to deploy directly in this setting because they often assume stable camera trajectories, static environments, or coarse object geometry. We introduce the Multi-modal Interactive Field (MIF), a humanoid-oriented system that integrates confidence-aware semantic 3D Gaussian Splatting, discrepancy-triggered spatial memory updates, and task-driven geometric reconstruction within a closed-loop perception-adaptation pipeline. MIF couples three fields: an uncertainty-aware 3DGS Appearance Field that suppresses gait-induced blur, a Spatial Field that maintains topological memory, and a Geometry Field that supports Interaction Pose Safety (IPS) before manipulation. A discrepancy detection score is introduced to separate locomotion-induced false-positive changes from persistent changes and updates only locally inconsistent regions. On a Unitree-G1 humanoid in a real dynamic office, MIF improves relocation success in non-static environments from 12% to 94% compared with static scene-graph memory, while reducing semantic memory footprint by 91.4% through feature distillation for practical online operation. Project page and code: https://ziya-jiang.github.io/MIF-homepage/

Multi-Robot Task Allocation (MRTA) is a central challenge in decentralized multi-agent systems, where teams of robots must cooperatively assign and execute tasks under limited communication while optimizing global performance objectives. Auction-consensus algorithms, such as the Consensus-Based Bundle Algorithm (CBBA), provide scalable decentralized coordination with provable convergence, but rely on hand-crafted greedy scoring functions that often lead to suboptimal task allocations. This paper proposes a learning-enhanced auction-consensus framework in which CBBA's deterministic bidding mechanism is replaced by a neural bidding policy trained using reinforcement learning. Under a centralized training and decentralized execution paradigm, agents learn to compute task bids from partial local observations while retaining the standard auction and consensus phases for decentralized coordination. The learned bidding policy is trained using Proximal Policy Optimization with rewards shaped by proximity to globally optimal solutions obtained via mixed-integer linear programming. Multiple neural architectures are evaluated, including a Neural Additive Model, the Long Short-Term Memory (LSTM) model, and the Set Transformer Model. Experimental results across varying swarm sizes demonstrate that learned bidding policies can improve solution quality over classical CBBA while preserving decentralized execution. The proposed approach highlights the effectiveness of integrating reinforcement learning with classical distributed coordination algorithms, offering a scalable pathway toward higher-quality decentralized multi-robot task allocation.

The integration of machine learning with domain-specific physics is transforming the design, monitoring, and control of electricity systems, where data scarcity, limited interpretability, and the need to enforce physical laws constrain purely data-driven models. Physics-informed machine learning (PIML) addresses these limitations by embedding governing equations directly into the learning process, yielding accurate, efficient, and scalable solutions for Industry 4.0 applications. This article reviews hybrid PIML architectures for electricity systems, including physics-informed neural networks (PINNs), Deep Operator Networks (DeepONets), Fourier Neural Operators, Extreme Learning Machine-enhanced PINNs, graph-based PINNs (PIGNNs), and domain-decomposition PINNs. Each approach is examined through case studies spanning field analysis, fault detection, digital twins, surrogate modeling, and control optimization. The review shows that embedding Maxwell's equations and other first-principles constraints substantially improves predictive accuracy under sparse and noisy data, reduces simulation time by orders of magnitude relative to finite element methods, and enhances generalization across operating regimes. Hybrid frameworks consistently outperform purely data-driven baselines on parameter sensitivity, dynamic behavior, and robustness, while supporting real-time digital-twin calibration and uncertainty quantification. Persistent challenges include training instability for stiff multi-scale problems, computational cost of high-fidelity models, and the absence of standardized benchmarks. The findings demonstrate that PIML enables a paradigm shift from black-box data-driven methods to transparent, physics-informed strategies, positioning the field for sustained innovation in resilient and intelligent electricity systems.

One of the significant challenges in legged robotics is achieving accurate odometry using only onboard proprioceptive sensors. In this study, we present a complete leg odometry pipeline based on an Error-State EKF (ESEKF) that relies exclusively on proprioceptive data: a body fixed IMU, joint encoders, and force sensors, where filter's state is corrected by feet determined to be in a stationary stance. The core of our contribution is fused contact detection and an uncertainty quantification module designed to explicitly identify and reject slippage. This module runs two detectors in parallel for each foot, 1) a debounced, force-based Gaussian Mixture Model (GMM) guided Finite State Machine (FSM) to confirm physical contact, and 2) a kinematic-based Generalized Likelihood Ratio Test (GLRT) on the estimated velocity of the foot. The continuous quality scores from both estimators are fused to detect if the foot is both physically loaded and kinematically stationary and served as an uncertainty signal for each contact. To validate our approach, we collected a multi-modal dataset of 29 sequences spanning diverse indoor and outdoor terrains (e.g., concrete, grass, pebble, and rock) total of 2.4 km long. We benchmarked our approach against both proprioceptive and exteroceptive methods. The results demonstrate our method's efficacy in providing accurate odometry estimates, robustly handling slippage-prone environments. We also share our code and real-time ROS2 package as open-source.

Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet robot actions cause contact, occlusion, and object motion, and the geometry that later decisions depend on can change before the next visual update arrives. Spatial VLAs improve current-frame geometry. Temporal VLAs aggregate past frames. Neither maintains an action-updated scene prior across chunks. We argue for a persistent action-updated scene state across control calls, and introduce EvoScene-VLA. Its recurrent scene prefix carries a geometry-aware scene state across chunks. At each vision-language model (VLM) call, the VLM combines scene information from the current observation with the action-updated prior from the previous chunk; the action decoder outputs both the next action chunk and a compact scene update. This update becomes the next prior, which the VLM corrects against the new observation when the next call arrives. Each control call therefore starts from a scene prior that reflects both recent actions and fresh visual evidence. During training, \textbf{Scene Predictor} supplies future scene-token targets, and Geometric Anchor aligns scene slots with frozen depth and 3D teachers. We discard both modules at deployment. On 31 RoboTwin tasks, EvoScene-VLA raises average success from 87.2% to 89.1% in fixed evaluation and from 86.1% to 88.5% in randomized evaluation. On the Galaxea R1-Lite real robot, EvoScene-VLA outperforms all baselines.

Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and receiving environment observations across many turns. The evidence needed to answer the original question is thus scattered throughout these turns, requiring integration of distant context segments. Nevertheless, standard agent SFT masks tool responses and only trains turn-level tool selection, creating a supervision blind spot where these scattered signals go unused. We propose Agent Context Compilation (ACC), which converts trajectories from search, software engineering, and database querying agents into long-context QA pairs that combine the original question with tool responses and environment observations gathered across multiple turns, training the model to answer directly without tool use. This makes the dependencies between the question and the evidence explicit, enabling direct supervision of long-context reasoning over distant segments without additional annotation. ACC is a simple but effective approach that can be combined with any existing long-context extension or training method, providing scalable supervised fine-tuning data. We validate ACC on long-range dependency modeling tasks through MRCR and GraphWalks, challenging benchmarks requiring cross-turn coreference resolution and graph traversal over extended contexts. Training Qwen3-30B-A3B with ACC achieves 68.3 on MRCR (+18.1) and 77.5 on GraphWalks (+7.6), results comparable to Qwen3-235B-A22B, while preserving general capabilities on GPQA, MMLU-Pro, AIME, and IFEval. Further mechanism analysis reveals that the ACC-trained model exhibits task-adaptive attention restructuring and expert specialization.

Robotic dexterous manipulation requires continuously reconciling objectives and constraints defined on heterogeneous geometric spaces: a robot controlled on a $\mathbb{R}^7$ configuration manifold may need to track end effector poses on $\mathrm{SE}(3)$ while satisfying obstacle avoidance margins in $\mathbb{R}$. We present Safe Pullback Bundle Dynamical Systems (SafePBDS), a geometrically consistent framework that computes optimal, certifiably safe configuration manifold accelerations from objectives and safety requirements on arbitrary task manifolds. SafePBDS builds on prior work that combines predefined task manifold dynamical systems to produce autonomous motion. Its first innovation is a pullback control barrier function construction, which converts task manifold safety conditions into linear constraints on configuration manifold accelerations. The second innovation is a task manifold action interface that allows a high-level policy to inject low dimensional residual motions; zero input recovers the autonomous behavior, while safety is preserved under arbitrary inputs. This lets high-level policies efficiently steer exploration while leaving precise motion to the autonomous behavior. We validate SafePBDS in simulation and on a 23-DOF Franka Panda-Allegro Hand platform. On dexterous grasping, SafePBDS achieves a $92.5\%$ success rate across 20 household objects and 120 trials. Using the action interface, the method can exclude any one of the four fingers during grasping via a one-dimensional action, achieving $94.4\%$ 3-finger grasp success across 3 objects and 36 trials. The efficient planning and safety guarantee of SafePBDS also enables the first model-based, fully actuated palm-down in-hand reorientation, exceeding $360^\circ$ of yaw rotation in both directions under varying object weight and wrist motion. Demo video and details: https://tml.stanford.edu/safe-pbds

Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, making precise edits, and recovering from sparse hidden-verifier failures. We present Trace2Skill, a test-time scaling framework that improves a hardware agent without RTL-specialized model fine-tuning. Rather than training a new model or only sampling more candidate solutions, Trace2Skill treats the agent's natural-language skill as an evolvable policy. It mines repeated rollout traces for success and failure modes, converts them into dense diagnostics and oracle lessons, and uses an oracle, mutator, and selector loop to produce task-specific skills that guide later search, editing, validation, and recovery. Because final pass/fail labels are often too coarse for hard failures, Trace2Skill also supports bounded runtime dense verifier feedback that returns sanitized functional observations while keeping hidden harnesses and reference solutions inaccessible to the agent. This feedback helps guide skill evolution and agent execution by connecting skill text, verifier evidence, and downstream behavior. Across hard CVDP tasks that defeat the seed CVDP agent, including tasks that also defeat frontier coding agents, Trace2Skill with dense verifier feedback substantially improves task pass rates and produces breakthrough passes on previously unsolved tasks, without requiring high-quality fine-tuning data, specialized RTL model training, or model weight updates. The same framework provides a general test-time scaling strategy that can extend beyond digital design to other verifiable EDA tasks.

Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These pathways routinely fall short for the long tail of real-world care not covered by guidelines. Most medical large language models (LLMs), however, are trained to encode common, guideline-focused medical knowledge in their parameters. Current evaluations test models primarily on recalling and reasoning with this memorized content, often in multiple-choice settings. Given the fundamental importance of evidence-based reasoning in medicine, it is neither feasible nor reliable to depend on memorization in practice. To address this gap, we introduce OGCaReBench, a free-form retrieval-focused benchmark aimed at evaluating LLMs at answering clinical questions that require going beyond typical guidelines. Extracted from published medical case reports and validated by medical experts, OGCaReBench contains long-form clinical questions requiring free-text answers, providing a systematic framework for assessing open-ended medical reasoning in rare, case-based scenarios. Our experiments reveal that even the best-performing baseline (GPT-5.2) correctly answers only 56% of our benchmark with specialized models only reaching 42%. Augmenting models with retrieved medical articles improves this performance to up to 82% (using GPT-5.2) highlighting the importance of evidence-grounding for real-world medical reasoning tasks. This work thus establishes a foundation for benchmarking and advancing both general-purpose and medical LLMs to produce reliable answers in challenging clinical contexts.

Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but lack principled mechanisms to distinguish informative from noisy signals. Recent approaches leverage response-level measures as uncertainty signals to regulate group-based optimization methods such as GRPO. Yet their empirical success remains unstable and unclear in how they influence optimization dynamics. In this paper, we provide, to our knowledge, the first principled formulation that interprets uncertainty signals as mechanisms for characterizing and regulating gradient variance and learning signal quality. Based on both empirical and theoretical analysis, we identify two critical gaps of current entropy-based estimators: The anisotropic gap and The calibration gap. Motivated by this analysis, we propose Geometric-aware Calibrated Policy Optimization (GCPO), a novel framework integrating geometry-aware measures to capture semantic disagreement with reward-based calibration to align uncertainty with learning signal strength. Experiments on multiple benchmarks show that our approach more faithfully tracks gradient variability and consistently improves post-training performance. Our results highlight the importance of designing uncertainty signals that are aligned with optimization dynamics, offering a principled perspective for robust post-training.

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols hindering reproducibility and fair comparison. Current practice is further limited by three key bottlenecks: fragile one-off codebases, slow video data loading, and the lack of standardized generalization benchmarks. We present stable-worldmodel (swm), an open-source platform for standardized and reproducible world modeling research and evaluation. It delivers (1) a high-performance Lance-based data layer with native support and conversion tools for MP4, HDF5, and LeRobot datasets, (2) clean, well-tested implementations of modern world model baselines and planning solvers, and (3) a broad suite of environments and tasks extended with controllable visual, geometric, and physical factors of variation for systematic in-silico evaluation of dynamics understanding, control performance, representation quality, and out-of-distribution generalization. By unifying the full pipeline under a single, scalable framework, \texttt{swm} dramatically reduces research overhead and accelerates trustworthy progress toward reliable world models.

Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing (1) a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry, and (2) a two-stage grounding pipeline that explicitly resolves conversational ambiguity before visual localization. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types. Our contextual rewriting approach improves grounding performance by 11-22 percentage points on average, with a pure detector (GroundingDINO) reaching 56.7% on pronominals after rewriting, nearly double the best end-to-end baseline. Results demonstrate that decoupling linguistic reasoning from visual perception is more effective than end-to-end approaches for conversational grounding.

Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K. On Spider2-Lite, DivSkill-SQL improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline, with consistent gains across two base models (Opus-4.6 and GPT-5.4). Skills optimized on a single dialect transfer without retraining across dialects (Snowflake, BigQuery, SQLite) and to a different task formulation, such as BIRD-Critic (+2.6 pts). Error diagnostics show up to 3x fewer hallucinated schema references and function calls, indicating that gains come from genuinely reliable complementary skills rather than surface-form variation.

Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relationships from 2D views, which are subsequently lifted into a persistent 3D scene graph encoding both spatial and semantic relations. Given a query, we construct a query graph and perform constrained alignment with the scene graph, ensuring multi-view consistency and interpretable reasoning. Experiments on the ScanRefer benchmark demonstrate that our method achieves competitive performance among zero-shot approaches, using only RGB-D inputs. We further validate our framework through real-world deployment on a mobile robot, demonstrating robust spatial reasoning in long-horizon physical environments. We will make our code publicly available upon acceptance.

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive and highly sensitive to formatting, phrasing, and instruction order, motivating automated prompt optimization methods that reduce manual effort while preserving inference-time flexibility. However, existing methods often search over prompt candidates or use fixed critique-refine pipelines driven by individual examples or small batches, limiting their ability to capture systematic error patterns and make targeted edits grounded in failure history. We propose Reflective Prompt Tuning (RPT), a framework that uses LLM function calling to simulate the iterative workflow of human prompt engineers. An LLM optimizer calls a diagnostic function that evaluates the target model over an entire optimization set, summarizes recurring failure modes, and returns a structured diagnostic report. The optimizer uses this report, together with an accumulated memory of prior reports, to revise the prompt for the next iteration. RPT further supports confidence-aware optimization by using calibration signals in diagnostic feedback and final prompt selection. Across three reasoning tasks, RPT improves over initial prompts by up to 12.9 points, remains competitive with state of the art, and improves confidence calibration. Our analyses show that RPT is especially effective on multi-hop and mathematical reasoning, producing targeted prompt revisions that align with diagnosed failure patterns and lead to gains in task performance and calibration.

Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using only prompts and elicited probabilities. We introduce a benchmark with human-derived ground-truth PMI across three publicly available datasets, and evaluate five information-theoretic prompting-based estimators. Our main method, PromptNCE, frames conditional probability estimation as a contrastive task and augments the candidate set with an explicit OTHER category. We show theoretically that adding OTHER recovers the true conditional P(y | x) rather than just a ranking over listed candidates, turning a contrastive prompt into a general-purpose zero-shot probability estimator. PromptNCE is the best zero-shot method on all three datasets, reaching Spearman correlation up to 0.82 with human-derived PMI. We also present a case study in computer science education showing how these estimators can be used to score student knowledge summaries in a low-data setting.

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments is challenging because memory turns the agent's past actions into part of its future environment. Once different rollouts write, update, or delete different memories, they no longer share the same intermediate memory state, making trajectory-level comparisons fundamentally unfair. This violates a key assumption behind group-relative methods such as GRPO, where rollouts are compared as if they were sampled from the same effective environment. Consequently, trajectory-level rewards provide noisy or biased credit signals for long-horizon memory operations. To address this challenge, we introduce Memory-R2, a training framework for long-horizon memory-augmented LLM agents. Its core algorithm, LoGo-GRPO, combines local and global group-relative optimization. The global objective preserves end-to-end learning from long-horizon trajectory-level rewards, while local rerollouts compare different memory-operation outcomes from the same intermediate memory state, yielding fairer group comparisons and more precise supervision for memory construction. Beyond credit assignment, Memory-R2 jointly optimizes memory formation and memory evolution with a shared-parameter co-learning design, where a fact extractor and a memory manager are instantiated from the same LLM backbone through role-specific prompts. To stabilize multi-step RL over long memory horizons, we adopt a progressive curriculum that increases the training horizon from 8 to 16 to 32 sessions. Together, these components provide an effective training paradigm for memory-augmented LLM agents in long-horizon multi-session settings.

As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human evaluation may be practical, but in complicated systems like conversational chatbots, the amount of generated text can overwhelm human annotation resources. Model developers have begun to rely heavily on auto-evaluation, where LLMs are also used to judge generation quality. However, existing LLM-as-a-judge benchmarks largely focus on simple Q\&A tasks that do not match the complexity of multi-turn conversations. We introduce RankJudge, a benchmark generator for evaluating LLM-as-a-judge on multi-turn conversations grounded in reference documents. RankJudge creates pairs of conversations where one conversation has a single flaw injected into one turn. This construction allows paired conversations to be labeled unambiguously as better or worse, and precisely isolates failure categories to individual turns, enabling a strict joint correctness criterion for judging. We implement RankJudge across the domains of machine learning, biomedicine, and finance, evaluate 21 frontier LLM judges, and rank those judges via the Bradley-Terry model. Our formulation also allows ranking each conversation pair with difficulty ratings, which we use to dynamically curate the evaluation slice to reduce label noise, as confirmed via human annotation. We find that judge rankings are stable under partial observability, coarser correctness criteria, and an alternative random-walk rating algorithm.

Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve extensive computational costs associated with the use of Large Language Models (LLMs) as judges, or instead suffer from the limitations of standard CLIP-based encoders, such as strict token limits, lack of fine-grained sensitivity, or lack of compositional generalization by treating captions as ``bags-of-words.'' We propose a new learned metric that tackles the aforementioned challenges, based on a lightweight cross-encoder that is initialized from a visual question-answering model checkpoint, balancing a strong weight initialization with computational efficiency. Our training scheme uses a carefully assembled data mixture for supervised learning, featuring adversarial LLM-based data augmentations to enhance model sensitivity to fine-grained visual-linguistic errors. We also introduce a new benchmark designed to assess detailed captioning evaluation across diverse scenarios. Experimental results demonstrate that the proposed metric achieves state-of-the-art performance while maintaining the efficiency required for large-scale benchmarking, quality-aware decoding, or reward guidance.

Behavior cloning for contact-rich bimanual manipulation remains challenging because diverse demonstrations are expensive to collect, and even small disturbances can push the system into off-manifold states where no recovery supervision is available. We propose PGDG, a data generation framework with zero-shot curation that expands a single demonstration into a compact dataset of physically plausible, successful, and diverse recovery behaviors without additional human labeling. PGDG iterates between a physics-grounded sampler and a dataset curator, where the curator selects informative, non-redundant, and recoverable behaviors to update the sampling distribution toward under-covered recovery modes, and the sampler draws physically plausible rollout candidates from this updated distribution and retains successful trajectories. To further improve data quality, PGDG applies short-horizon sampling-based control to relabel selected risky states with corrective actions. Across four bimanual manipulation tasks, PGDG consistently outperforms spatial-only augmentation in both simulation and zero-shot real-world transfer. On RotateBox-Pitch, success improves from 38% to 93% in simulation and from 35% to 82% in the real world. PGDG also enables effective foundation models fine-tuning such as GR00T, increasing success from 46% to 77%. Additional results are available in our website: https://cunxid.github.io/PGDG/.

Locomotion in microgravity often relies on sparsely and irregularly arranged anchors, motivating grasp-based mobility with multiple limbs. In this setting, dynamic locomotion is feasible only through deliberate regulation of both anchored interactions and whole-body coordination under coupled dynamic and kinematic constraints. This paper presents design insights for grasp-based dynamic locomotion with multi-limbed robotic systems in microgravity, targeting scenarios that require 6D limb manipulation to establish contacts with candidate anchors. The investigated design parameters include gait pattern, stride length, locomotion speed, and nominal posture. A parameterizable locomotion planning framework is proposed to support variations of these parameters and to evaluate the resulting locomotion performance in terms of stability and actuation demand. Two representative quadruped morphologies are adopted for evaluation in physics-based simulation. The results demonstrate that enlarging the feasible contact wrench space and attenuating impulsive whole-body dynamics improve locomotion performance. These findings inform strategies for contact configuration selection and whole-body coordination in microgravity locomotion with multi-limbed systems.

Autonomous contact-based micromanipulation is challenging because surface and interfacial interactions at the microscale are difficult to model accurately, limiting the use of conventional model-based control and sim-to-real learning. We present a closed-loop sim-to-real reinforcement learning (RL) approach for microfiber shape control on a surface. The central idea is to train geometric shape regulation in a simplified frictionless simulator and rely on real-time visual feedback during deployment to iteratively correct the observed effects of unmodeled surface interactions. An RL policy trained entirely in simulation is transferred directly to a physical dual-gripper micromanipulation system operating at 40 Hz, without retraining or domain adaptation. Using silk microfibers as a testbed, the policy achieves a mean point-wise shape error of 270 $\pm$ 80 $μ$m across twenty-four diverse initial configurations. Across nine specimens covering all combinations of three fiber diameters (50, 80, and 120 $μ$m) and three manipulated lengths (10 mm, 15mm, and 20 mm), the same policy achieves sub-millimeter final shape error without any retraining or retuning. These results show that a policy learned in a simplified simulator can achieve repeatable real-world microfiber shape regulation under surface contact, provided that the task-relevant effects of the sim-to-real mismatch remain observable and correctable within the closed feedback loop.

While autonomous multi-robots can achieve safe and coordinated navigation, they often struggle to adapt to unforeseen conditions and to capture operator-driven objectives in unstructured environments. We present a Virtual Reality (VR)-based shared control framework for teams of drones operating in constrained and unknown environments, enabling real-time, user-guided exploration. At the core of our approach is a novel, user-guided motion-primitive-based planner that computes continuous, collision-free trajectories while continuously integrating operator input. This planner is coupled with an admittance controller, allowing the operator to flexibly influence team behavior and guide drones toward regions of interest that autonomous planners may overlook. The system supports mixed-reality operations with both physical and simulated drones, and implements a bilateral VR-based interface, allowing the operator to guide the robot team via migration points while receiving immediate visual feedback of the team state. Experimental results show that shared control improves obstacle avoidance, maintains inter-agent spacing, and reduces operator effort, demonstrating the feasibility and advantages of immersive, human-in-the-loop multi-robot navigation.

Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO work as well as they do, and when they should provide the largest gains. We develop a value-gradient perspective of critic-free RL for LLM post-training. First, under a differentiable rollout and additive-noise parameterization, we show that the actor update is value-gradient-like in expectation: the backward pass propagates costates whose conditional expectation equals the value gradient. Second, for discrete transformer policies, we show that autodifferentiation through attention produces empirical costates that approximate this value signal, with an error controlled by the sampling gap and policy entropy. These results motivate a decomposition of RL impact into value gradient signal and reachable reward headroom, yielding a criterion for when RL should be most effective along a pretraining trajectory.

Long-context decoding is increasingly limited by KV-cache memory traffic since each generated token attends over a cache whose size grows linearly with context length. Existing sparse decoding methods reduce this cost by selecting subsets of tokens or pages, but are designed for softmax attention, whose dense tails make any truncation discard nonzero probability mass. In contrast, $α$-entmax produces exact zeros, turning sparse decoding from dense-tail approximation into support recovery: if the selected candidates contain the entmax support, sparse decoding remains exact. While recent entmax kernels enable efficient training, they do not address the autoregressive decoding bottleneck, where dense inference still streams the full KV cache before sparsity is known. In this work, we introduce EntmaxKV, an entmax-native sparse decoding framework that exploits sparsity before KV pages are loaded. EntmaxKV combines query-aware page scoring, support-aware candidate selection, and sparse entmax attention. We analyze truncation error through the dropped probability mass $δ$, showing that output error is controlled by $δ$ and vanishes when the entmax support is recovered. We further introduce a Gaussian-aware entmax selector that estimates the entmax threshold from lightweight page statistics, adapting the selected budget to the score distribution. Empirically, EntmaxKV drops less probability mass, retains more support tokens, and achieves lower output error than softmax-based sparse decoding at matched KV budgets. On long-context and language modeling benchmarks, it closely matches full-cache entmax while using a small fraction of the KV cache, achieving up to $3.36\times$ (softmax) and $5.43\times$ (entmax) speedup over full attention baselines at 1M context length. Code available at: https://github.com/deep-spin/entmaxkv.

The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely on entities that can be easily identified verbally, like household objects, animals, human subjects, etc., limiting their applicability to complex, in-the-wild video scenarios. But, many applications such as furniture assembly, cooking, etc., require step-by-step fine-grained spatio-temporal understanding of the video, which is not sufficiently evaluated in current benchmarks. To address this gap, we introduce Flat-Pack Bench, a novel benchmark centered on furniture assembly tasks. Our benchmark evaluates LVLMs on nuanced tasks, including temporal ordering of assembly actions, temporal localization of assembly state, understanding part mating, and tracking, using multiple-choice questions paired with visual prompts highlighting relevant parts as references for fine-grained questions. Our experiments reveal that state-of-the-art LVLMs struggle significantly with fine-grained spatio-temporal reasoning, highlighting their limitations in effectively leveraging temporal information from videos, limited tracking ability, and understanding of spatial interactions like physical contact.

Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.

Autonomous manipulation systems have achieved remarkable capabilities, yet the integration of human expertise with diffusion-based policies in shared control remains relatively unexplored. In this paper, we propose Human-In-The-Loop Diffusion (HITL-D), a shared control framework that enhances user performance in multi-step, insertion, and fine manipulation tasks. HITL-D leverages a novel combination of diffusion-based policies and human control to provide autonomous end effector orientation updates conditioned on a scene point cloud and the Cartesian position of the end effector. This approach reduces the number of joystick control axes required, thereby lowering mental workload. In a multi-task user study with 12 participants, HITL-D reduced average task completion times by 40%, decreased perceived workload by 37%, and improved Likert-scale ratings for independence, intuitiveness, and confidence compared to traditional teleoperation methods. These results demonstrate that HITL-D effectively integrates human expertise with autonomous assistance, improving both objective and subjective aspects of teleoperation.

Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world sensor degradation. In this paper we present a controlled perturbation study of Vision-Language-Action (VLA) robustness in autonomous driving, evaluating Alpamayo R1 (10B parameters) across 1,996 scenarios under eight sensor perturbations (Gaussian noise at four intensities, two lighting extremes, and two fog levels; ${\sim}18{,}000$ inference trials). We find that reasoning consistency is a high-fidelity indicator of trajectory reliability: when Chain-of-Causation (CoC) explanations change after perturbation, trajectory deviation spikes $5.3{\times}$ (21.8m vs 4.1m), with $r\!=\!0.99$ across attack types and $r_{pb}\!=\!0.53$ per-sample (Cohen's $d\!=\!1.12$). A controlled ablation provides evidence that enabling CoC generation is associated with improved trajectory accuracy (11.8% on average across conditions; $p < 0.0001$) under matched inference settings. Over the tested noise range ($σ\in \{10, 30, 50, 70\}$), degradation is approximately linear ($R^2\!=\!0.957$), while standard input preprocessing defenses provide only marginal relief. Together, these results establish CoC consistency as a quantitative proxy for planning safety and motivate reasoning-based runtime monitoring for safer VLA deployment.

Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (\texttt{roto 2.0}), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations, which limit their ability to reason about fine-grained geometry and spatial grounding - capabilities that are essential for precise and robust manipulation in 3D environments. In this paper, we propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process. PointACT employs a multi-scale point-action interaction mechanism with efficient bottleneck window self-attention, enabling evolving action tokens to densely attend to both local geometric detail and global scene structure. We evaluate PointACT on the LIBERO and RLBench benchmarks and systematically compare it against monolithic and dual-system VLA baselines, including variants augmented with point cloud inputs. PointACT achieves consistent improvements across both benchmarks, increasing success rates by 10% on the challenging RLBench-10Tasks suite over state-of-the-art pretrained VLAs, with even larger gains when the vision-language backbone is frozen and the action expert is trained from scratch. Extensive ablation studies demonstrate that tightly coupling hierarchical 3D geometry with pretrained 2D semantic representations is critical for robust and spatially grounded robot control. Our results also highlight the promise of pretrained 3D representations for 3D-aware VLA policies.

Accurate registration between a prior model and the real scene is essential for high-precision robotic manipulation, yet optical methods suffer from long calibration chains, line-of-sight constraints, and fabrication errors. We propose a calibration-free alternative that reformulates contact registration as complementary-shape docking between the object and the probe's swept volume, explicitly accounting for probe geometry and leveraging both contact and non-contact evidence. Our solver integrates a global-to-local search via 3D FFT correlation over low-discrepancy SO(3) samples, then followed by continuous SE(3) refinement using Lie-algebra updates and analytic contact sensitivities. This pipeline yields efficient exploration and metric-grade convergence without fragile point correspondences. Simulation across free-form meshes achieved sub-0.04 mm and sub-0.4° accuracy and robustness to pose noise and contact loss. On a tooth-preparation robot, our method attained 0.42 mm and 3.75°, outperforming an optical tracker registration while requiring no external sensors. These results demonstrate a practical and precise registration strategy for surgical and industrial robots.

In-hand object manipulation is a fundamental yet challenging capability for dexterous robots. Despite significant progress in dexterous manipulation, existing approaches rely heavily on vision or tactile sensing to track object states, while joint sensing -- the most readily available modality on any robotic hand -- remains largely overlooked, particularly for tendon-driven hands. In this paper, we study how far joint sensing alone can go by asking: (i) whether motor encoders or direct joint sensing provides better proprioceptive feedback, (ii) how to extract environment information from joint measurements, and (iii) whether joint-only control can achieve competitive real-world performance without external perception. We present the Proprioceptive Transformer (PT), an exteroceptive-free approach for continuous cube rotation on a tendon-driven dexterous hand that uses only joint sensing feedback. A teacher policy is first trained via reinforcement learning with privileged object information, then distilled into PT, which operates solely on joint position and velocity histories. The Transformer architecture effectively extracts implicit object state information from temporal patterns in joint sensor readings. Experiments on the real ORCA hand show that our approach achieves 3.1x higher rotation speed than baselines. We also demonstrate that our PT achieves a 23.4% lower RMSE for cube position estimation than the MLP baseline, indicating superior extraction of exteroceptive information from proprioceptive sources.

Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental representation through shared sensory data. While recent works have advanced multi-agent fusion for improved perception, uncertainty quantification in such cooperative frameworks remains largely unexplored. This paper introduces Hyper-V2X, a hypernetwork-based framework for estimating both epistemic and aleatoric uncertainties in V2X-based perception. Specifically, we propose a partial weight generation scheme and V2X context embedding module that conditions a Bayesian hypernetwork on fused multi-agent features to generate weight distributions for stochastic Bird's-Eye-View (BEV) segmentation. Unlike existing deterministic BEV models, Hyper-V2X enables efficient uncertainty estimation with little computation overhead. Our approach is architecture-agnostic, and can be seamlessly integrating with modern cooperative backbones such as CoBEVT. Experiments on the OPV2V benchmark demonstrate that Hyper-V2X provides accurate, well-calibrated uncertainty estimates and improves overall perception reliability. Our code and benchmark are publicly available under an open-source license: https://github.com/abhishekjagtap1/Hyper-V2X

Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit representations, while expressive, lack explicit structural cues, whereas explicit ones preserve geometry but suffer from resolution limits and weak generalization. To address these limitations, we propose a novel pretraining framework that learns a hybrid representation-structural latent points. Specifically, we insert a point-wise latent variational autoencoder into the latent space of a point-cloud autoencoder, jointly regularizing point-wise features and coordinates toward a Gaussian prior. The resulting compact latent preserves coarse structural tendencies, which do not encode precise geometry but capture richer rough shape and semantic information, effectively combining the expressiveness of implicit representations with the structural priors of explicit ones. In addition, informed by shared design choices in prior work, we develop a streamlined, efficient 3DGS-based rendering pipeline that is deliberately kept lightweight, improving efficiency while leaving greater representational capacity to the front-end latent module. Extensive evaluations on RLBench, ManiSkill2, and a real-robot platform demonstrate consistent gains in task success, sample efficiency, and robustness to viewpoint and scene variations over strong baselines. Ablation studies further confirm that each component of our framework is critical to overall performance.

As robot fleets become more heterogeneous, including humanoids, rovers, quadrupeds, and drones, selecting the right robot for a task becomes a core systems problem. We study robot skill prediction: mapping a natural-language task description to the physical capabilities required to execute it, such as fly, wheels, legs, surface water, under water and hands. Since labelled data that maps natural-language task descriptions to robot's physical capabilities does not exist, we construct a synthetic task-to-skill dataset using LLM-assisted generation and targeted label auditing. Trained on this data, a ~133M-parameter ensemble of two fine-tuned sentence encoders (mpnet + MiniLM) reaches 83.5% task-to-skill matching on a stratified 200 task dataset, outperforming Kimi K2 (1T MoE) at 72.0%, GPT-OSS-120B at 71.5%, and Llama-4-Scout-17B at 69.0% under the same zero-shot prompt. These results suggest that, for fixed robot skill taxonomies, small specialized models trained on synthetic data can outperform much larger general-purpose LLMs for fleet-level task routing.

In this work we present an efficient and practically implementable approach for the application of reinforcement learning (RL)-based control in chemical process systems. This is an area that has yet to widely adopt RL-based control largely due to inherent challenges in trusting RL algorithms and the time-consuming process of training reliable agents. To address these challenges, we leverage a class of RL algorithms termed Y-wise Affine Neural Network (YANN)- RL, which we have developed in our prior work (Braniff and Tian, 2025a). By strategically initializing actor and critic networks YANN-RL algorithms provide confident and interpretable starting points within control schemes. We apply this RL-based control approach to three different process engineering case studies publicly available on the PC-Gym library (Bloor et al., 2026): (i) a continuous stirred tank reactor (CSTR), (ii) a four-tank system, and (iii) a multistage extraction column. Our approach is compared to several popular RL algorithms (PPO, SAC, DDPG, and TD3) and is benchmarked against nonlinear model predictive control (NMPC). These case studies demonstrate that YANN-RL can greatly reduce the training time and data needed, can be deployed with confidence for chemical process systems, and can approach the performance of NMPC without the knowledge of a full nonlinear model.

In this paper, we explore spatial-aware humanoid whole-body manipulation task. Compared with tabletop settings, this task poses two key challenges: 1) Spatial understanding is challenging in complex 3D environments with diverse spatial relations. 2) Action generation is difficult to generalize, as limited and costly real-robot data restricts data-driven models generalization. To address these challenges, we propose a generalizable humanoid loco-manipulation framework that leverages the spatial perception and action generation capabilities of multi-agent large models. Specifically, our framework includes two components: Active Spatial Brain for active spatial perception and decision-making, and Generalizable Action Cerebellum for executable robot action generation. The first component actively perceives the spatial scene and makes decisions on task planning and subtask decomposition. The second component generate executable robot actions based on the decisions made by the first module without needs of task-specific real robot data. To benchmark our framework, we design a set of spatial manipulation tasks from two perspectives: evaluating spatial perception and understanding, and assessing real-robot task performance. The results demonstrate strong performance on both aspects across diverse tasks and environments.

Feedforward steering control is a key component of hierarchical control architectures for autonomous racing. The goal is to reduce steering corrections from the feedback controllers by predicting the vehicle's inverse lateral dynamics. This paper presents a systematic benchmark of two learning-based and two empirical (analytical) feedforward steering controllers. We introduce a new \acf{ehd} formulation based on a polynomial surface fit that captures velocity-dependent nonlinear steering behavior with minimal parametrization. We test the feedforward controllers in a high-fidelity simulation framework based on the real-world Abu Dhabi Autonomous Racing League competition, using a high-fidelity double-track vehicle dynamics simulator. Open-loop evaluation shows that the learning-based controllers achieve the lowest prediction errors; however, closed-loop testing reveals that this improved accuracy does not translate into superior path tracking performance or lap times, even after iterative fine-tuning. In contrast, the proposed EHD approach achieves the best overall closed-loop robustness and lap time, highlighting the necessity of evaluating feedforward strategies within the complete trajectory planning and control software stack. Our code is available at https://github.com/TUMRT/steering_ff_control.

Reliable confidence estimates are important for safely deploying vision-based controllers in autonomous racing, where safety predictions must be derived from camera images, yet modern predictors become dangerously overconfident under test-time distribution shifts. We identify a critical perception-dynamics gap in existing anomaly signals: widely used scores, such as autoencoder reconstruction error, capture visual corruptions but miss dynamics anomalies (e.g., actuation bias, latency), where images remain plausible while the trajectory degrades. To address this, we propose an Anomaly-Informed Online Calibration approach that, without retraining any model component, fuses two complementary anomaly scores extracted from a world model: a perceptual score from reconstruction error and a dynamics score from epistemic uncertainty and control-stream statistics. Based on these fused scores, a lightweight temperature-scaling calibrator leverages test-time augmentation to selectively reduce overconfidence under shift while preserving nominal-condition performance. Experiments on a physical DonkeyCar under four real-world anomaly protocols unseen during training (darkness, blur, actuation bias, processing latency) reduce average expected calibration error from 0.184 to 0.116, a 37% improvement over the best baseline, without modifying the base safety predictor.

Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe bandwidth constraints. Many communication architectures still expose a coupled bottleneck in which a shared latent representation is used for both policy execution and inter-agent communication. Consequently, reducing message size directly limits the policy's latent space, often leading to significant performance degradation. We address this with two contributions. First, we introduce $β$, a normalised per-agent bandwidth budget that unifies sparsity, rounds, and message dimension into a single comparable constraint. Second, we provide SLIM, a minimal architecture that decouples the communication pathway from the policy's latent representation, allowing us to isolate the effect of bandwidth from the effect of policy capacity while benefiting from in-step communication. We evaluate our method on several partially-observable MARL benchmarks, where communication is essential. Our approach achieves state-of-the-art performance and exhibits scalability and robustness under limited communication, with only marginal degradation as bandwidth is reduced.

Materials discovery and biomedical translation increasingly require models that can reason across composition, processing, structure, biological response, manufacturability, safety, and governance constraints. Existing materials and biomedical data ecosystems are powerful but remain poorly coupled for AI-guided discovery. Here we present AIMBio, a conceptual framework for an AI-native, FAIR, and governance-aware decision layer that links materials provenance, biomedical context, knowledge graphs, uncertainty-aware machine learning, and human-in-the-loop active learning. The framework formulates biomedical-materials discovery as constrained multi-objective optimization under uncertainty and introduces practical requirements for metadata, model documentation, risk-tiered governance, evaluation metrics, and phased implementation. To make the roadmap testable, we add a minimum viable prototype specification and a worked pilot for AI-guided nanomaterials for drug delivery. AIMBio is positioned as exploratory and preclinical discovery infrastructure, not as clinical decision-support software; any clinical or regulated-device use would require separate validation, change control, and regulatory review. The central contribution is a publishable platform blueprint for converting fragmented materials and biomedical records into auditable, experimentally actionable, and translationally responsible discovery workflows.

Thin-film lithium niobate (TFLN) electro-optic modulators are attractive for high-speed optical interconnects, but scalable transmitter architectures require not only high modulation bandwidth but also multi-channel optical power distribution and practical laser-to-chip integration. Here, we demonstrate a hybrid-integrated 1 * 8 TFLN electro-optic modulator array passively butt-coupled to a 1550 nm distributed-feedback laser. The chip integrates a three-stage cascaded 1 * 2 multimode-interference splitter, spot-size converters, eight traveling-wave Mach-Zehnder modulators, thermal tuning electrodes, and on-chip 50 Ω terminations. The cascaded splitter provides uniform optical power distribution with a maximum normalized power deviation of 9.7%, while the optimized electrodes enable electro-optic 3 dB bandwidths exceeding 40 GHz for all channels. The measured half-wave voltages are 3.60-3.83 V, corresponding to VπL products of 2.52-2.68 V cm for a 7 mm modulation length, and the extinction ratio reaches approximately 25 dB. The bare-chip insertion loss is 15.19-16.55 dB, and DFB laser bonding introduces an additional coupling loss of approximately 5 dB while preserving channel uniformity. These results establish a practical TFLN-based multi-channel modulator platform and represent a step toward compact hybrid-integrated optical transmitters for high-speed parallel interconnects.

Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs more than an order of magnitude larger, on both the closed-loop NAVSIM-v2 and the nuScenes benchmarks. Extensive analysis further shows that this improvement stems from a recovered ability to exploit visual features, with the effect being most pronounced in dynamic driving situations such as turning.

Wheeled-legged robots, which have wheels at their feet and achieve high mobility by coordinating wheel drive and leg drive, have been developed. These robots have been developed purely as platforms specialized for locomotion. Therefore, they do not have a means to repurpose their legs for roles other than locomotion, such as object manipulation or tool utilization. In this paper, we address the problem of how to draw out the potential task-execution capability of the legs by freeing them from the roles of locomotion through external body support. To this end, we propose and develop a new robot, WiXus, which fuses a wheeled-legged mechanism with a wire-driven mechanism that utilizes the external environment. The developed WiXus demonstrates not only planar locomotion with wheeled-legged drive, but also three-dimensional mobility such as cliff climbing by coordinating wire-driven and wheeled-legged actuation. Furthermore, by suspending the body with wire-driven actuation, WiXus successfully repurpose its legs as arms to perform object manipulation, (e.g., rescuing a dog (stuffed animal)), and tool utilization (e.g., harvesting an apple (mockup) with loppers). This study demonstrates that the approach of utilizing the environment with wire-driven actuation is a new design principle that extends the operational domain of wheeled-legged robots.

We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based decentralized Multi-Agent Path Finding (MAPF) in discrete environments. Given a pretrained decentralized policy, STEAM requires no retraining, architectural modification, or replacement by a centralized planner. Instead, it injects lightweight congestion-aware guidance into the original policy execution. STEAM first rolls out the shortest paths induced by the current cost-to-go maps to identify potential future congestion hotspots. Spatially avoidable congestion is mitigated by updating agent-specific cost-to-go information, while spatially unavoidable bottlenecks are handled through temporal logit correction. In addition, emergent local congestion is reduced by a density-aware logit correction based on neighboring agents' corrected cost-to-go maps. Extensive experiments on representative learning-based decentralized MAPF algorithms show that STEAM consistently improves success rate, makespan, and solution cost, with success-rate gains of up to 60% and only minor computational overhead. The implementation is available at https://anonymous.4open.science/r/STEAM-MAPF-7A62.

Subterranean (SubT) environments have been a frontier for autonomous robotics, driven by the push for automation of mining operations and the interest in planetary exploration (Martian Lava Tubes). Due to the challenges involved in accessing real SubT environments, rigorous hardening of autonomy stacks in realistic simulation environments is critical. This article fills a well-known gap, which relates to the unavailability of a large-scale simulation-based benchmarking infrastructure for rigorous statistical evaluation of robotic autonomy, due to which it is common for SubT research articles to present validation results in a few environments at best. This article presents SubTGraph, a novel framework for rapid synthesis of multi-level SubT environments with high variability, incorporating user specifications related to topology, dimensionality, textures, etc., to generate distinct environments such as operational mines, natural caves and lava tubes. SubTGraph builds a cost matrix from user-specified structural constraints to guide the classical Dijkstra algorithm to procedurally generate SubT worlds utilizing topometric tiles from the DARPA World Generator. Three robotics case-studies are investigated to demonstrate the utility of SubTGraph for rigorous validation of different layers in the robotic autonomy stack. Structural semantic segmentation is validated against topometric ground truths, multi-agent path planning is widely tested for identification of patterns and trends in the algorithm behavior and LIO SLAM is stress-tested in challenging subterranean sections to identify failure cases. The SubTGraph world creation codebase is open-sourced (https://github.com/LTU-RAI/SubTGraph.git) along with a database consisting of 150 highly variable underground worlds.

Mobile imitation learning on portable demonstration interfaces faces two coupled bottlenecks: locomotion-contaminated action labels and inference-induced execution latency on a continuously moving base. Recent wrist-mounted interfaces lower the cost of tabletop data collection, yet a single wrist view does not capture the global context required for base navigation. Adding a body-mounted camera entangles human walking with hand motion. Meanwhile, generative policies introduce hundreds of milliseconds of inference latency, during which the base advances past predicted waypoints, forcing backward corrections at action splices. This paper presents Mobile UMI, a hardware-free demonstration framework that addresses both gaps through three components. First, a dual-camera capture system records chest-centric global context and wrist-centric local interaction without any robot present. Second, a one-shot ChArUco-based spatial anchor unifies the chest and hand visual-inertial frames; the hand pose is then re-expressed relative to the chest to extract decoupled SE(3) manipulation and SE(2) base trajectories. Third, an asynchronous receding-horizon executor performs online state matching: each generated action chunk is realigned with the current physical pose so that expired waypoints are discarded before execution. The full system is evaluated on four long-horizon household tasks, achieving an average success rate of 83.8% over 100 trials per task. Controlled comparisons against ACT and Diffusion Policy show that the chest-relative label alone closes much of the gap; online state matching closes the remainder. These results indicate that, for mobile imitation learning under the tested conditions, explicit kinematic factorization combined with state-level latency alignment provides an effective solution without requiring architectural changes to the underlying policy class.

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or recover from failures at runtime. We present a tiered KV cache architecture that enables runtime-certified attention: INT8 keys and INT4 values are stored in GPU memory, while FP16 originals are retained in system RAM for deterministic fallback. A two-term error decomposition yields per-head, per-step bounds on (i) attention distribution distortion from key quantization and (ii) value reconstruction error. These bounds are computed online and used to drive adaptive precision selection and a multi-stage fallback ladder, which guarantees recovery to the exact dense attention output when required. Across PG-19, NIAH, and RULER benchmarks on LLaMA~3.1-8B with contexts up to 128K, the system matches dense FP16 KV quality within noise for language modelling and retrieval tasks, while recovering catastrophic failures observed in naive INT8/INT4 baselines. Value-sensitive tasks at short context expose a controlled trade-off between compression and fidelity, which can be eliminated via tighter value tolerances or FP16-value fallback. The certification is local (per-head, per-step) and does not guarantee end-to-end model correctness, but ensures that each attention computation is either bounded relative to an FP16 reference or exactly recovered via fallback. This reframes KV cache quantization as a runtime-verified computation rather than a fixed approximation. The goal is not raw speedups, but enabling safe deployment of aggressive KV compression under strict quality constraints.

Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analytical perspectives needed vary across samples due to the diversity of sarcastic mechanisms. While recent methods make this analytical process explicit, they still rely on fixed, predefined perspectives that operate independently under hand-crafted routing rules. We argue that multimodal sarcasm detection instead calls for self-elicited multi-perspective reasoning, where a model autonomously generates the perspectives needed for each sample and progressively integrates them into a coherent analysis. To realize this goal, we propose ProCrit, a Proposal-Critic two-agent framework with a proposal agent for multi-perspective reasoning and a critic agent for external evaluation and targeted revision guidance. First, to overcome the lack of process-level supervision in existing sarcasm datasets, ProCrit synthesizes process-level reasoning annotations through a dynamic-role agentic rollout: a strong vision-language model sequentially spawns analytical roles within a shared context, and the resulting multi-role trajectories are flattened into sequences that preserve cross-perspective dependencies while enabling efficient autoregressive generation. Second, to improve reasoning reliability, ProCrit adopts a draft-critique-revise paradigm in which an independent critic identifies reasoning deficiencies and provides targeted natural-language feedback for directed revision. Finally, we develop a mutual-refinement training framework that jointly optimizes proposal drafting and feedback-guided revision via dual-stage reinforcement learning, while refining the critic agent according to the actual effectiveness of its feedback. Experiments on three widely used benchmarks demonstrate the effectiveness of ProCrit.

Language-conditioned manipulation policies typically process instructions and observations through shared network parameters. This task-state entanglement provides a pathway for observation leakage -- networks learn scene-to-action shortcuts that bypass language grounding entirely. DISC eliminates this failure structurally. Rather than conditioning a universal policy on language, DISC uses a hypernetwork to generate the entire parameter set of a task-specific visuomotor policy from the instruction alone. The generated policy never directly accesses language; therefore, its task-awareness must come from the language. Consequently, observation leakage has no pathway to emerge. On the other hand, generating coherent high-dimensional policy weights is itself a challenging problem. We address it with a two-stage hypernetwork whose refinement stage embeds the structure of gradient-based optimization as a feed-forward inductive bias, producing globally consistent parameters without actual gradient computation. Trained entirely from scratch on standard data budgets, DISC outperforms all entangled baselines on LIBERO-90 and Meta-World, with advantages that widen on complex, long-horizon tasks -- and surpasses the large-scale pretrained $π_0$ despite using no external pretraining data. On a real-world benchmark where all tasks share identical visual context, DISC substantially outperforms entangled alternatives, directly confirming that language-generated policy parameters, not visual shortcuts, drive behavior. The hypernetwork further learns a semantically structured parameter manifold that enables few-shot adaptation from minimal demonstrations and robust generalization across paraphrased instructions. Our code is available at: {https://github.com/ReNginx/DISC}.

Silicon photonic integrated circuits critically depend on compact on-chip light sources, for which nanowire (NW) lasers are an attractive solution. However, their practical implementation is often limited by broad emission linewidths and poor frequency stability resulting from weak optical feedback. Here, we integrate individual GaAsSb NWs by transfer-printing onto silicon-on-insulator (SOI) racetrack resonators to realize optical feedback at silicon-transparent wavelengths. Finite-difference-time-domain simulations reveal efficient coupling between the hybrid NW-waveguide mode and the fundamental TE resonator mode, with calculated cavity Q-factors exceeding 10$^4$. Experimentally, we observe feedback-induced lasing emission at a low threshold (P$_{th}$) of 8.6 $\pm$ 1.8 $μ$J/cm$^2$. Compared to identical NW lasers without SOI resonator, the linewidth is reduced by more than a factor of four at 3P$_{th}$ and remains stable below 1.8 meV up to 5P$_{th}$. Our results demonstrate NW-based light sources on SOI and show that tailored resonator designs enable improved linewidth control and frequency stabilization.

Detecting what has changed in an environment is essential for long-term autonomy, yet most change detection settings assume fixed viewpoints, mild misalignment, or only a few changed objects. We introduce Video-based Scene Change Detection (VSCD), which predicts a pixel-wise change mask for each query frame, given a reference and a query RGB video of the same indoor space recorded at different times under unconstrained camera motion. The two videos are not temporally synchronized, and many object instances may appear or disappear. To study this setting, we build a large-scale benchmark with over 1.1 million frames annotated with pixel-accurate change masks, together with a real-world test set for evaluating transfer beyond simulation. We propose a query-centric multi-reference model that learns temporal matching implicitly from change-mask supervision, aligns candidate reference features to the query via local patch correspondence, and fuses per-candidate change features using frame-level and patch-level confidence before decoding a high-resolution mask once per frame. Our approach achieves state-of-the-art performance against strong image- and video-based baselines, and we validate its real-world impact by deploying it on a mobile robot for two downstream applications -- visual surveillance and object incremental learning.

Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or action spaces, this action-centric view requires shared action spaces, heuristic retargeting, or large-scale multi-embodiment co-training. We instead view demonstrations as implicit specifications of future goals: the target agent should infer what state the demonstrator is trying to realize, rather than how the demonstrator executes it. We propose Demo-JEPA, a cross-embodiment imitation framework that decouples demonstration intent from embodiment-specific execution. Built on a JEPA-based world model, Demo-JEPA translates source visual demonstrations into target-compatible future latent trajectories in a shared predictive representation space. The target agent then uses these latent trajectories as subgoals and realizes them through planning under its own learned forward dynamics. Because Demo-JEPA avoids action-level correspondence and requires only visual demonstrations plus the target agent's own interaction experience, it supports flexible imitation across heterogeneous embodiments. Experiments on RLBench and real-world manipulation tasks show that Demo-JEPA matches specialized in-domain planners and generalizes to unseen tasks and embodiment configurations where prior methods fail.

Adaptive robot navigation in dynamic environments requires policies that can reach the target reliably while producing efficient and stable trajectories. This paper presents Q-SpiRL, a quantum spiking reinforcement learning framework for obstacle-aware robot navigation. The framework develops and evaluates five agent families: tabular Q-learning, classical MLP, classical SNN, quantum-enhanced MLP (QMLP), and quantum-enhanced spiking neural network (QSNN). While all models are implemented under a unified training and evaluation pipeline, the QSNN is the central architecture of interest, as it combines spike-based temporal processing with variational quantum feature transformation. Experiments are conducted across three grid-world environments of increasing size, namely 20x20, 30x30, and 40x40, with both static and dynamic obstacles. Performance is assessed using success rate, success-weighted path length, path length, and turn rate under deterministic inference. Results show that QSNN achieves the strongest overall trade-off between task completion, trajectory efficiency, and motion smoothness, reaching up to 99% success rate while maintaining high path efficiency in the most challenging setting. Execution on IBM quantum hardware further demonstrates the feasibility of deploying the proposed hybrid policy under real-device conditions.

Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, but their real-world evaluation remains limited by a lack of accessible, reproducible, and consistent benchmarks. Simulation benchmarks fail to capture real-world complexity, while existing real-world benchmarks often require expensive hardware, centralized evaluation, or are limited in task diversity. We introduce VLA-REPLICA, a low-cost, easily reproducible real-world benchmark for evaluating VLA models. Built from off-the-shelf components, our system can be quickly assembled and replicated across laboratories, providing a consistent environment for policy evaluation anywhere in the world. VLA-REPLICA includes a diverse suite of manipulation tasks and a small-scale demonstration dataset for target-domain adaptation, with real-world evaluation protocols for both in-distribution and out-of-distribution settings. Experiments with imitation learning and state-of-the-art VLA models reveal model strengths and limitations, while consistent results across independently constructed setups demonstrate the reproducibility of our benchmark.

Temporal ghost imaging (TGI) enables ultrafast temporal signal recovery using slow detectors, offering a promising route for high-speed mid-infrared (MIR) detection. However, conventional schemes remain limited in temporal resolution by the modulation bandwidth or pattern timescale, and are mostly confined to structured illumination. Here, we demonstrated a high-resolution MIR single-photon computational TGI system, which integrated nonlinear structured detection with sub-pixel temporal shifting. A pre-programmed near-infrared pump serves as a temporally optical gate to drive sum-frequency generation in a nonlinear crystal. Consequently, MIR waveforms at 3.4 $μ$m were upconverted, and captured by a room-temperature silicon detector. We realized sub-pixel operation by fractional-bin temporal stepping of the gate and multi-shot fusion via pseudo-inverse reconstruction. The sub-pixel shifting strategy decouples the achievable resolution from modulation speed, enabling 40 ps temporal precision at a driving rate of only 3.125 Gbps. This performance surpasses both detector jitter and pattern-rate limits, while maintaining single-photon sensitivity. The presented paradigm establishes a versatile route for ultrafast MIR waveform reconstruction, opening new opportunities in high-resolution infrared sensing and quantum photonics.

Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-language models to action generation. Yet, standard action-imitation training often provides limited explicit supervision for 3D geometry, dense visual structure, and short-horizon environment evolution, which are critical for physically precise manipulation. We introduce \textbf{GaussianDream}, a feed-forward 3D Gaussian world-model plug-in that turns robot trajectories into structured spatial-temporal supervision. The key idea is to couple current Gaussian reconstruction with horizon-conditioned future Gaussian prediction during training, forcing a compact spatio-temporal prefix to be decodable into renderable 3D Gaussian states. This enables dense RGB rendering, depth, and pseudo 3D scene-flow supervision without requiring test-time Gaussian decoding. At inference, GaussianDream discards all auxiliary decoding heads and retains only the learned prefix to condition action generation, avoiding rendering, video rollout, or additional planning during closed-loop control. Experiments on LIBERO, RoboCasa Human-50, and real-robot tasks demonstrate strong and highly competitive performance, achieving \textbf{98.4\%} average success on LIBERO, \textbf{52.6\%} on RoboCasa Human-50, and \textbf{50.0\%} in real-world evaluation.

Autonomous AI agents that spawn sub-agent swarms create a safety gap: existing credential revocation mechanisms, OAuth~2.0 introspection, OCSP, and W3C Status Lists, require network connectivity to a central authority, leaving ``zombie agents'' executing privileged operations for minutes to hours after operator shutdown. We present Heartbeat-Bound Hierarchical Credentials (HBHC), a cryptographic protocol that binds credential validity to periodic parent liveness proofs. Verifiers enforce freshness using only a cached public key and local clock; no network round-trip is required. When heartbeat generation ceases, all descendant credentials become unusable within a deterministically bounded window $W_z \le W_{\max} + Δ_h + ε$, conditional on bounded clock skew and parent keys held in secure enclaves. Evaluation at the protocol layer and with real LLM-backed agent swarms (GPT-4o-mini) demonstrates a 90$\times$ reduction in the zombie window over OAuth~2.0, 0.26~ms full authentication in Rust, 18,000+ verifications per second under concurrent HTTP load, and stable per-verification latency from 10 to 10,000 agents. Real-agent experiments show 0.71\% end-to-end overhead on tool calls, zero post-revocation tool calls under prompt injection that bypasses application-layer guardrails, and cascading revocation across a 49-agent four-level hierarchy within the theoretical bound.

Advanced Air Mobility (AAM) operations are expected to significantly increase aerial traffic in urban airspace, requiring autonomous traffic management systems to ensure collision-free operations in highly congested environments. In this paper, we propose a multi-agent coordination framework that uses minimum time-to-reach (TTR) as a unifying metric for priority assignment, temporal separation, and safety filtering. We focus on the problem of coordinating multiple aerial vehicles merging into an air corridor while maintaining safe separation between vehicles. Vehicles are assigned arrival-consistent priority based on TTR, and target TTR values are used to enforce temporal spacing that induces spatial separation. A priority-consistent safety filtering layer based on Hamilton-Jacobi reachability value functions ensures collision avoidance while minimally modifying the reference guidance. Simulation results in a highly congested corridor merging scenario show that the proposed method improves safety, fairness, and efficiency compared to time-optimal guidance and priority-agnostic safety filtering.

Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase concurrently, their changes can silently conflict and inconsistent views lead to integration failures. Existing multi-agent systems address this through workspace isolation (e.g., one git worktree per agent), but this defers conflict resolution to a post-hoc merge step where recovery is expensive. In this paper, we propose STORM, i.e., STate-ORiented Management for multi-agent collaboration. Specifically, STORM manages agent states by mediating their interactions with the shared workspace, ensuring that each agent operates on a consistent view of the codebase and that conflicting edits are detected and resolved at write time. We evaluate STORM on Commit0 and PaperBench across multiple LLMs. STORM outperforms the git-worktree-based multi-agent baseline by +18.7 on Commit0-Lite and +1.4 on PaperBench, while achieving comparable or better cost efficiency. Combined with single-agent runs, STORM reaches highest scores of 87.6 and 78.2 on the two benchmarks respectively, suggesting that explicit state management is a more effective foundation for multi-agent collaboration than workspace isolation. STORM can also be plugged into any multi-agent system seamlessly.

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error propagation, where early-stage information degrades downstream reasoning. To address this, we conduct a systematic analysis of inter-agent communication to identify which information drives MA performance. We find that the absence of reasoning and verification in inter-agent communication significantly degrades performance. Based on these insights, we propose Category-Aware Recovery Augmentation (technique), which enforces the presence of critical information during communication. recovers up to 86.2% of failed cases. Our results highlight the key role of information quality in effective MA collaboration. Our code is available at https://anonymous.4open.science/r/cara_mas

Agentic AI coding systems can inspect repositories, plan implementation steps, edit files, call tools, run tests, and submit pull requests. These capabilities make software and hardware development faster in some settings, but current evidence does not support the simple claim that autonomous code generation automatically improves engineering outcomes. Controlled studies report productivity gains in some enterprise tasks, slowdowns in mature open-source work, moderate but heterogeneous meta-analytic effects, and persistent failures in repository setup, dependency handling, permission gating, and hardware verification. This paper argues that the central problem is no longer prompt engineering; it is engineering process control. It synthesizes evidence from agentic software engineering, GitHub-scale adoption studies, repository-level agent configuration, productivity trials, issue-resolution benchmarks, and hardware/RTL verification research. It proposes Agentic Agile-V, a process framework that uses Agile-V as the lifecycle backbone and a task-level SCOPE-V loop - Specify, Constrain, Orchestrate, Prove, Evolve, and Verify - to convert conversational intent into structured engineering artifacts and acceptance evidence. The paper contributes: (i) a taxonomy of minimum input artifacts for agentic software, firmware, and hardware work; (ii) a conversation-to-contract gate that separates exploratory dialogue from implementation; (iii) risk-adaptive feature, bug-fix, testing, and hardware workflows; and (iv) an evidence-bundle acceptance model for agent-generated artifacts. The paper concludes that agentic AI does not eliminate engineering discipline; it increases the value of requirements, constraints, traceability, independent verification, and human approval.

TiO2 ferroelectric field effect transistors (FeFETs) with HfZrO2 (HZO) ferroelectric dielectric layers and bottom gate topology are fabricated for applications in neuromorphic systems. Two sets of devices are fabricated with different gate topologies by varying the thickness of the ferroelectric gate stack. Different device architectures are studied by varying the source drain length (LSD) and gate length (LG). The devices have high on/off ratios up to 10^7 with low leakage off currents <10^-12 A. Repeated cycle testing shows high reliability and a stable memory window. The devices have large memory windows ranging from 3 to 8 V.

One central theme in quantum photonics is tailoring the interactions between atoms/spins and their electromagnetic (EM) environments. Considerable effort has focused on engineering spontaneous emission by shaping EM environments, known as the Purcell effect. However, photonic environment control of pure dephasing, which is a complementary paradigm of non-unitary atom/spin couplings with EM environments, remains largely unexplored. Here, we introduce a nanophotonic approach to modify qubit pure dephasing dynamics. Unlike Purcell engineering that tailors photonic environments at qubit resonance frequencies (typically optical/near-infrared), we develop ultra-subwavelength spin noise metasurfaces for efficient broadband control of low-frequency (e.g., $\sim$MHz) photonic environments far off-resonant with atoms/spins for dephasing engineering. We experimentally demonstrate our approach using lithographically defined CoFeB metasurfaces and shallow nitrogen-vacancy (NV) centers in diamond. Instead of modified spontaneous emission, we observe modified NV pure dephasing dynamics near different spin noise metasurfaces. We further isolate metasurface-controlled dephasing from other dephasing mechanisms (e.g., spin bath) by measuring the NV ensemble dephasing noise spectrum with dynamical decoupling spectral decomposition techniques. Our results establish a new frontier in engineering quantum light-matter interactions with nanophotonic structures.

Autonomous agents deployed in regulated domains must produce a verification artifact per consequential output: a record an auditor can re-execute offline, capturing what was claimed, against what source, by whom, when, and how. Production verification today splits into two unstandardized halves. Probabilistic verdict patterns (self-consistency voting, reviewer LLM ensembles) produce judgments, not artifacts. Artifact-producing patterns (RAG, tool-augmented traces, generator-verifier loops) produce vendor-specific records no external auditor can reconstruct without bespoke integration. Pramana defines the missing wire format. Every consequential agent output is wrapped in a typed ClaimAttestation with one of four variants (measurement, inference, analogy, citation), each paired with a verify() operation against the recorded source. verify() is deterministic for MeasurementClaim and CitationClaim. For InferenceClaim and AnalogyClaim, determinism is conditional on the oracle (audit-replayable when LLM-backed). The four-way typology derives from classical Indian epistemology (pramana, valid means of knowledge). The lifecycle is specified in TLA+ and exhaustively verified under TLC across three symmetry-reduced models: 38,563 distinct reachable states, zero invariant violations. The Python reference implementation passes 84 tests. An A2A and MCP wire-extension manifest layers three deployment-grade invariants: reachability, SLA bound, and offline re-verifiability. An exploratory pilot (n=100, 2,275 reviewer calls) probes LLM-as-judge in code generation. The strongest observation is a 40-percentage-point raw FPR delta across corpora, consistent with reference-solution quality contributing significantly. The pilot does not validate Pramana on its own; the structural argument and formal verification do that.

Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks show wide variance, with 16 of 84 tasks suffering negative deltas when Skills are introduced. The community has not yet articulated a clean mechanism for \emph{when} Skills help and when they are merely redundant overhead. We re-analyze a recently published 180-run controlled study of an MCP-grounded autonomous Capture-the-Flag (CTF) agent under four documentation conditions of increasing richness (55, 1{,}478, 1{,}976, and 4{,}147 lines), and show that these conditions correspond almost exactly to a No-Skills, Experiential-Skills, Curated-Skills, and Comprehensive-Skills ablation. In offensive cybersecurity, a domain not deeply covered by existing Skills benchmarks, the marginal benefit of Skills collapses. The spread between the no-Skills and full-Skills conditions is only 8.9~pp ($p = 0.71$, $χ^2$; $p = 0.25$, Cochran--Armitage trend test; five of six pairwise Cohen's $h$ values fall below the $0.2$ small-effect threshold). We argue that the missing variable is \emph{environment-feedback bandwidth}. When an agent's tool layer returns strict, schema-validated, low-latency observations, the environment itself supplies the procedural correction signal that Skills are normally needed to provide. As a result, the marginal benefit of curated Skills diminishes substantially, and, in some cases (e.g., our timing side-channel setting), actively degrades performance. We articulate a falsifiable hypothesis, sketch its design implications for compound AI systems, and will release the reanalysis pipeline to support replication.

This paper investigates robust synchronization for multi-agent systems (MASs) governed by parabolic partial differential equations in the presence of both observable and unobservable disturbances. Using only boundary output measurements, a disturbance observer is designed to estimate observable Dirichlet boundary disturbances while ensuring robustness of the observer error system with unobservable disturbances occurring in the domain. Using only the reference signal and local output information, distributed synchronization controllers are then constructed to enable all agents to track the reference trajectory. In particular, exponential tracking is achieved in the absence of unobservable disturbances, while robustness is preserved when additional unobservable disturbances occur during controller implementation. We further analyze the impact of unobservable Dirichlet-Robin boundary disturbances on synchronization performance by proving the boundedness of solutions to the synchronization error system. Moreover, to characterize the influence of all disturbances, input-to-state stability (ISS) is established for the closed-loop system. For the involved systems, the generalized Lyapunov method and the recursion technique are extensively employed in the stability analysis, and the lifting technique and semigroup theory are used to prove the well-posedness. Simulation results validate the proposed control scheme, demonstrating effective disturbance estimation and rejection, robust synchronization, and the ISS properties under various scenarios.

This paper implements deep reinforcement learning (DRL) with a safety filter for spacecraft reorientation control with a single pointing keep-out zone. A new state space representation is designed which includes a compact representation of the attitude constraint zone. A reward function is formulated to achieve the control objective while enforcing the attitude constraint. The soft actor-critic (SAC) algorithm is adopted to handle continuous state and action space. A curriculum learning approach is implemented for agent training. To guarantee the compliance of the attitude constraint, a control barrier function (CBF)-based safety filter is implemented for agent deployment. Simulation results demonstrate the effectiveness of the proposed state space presentation and the designed reward function. Monte Carlo simulations underscore that reward shaping alone cannot guarantee the safety during reorientation maneuver. In contrast, with the CBF-based safety filter, the constraint can be guaranteed during maneuvers.

Classical models of opinion dynamics assume human participants with bounded rationality and limited coordination. The rise of LLM-based agents introduces a qualitative shift: agents can now participate in online discussions at scale, maintain consistent persuasion strategies, and coordinate systematically. This paper argues that LLM agents make collective belief dynamics programmable, enabling deliberate steering of population-level beliefs. We term this emerging problem programmable collective belief control. Through controlled multi-agent simulations, we provide proof-of-concept evidence that coordinated AI agents can induce measurable belief shifts that stabilize within a few interaction rounds. We identify four structural properties (indistinguishability, persistence, contextuality, and configurability) that make detection and defense fundamentally difficult. Based on these findings, we outline a research agenda spanning theoretical foundations for adversarial belief dynamics, operational methods for system-level detection and intervention, and simulation infrastructure for scalable experimentation. Our goal is not to present a complete solution, but to articulate why this problem demands urgent attention and to provide a conceptual foundation for future work.

Photonic neuromorphic computing offers a promising route to overcoming the limitations of conventional von Neumann architectures by exploiting the high bandwidth, low latency, and massive parallelism of optical systems. However, most existing implementations rely on fixed dynamical substrates such as classic reservoir computing, where learning is restricted to external readout layers and memory is limited to transient fading effects. In this work, I propose a Reconfigurable Nonlinear Photonic Decision Network (RNPDN), a physically grounded neuromorphic framework in which computation, memory, and learning emerge directly from driven-dissipative dynamics. Through numerical simulations, I demonstrate the simultaneous realization of key properties: local physical learning rules enabling adaptive state evolution, a tunable stability-plasticity tradeoff governed by decay and hysteresis mechanisms, controlled memory formation and erasure via bistable photonic states, fading memory, in-situ learning, and hardware-faithful nonlinear dynamics incorporating saturation and dissipation. In contrast to conventional approaches, the proposed system enables intrinsic adaptation within the physical layer while supporting both transient and persistent memory. These results establish a unified framework for adaptive photonic information processing and provide a pathway toward scalable and energy-efficient neuromorphic photonic hardware.

To support operations and passenger-facing services, transit agencies need reliable passenger load trajectories. Currently, load estimates are typically inferred from imperfect sensing systems rather than fully observed, and the accuracy of modern automatic passenger counting (APC) systems still varies with station layout, flow intensity, and operating conditions. To address the challenges of robust passenger load estimation from heterogeneous data streams, including incremental count errors, evidence conflicts, and context-dependent sensor reliability, we propose a closed-loop, state-centric, multi-agent framework. This method enforces physical feasibility at every step, allocates trust dynamically among evidence sources, and feeds physics-derived violation residuals back into training for robustness improvement. The architecture consists of a unified stop-event backbone, a coupled Perception--Physical--Fusion loop for stop-by-stop inference, and optional trip-level macro-correction and closed-loop calibration modules.

Data-centric materials science is changing how materials are discovered, optimized, manufactured, and qualified, yet many deployment-limiting materials problems still depend on experimental, processing-rich, device-level, and field-relevant data that are difficult to capture in conventional materials databases. This perspective argues that the Great Plains and adjacent interior research corridor can make a distinctive national contribution by organizing distributed experimental assets into a trusted regional materials-data ecosystem. The proposed model emphasizes FAIR metadata, provenance, persistent sample identifiers, uncertainty-aware modeling, semi-closed-loop workflows, stackable workforce training, and tiered governance for academic, public, controlled-access, and industry-protected data. We identify five coupled barriers -- fragmented data, weak algorithm--laboratory translation, uneven access to cyberinfrastructure and technical staff, workforce gaps at the materials--data interface, and insufficient incentives for sharing and reuse -- and propose a staged roadmap for addressing them. A high-purity germanium pilot illustrates how regional strengths can be converted into reusable datasets, benchmark models, trained personnel, and decision-improving workflows. The broader message is that regional leadership in data-centric materials science will depend less on geographic concentration than on trustworthy data practices, interoperable infrastructure, cross-trained people, and application-driven materials challenges.

Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large language models (LLMs) often fall short when handling complex CAD models characterized by long operation sequences, diverse operation types, and strong geometric constraints, primarily because reasoning chains break and effective error-correction mechanisms are lacking. To address this problem, this paper proposes a memory-augmented reinforcement learning framework for CAD generation agents. The framework encapsulates the underlying geometric kernel into a structured toolchain callable by the agent and builds a closed-loop mechanism of design intent understanding, global planning, execution, and multi-dimensional verification. It also designs a dual-track memory module consisting of a case library and a skill library, and proposes a dynamic utility retrieval algorithm. By introducing reinforcement learning into retrieval and policy optimization, the agent can effectively avoid retrieval traps in which examples are semantically similar but geometrically infeasible, enabling online self-correction and continual evolution without additional large-scale annotated data. Experiments show that the proposed method significantly improves both the success rate and geometric consistency on complex CAD model generation tasks.

Large Language Model (LLM) agents are increasingly applied to engineering design tasks, yet existing evaluation frameworks do not adequately address multi-agent systems that combine simulation, retrieval, and manufacturing preparation. We introduce a benchmark suite with three evaluation dimensions: (1) a workflow benchmark with seven prompt styles targeting distinct cognitive demands-including direct tool use, semantic disambiguation, conditional branching, and working-memory tasks; (2) a Retrieval-Augmented Generation (RAG) benchmark with gated scoring isolating retrieval contributions to parameter selection; and (3) an High Performance Computing (HPC) benchmark evaluating end-to-end ML training orchestration on a SLURM cluster. Alongside the benchmark we present EngiAI, a Multi-Agent System (MAS) reference implementation built on LangGraph that operationalizes the benchmark by coordinating seven specialized agents through a supervisor architecture, unifying topology optimization, document retrieval, HPC job orchestration, and 3D printer control. Across four LLM backends and two EngiBench problems, proprietary models achieve 96-97% average task completion on Beams2D, while open-source 4B-parameter models reach 55-78%, with clear generational improvement. Conditional branching proves most challenging, with task completion dropping to 20-53% for the conditional style on Photonics2D. RAG gating confirms near-perfect retrieval-augmented scores ($\approx 1.0$) versus near-zero without retrieval, validating the evaluation design. On HPC orchestration, one model completes all pipeline steps in 100% of runs while another drops to 50%, revealing that multi-step instruction following degrades over long-running workflows.

Optical microcavities have emerged as a powerful platform for emulating topological phases challenging to realize in conventional materials, offering precise control over dispersion, light confinement, and interactions. Among them, liquid crystal microcavities (LCMCs) offer exceptional tunability at room temperature, enabling voltage-controlled polarisation splitting, photonic spin-orbit coupling, and photonic potentials generated by self-assembled textures, such as cholesteric torons and uniform lying helix (ULH). Here, we design a LCMC hosting a dimerized ULH texture and show that the corresponding photonic potential describes two coupled Su-Schrieffer-Heeger chains with orthogonal linear polarisations, acting as an effective pseudospin degree of freedom. The applied voltage tunes the interchain coupling, enabling polarisation-dependent interactions. These results establish LCMCs as a versatile platform for tunable synthetic topological Hamiltonians.

Multicellular coordination relies on broadcast-addressable receptors, yet engineered magnetic systems face an addressability bottleneck because global fields intrinsically conflate power and control. Here, we introduce MagCeptors to resolve this by encoding selectivity directly into magnetic topology. Establishing an energetic isomorphism with biological receptors, these arrays utilize local couplings to shape potential landscapes where global field vectors act as spatial keys, triggering deterministic snap-through instabilities. This architecture decouples force from source distance, achieving a density of 385 mN/mm3 (>50-fold increase over prior art). We validate this primitive through signal demultiplexing, embodied sequential logic, and untethered distributed networking. This framework enables distributed systems to orchestrate complex tasks without tethers or electronics, relying solely on the intrinsic logic of matter.

Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required, such as fire evacuation or authority-supervised emergency, remains poorly characterized. We propose PAVE (Perception, Assessment, Verdict, Emulation), a novel four-module cognitive architecture that addresses this gap end to end: (i) Perception extracts a structured context with explicit authority distance, peer behaviors, and severity-tagged situational cues; (ii) Assessment scores the context along five scalars including an explicit legitimacy judgment that checks necessity, proportionality, and absence of alternatives; (iii) Verdict decides to comply or violate under a hard legitimacy gate, with a per-agent threshold elicited from the persona; (iv) Emulation enacts the verdict and scopes the violation to the rule the trigger justifies. We instantiate PAVE in Voville, a tile-based traffic environment forked from Smallville, and evaluate across three scenarios, four LLM backbones, and a focused ablation. PAVE agents satisfy four properties simultaneously: legitimate violation (only when a trigger justifies it), authority deference (officer instructions override even high legitimacy), bounded scope (violations confined to the targeted rule), and recovery (baseline restored once the trigger ends). PAVE agents make more structured and interpretable decisions than vanilla across all four properties, and human evaluators rate them as more plausible. Ablating the legitimacy gate reproduces vanilla-like failures. We release Voville, the PAVE prompts and code, and the evaluation pipeline.

Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, memory fragmentation, and imbalanced reasoning-tool trade-offs. In this paper, we introduce STAR-PólyaMath, a multi-agent framework that systematically addresses these challenges through meta-level supervision and structured Reasoner-Verifier interaction. STAR-PólyaMath is structured as an orchestrated state machine with nested challenge-step-replan loops, governed by a reasoning-free Python orchestrator that separates control from inference and bounds error propagation through trace-back and re-planning. Our key innovation is a persistent Meta-Strategist that maintains cross-attempt memory and exercises meta-level control by issuing high-level strategic guidance or mandatory directives, so the system can escape unproductive loops rather than stagnate or over-rely on tools. STAR-PólyaMath achieves state-of-the-art results on all eight top-tier competition benchmarks: AIME 2025-2026, MathArena Apex Shortlist, MathArena Apex 2025, Putnam 2025, IMO 2025, HMMT February 2026, and USAMO 2026. It obtains perfect scores on AIMEs, Putnam, and HMMT, and shows its largest margin on Apex 2025, scoring 93.75% compared with 80.21% by the strongest baseline GPT-5.5. Ablation studies show that the gains arise from the framework's orchestration rather than from model-level diversity since removing key components or substituting in mixed backbones consistently weakens performance. Code is available at https://github.com/Julius-Woo/STAR-PolyaMath.

Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iteration step. However, these screenshots exhibit highly non-uniform spatial information density: large regions may carry little information and are visually homogeneous, while key text and icons may require high visual fidelity. Existing approaches to this problem either require additional training or rely on attention-based token compression, ignoring the structured layout and spatial redundancy of GUI screenshots. To fill the gap, this paper proposes AquaUI, a training-free inference-time token reduction method for GUI agent models that utilizes the non-uniform information density in screenshots. AQuaUI constructs an adaptive quadtree on each screenshot input and keeps one representative merged token per leaf of the quadtree. AQuaUI preserves the spatial positions of retained tokens throughout the pipeline to ensure that all position-encoding stages remain consistent. To further improve temporal consistency across multi-step GUI interactions, we propose a conditional quadtree algorithm that leverages the continuity between consecutive screenshots within a single request. Specifically, it refines the current quadtree using previous quadtrees as references, helping preserve fine-grained regions across static or mildly shifted GUI states. We implement AQuaUI on state-of-the-art GUI agent models and conduct experiments on standard grounding and navigational benchmarks. AQuaUI consistently shows improved accuracy-efficiency trade-offs over prior baselines. Notably, on GUI-Owl-1.5-32B-Instruct, AQuaUI achieves up to 13.22% speedup and 29.52% fewer visual tokens while retaining 99.06% of full-token performance, suggesting that the spatial redundancy of GUI screenshots can be exploited at inference without retraining.

We propose ERFSL, an efficient reward function searcher using large language models (LLMs) for custom-environment, multi-objective learning-based methods (LB). ERFSL generates reward components based on explicit user requirements, rectifies them using a reward critic, and iteratively optimizes the weights of these components based on textual context generated by the training log analyzer. Applied to a simulation-based benchmark task, the reward critic corrects reward codes with only one feedback iteration per requirement, and the reward weight initializer acquires diverse reward functions within the Pareto set. Even when a weight is off by a factor of 500, an average of only 5.2 iterations is needed to meet user requirements. The approach works adequately with GPT-4o mini and does not require advanced understanding capabilities.

Cascade attacks in LLM multi-agent systems (MAS) arise when adversarial influence propagates across agents and leads to escalated system-level failures through complex agent interactions. Detecting such cascades is challenging, as their signals are distributed, tightly coupled across interaction channels, and often appear plausibly benign locally but may unfold quickly either within a single turn or gradually across multiple turns. Existing defenses, being largely local and text-centric, fail to capture such cross-channel, temporally coordinated dynamics of cascade propagation. Therefore, we propose CASPIAN, the first framework that provides a unified, cross-channel causal analysis of cascade behavior in LLM-MAS through online monitoring of dynamic influence propagation across agents. CASPIAN models multi-agent interactions using a unified, dynamic causal influence matrix across channels, estimated efficiently via a late-interaction conditional transfer entropy (LI-CTE) formulation, thereby enabling the detection of cascade onset from emergent system-level structure rather than isolated anomalies. It further performs online causal attribution, identifying the origin, bridge, and amplifier agents driving the cascade and reconstructing its principal propagation pathways, capabilities not supported by existing methods. Across diverse multi-agent frameworks and benchmarks, CASPIAN consistently outperforms semantic guardrails, LLM-based judges, and graph-based anomaly detectors in both detection accuracy and early cascade identification while operating with sub-1% relative overhead latency. These results demonstrate that unified cross-channel causal modeling is essential for reliably detecting and understanding cascade failures in LLM multi-agent systems.

Four-dimensional (4D; 3D + time) microscopic imaging has emerged as a powerful technique for investigating dynamic phenomena in complex systems, enabling direct visualization of structural evolution in space and time. However, when pushing the limits of spatiotemporal resolution, most time-resolved imaging techniques yield inherently sparse 4D datasets. While deep learning-based reconstruction methods have shown promise in reconstructing 4D from sparse spatiotemporal measurements, a practical approach for evaluating their performance in the absence of a 4D reference has, to the best of our knowledge, been lacking. Here, we present a bootstrapped cross-validation framework that estimates reconstruction performance by quantifying correlations between reconstructions generated from independently sampled subsets of the acquired data, as inspired by the 3D validation strategy in cryo-electron microscopy, where reconstructions from split datasets are compared to assess resolutions. This enables both qualitative and quantitative assessment in the absence of ground truth. We investigate two representative scenarios with sparse and ultra-sparse X-ray datasets and validate this approach using 4D-ONIX, a 4D deep-learning reconstruction method, on simulated water droplet collision experiments. The proposed approach provides a reference-free framework for performance estimation and support for better-informed experimental strategies across a wide range of ultrafast imaging applications.

Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good agent-generated papers actually are. We introduce ResearchArena, a minimal scaffold that lets off-the-shelf agents (Claude Code using Opus 4.6, Codex using GPT-5.4, and Kimi Code using K2.5) carry out the full research loop themselves (ideation, experimentation, paper writing, self-refinement) under only lightweight guidance. Across 13 computer science seeds and 3 trials per agent-domain pair, ResearchArena yields 117 agent-generated papers, each evaluated under three complementary lenses: a manuscript-only reviewer (SAR), an artifact-aware peer review (PR) in which agents inspect the workspace alongside the manuscript, and an human conducted meta-review. Under SAR alone the picture is optimistic: Claude Code obtains the highest score, outperforms Analemma's FARS, and matches the weighted-average human ICLR 2025 submission, suggesting that minimally scaffolded agents can produce papers that look competitive on manuscript-only review. Manual inspection, however, reveals this picture is overstated: SAR scores are poorly aligned with its actual acceptance decisions and reward plausible framing without verifying experimental substance. Under artifact-aware PR scores drop sharply, and manual auditing identifies experimental rigor as the major bottleneck, decomposing into three failure modes (fabricated results, underpowered experiments, and plan/execution mismatch) that are highly agent-dependent: Codex 5%/8% paper-vs-artifact mismatch / fabricated references versus Kimi Code 77%/72%, a $\sim$15$\times$ spread that tracks distinct research personas the agents develop. None of the 117 agent-generated papers reaches the acceptance bar of a top-tier venue. This suggests that we are still gapped from the true auto-research.

Physical computing systems provide a promising route toward hardware-native machine learning, but their computational capabilities remain difficult to characterize in a principled, task-independent, and data-efficient way. We extend the Information Processing Capacity (IPC) framework to stationary physical computing systems and establish several fundamental results: individual capacities are bounded between zero and one, their sum over a complete basis is bounded by the number of readouts, and noise strictly reduces this bound. We address the finite-sample estimation of IPC and derive the asymptotic form of the systematic positive bias affecting naive estimators. Building on these results, we introduce data-efficient estimation methods based on Richardson extrapolation and Sobol quasi-random sampling. We validate the framework experimentally using a photonic computing system based on picosecond laser pulses propagating through a nonlinear optical fibre. By varying the laser power and fibre length, we observe systematic shifts of the IPC distribution toward higher-order nonlinear capacities induced by the Kerr effect. Finally, we demonstrate that the total IPC strongly correlates with performance on benchmark machine-learning tasks and provides a reliable estimate of the effective dimensionality of the system. These results establish IPC as a practical bridge between the intrinsic dynamics of physical computing systems and their machine-learning performance.

Mean field game equilibria are predicated on the assumption of immediate pairwise interactions within a population of homogeneous agents with asymptotically vanishing influence as population size increases. However, in many real-world cases, agents receive population-level information with a delay. In this paper, we characterize agent best responses under an information exchange structure whereby agents observe the empirical mean state only at discrete time instants with some delay. Sufficient conditions are presented for the existence of a Nash equilibrium within a finite population of agents, and the cost increase due to delayed discrete empirical mean observations relative to zero-latency discrete observations and continuous global-state observations is also evaluated.

We introduce DecisionBench, a benchmark substrate for emergent delegation in long-horizon agentic workflows. The substrate fixes a task suite (GAIA, tau-bench, BFCL multi-turn), a peer-model pool (11 models, 7 vendor families), a delegation interface (call_model plus an optional read_profile channel), a deterministic skill-annotation layer, and a multi-axis metric suite covering quality, cost, latency, delegation rate, routing fidelity-at-k, vendor self-preference, and a counterfactual-delegation ceiling. The substrate is agnostic to how peer information is generated or delivered, so learned routers, richer peer memories, adaptive profile construction, and multi-step delegation can all be evaluated against it. We characterize the substrate with a five-condition reference sweep on the full pool (n=23,375 task instances). Three benchmark-level findings emerge: (i) mean end-task quality is statistically indistinguishable across the four awareness conditions (|beta| <= 0.010, p >= 0.21), so quality-only evaluation would miss the orchestration signal; (ii) routing fidelity-at-1 ranges from 7.5% to 29.5% across conditions at near-equal mean quality, with delivery channel (on-demand tool vs. preloaded description) dominating description content; (iii) a counterfactual ceiling places perfect delegation 15-31 percentage points above measured performance on every suite, locating large unrealized headroom for future orchestration methods. We release the substrate, annotation layer, reference intervention suite, analysis pipeline, and 220 per-condition run archives.

Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, multi-agent interactions common in complex driving scenarios. We introduce RLFTSim, a reinforcement-learning-based fine-tuning framework that enhances scenario realism by aligning simulator rollouts with real-world data distributions and provides a method for distilling goal-conditioned controllability in scenario generation. We instantiate RLFTSim on top of a pre-trained simulation model, design a reward that balances fidelity and controllability, and perform comprehensive experiments on the Waymo Open Motion Dataset. Our results show improvements in realism, achieving state-of-the-art performance. Compared with other heuristic search-based fine-tuning methods, RLFTSim requires significantly fewer samples due to a proposed low-variance and dense reward signal, and it directly addresses the realism alignment issue by design. We also demonstrate the effectiveness of our approach for distilling traffic simulation controllability through goal conditioning. The project page is available at https://ehsan-ami.github.io/rlftsim.

Humanoid robots are difficult to deploy safely because they have high-dimensional bodies, many collision constraints, and must operate near people and obstacles. Safety filters help by modifying a nominal control action when it may violate collision-avoidance constraints. Still, nominal benchmark scores do not fully show how these filters behave in harder environments. In this work, we study the robustness of SPARK humanoid safety filters through replication and stress testing. We replicate the SPARK benchmark case G1SportMode_D1_WG_SO_v1 in MuJoCo and evaluate RSSA, RSSS, SSA, CBF, PFM, and SMA under controlled random seeds. We also built a post-processing pipeline that converts raw SPARK logs into goal-tracking, minimum-distance, and collision-step metrics. Our results show that some methods track the goal more closely, while others reduce collision steps more effectively. The stress tests further indicate that safety behavior can change under obstacle crowding, noisy distance estimates, and delayed obstacle information. These findings suggest that humanoid autonomy should be evaluated beyond nominal performance, using metrics that expose failure modes before deployment.

Integrated photonics has enabled a wide class of chip-scale light sources and quantum technologies. Within this field, microresonator-based degenerate optical parametric oscillators (DOPOs) have gained prominence. Above a critical power threshold, these systems undergo spontaneous symmetry breaking to settle into one of two stable, π-phase-shifted states -- a mechanism successfully used for quantum random number generation and photonic Ising machines. Here, we show that DOPOs based on the Kerr nonlinearity host a significantly broader range of nonlinear dynamics than previously explored. Using a silicon nitride microring resonator, we experimentally identify Hopf bifurcations that trigger a transition from stationary operation to self-sustained oscillations at MHz frequencies. By adjusting pump detunings and powers, we achieve turnkey control over these oscillatory regimes, navigating the system between stable binary states and periodic limit cycles. Furthermore, we report the experimental observation of period-doubling bifurcations, which numerical simulations reveal as the precursor to a cascading instability culminating in chaos at elevated pump powers. Our results establish a framework for controlling nonlinear instabilities in chip-scale parametric oscillators, with applications in programmable photonic hardware and dynamical optical computing.

We present a controlled benchmark evaluating three LLMs -- Claude Sonnet 4.5, Gemini 2.5 Pro, and GPT-3.5 Turbo -- across four prompt formats (from concise narrative to structured JSON with explicit iteration trace) on Gauss--Seidel AC power flow computation for a three-bus system. Against 50 test cases with reference solutions computed numerically, Gemini 2.5 Pro with the simplest narrative prompt achieves the lowest mean absolute error (MAE = 0.257 MW/MVar, 54\% of cases within 5\% relative error), while the same model with a JSON-structured prompt raises MAE to 0.789 -- a 3.1$\times$ increase. Adding a worked example degrades accuracy for Gemini but provides a marginal gain for Claude. GPT-3.5 Turbo fails on at least 90\% of cases under all prompt formats. An independent 100-case replication with related prompt-format families confirms the qualitative ordering (Gemini $>$ Claude $>$ GPT-3.5): the best 100-case configuration (Gemini with explicit iteration trace) achieves MAE = 0.402 and 53\% within 5\%, while Claude Sonnet 4.5's near-flat accuracy profile ($\approx$38\% within 5\% across formats) and GPT-3.5's near total ineffectiveness (92--97\% above 20\% error) both replicate. In neither evaluation does any configuration achieve sufficient reliability for use as a direct numerical solver. These findings offer a diagnostic baseline for practitioners and researchers evaluating LLMs for smart-grid decision-support assistance.

Plasmonic optical tweezers based on Double Nanohole (DNH) structures are an emerging tool for label-free single-molecule manipulation. However, their current performance is hindered by low signal-to-noise ratios for small proteins, fabrication variability, and thermal damage risks from high laser power requirements. To address these limitations, we present a comprehensive optimization of DNH parameters using systematic simulations and morphological characterization. We evaluate critical structural features, including gap size, gap length, gap curvature, wedged tapers, adhesion layers, and the inclusion of interior pillars. By tailoring these variables, we aim to maximize trapping stiffness, local electric field confinement, and transmission variation upon trapping (ΔTT), while minimizing the required optical power. The resulting optimized DNH design substantially outperforms reference structures, delivering an almost 3-fold increase in electric field enhancement and a 5-fold improvement in the trapping transmission signal. These refinements provide a robust framework for developing highly efficient, reproducible optical tweezers for advanced single-molecule biophysics.

The distributed setting for Saddle Problems (SPs) has recently emerged as a framework for various modern applications in machine learning and multiagent systems. Despite its relevance, the theoretical foundations of this setting have not yet been thoroughly established. In this paper, we advance this research direction by formalizing the distributed setup for SPs and providing rigorous definitions of communication and computational costs. Our main result is a novel decoupled method that achieves optimal communication cost within the zero-respecting framework. Our method is based on a multi-stage reduction to the decoupled minimization of residual norms, which yields strict improvements over the best known communication cost for the class and the long-standing oracle cost of the Extragradient method. Further, we show by a matching lower bound that our method is communication-optimal within the family of gradient-span algorithms. Finally, we study the extension of distributed SP into Variational Inequality Problem (VIP), which generalizes two-player zero-sum games to multiplayer general-sum games. We show that our decoupled method achieves a new state-of-the-art communication complexity for this broader class.

Backward reachable tubes (BRTs), computed via viscous Hamilton-Jacobi (HJ) partial differential equations, provide principled safety certificates for learned controllers and planning algorithms in trustworthy machine learning. However, classical grid-based HJ solvers require $O(M^n)$ memory footprint for $M$ grid points per $n$ state dimension. This renders them impractical for high-dimensional systems. We address this bottleneck with a local PDE linearization that enables a frozen-coefficient sampling scheme for the viscous HJ PDE: a generalized Cole-Hopf-type transformation reduces the nonlinear HJ equation to a sequence of linear heat equations whose solutions admit Gaussian heat-kernel representations. The value function and its spatial gradient are then recovered via roll-outs of Monte Carlo expectations on Gaussian densities, yielding a storage and grid-free algorithm that scales as $N\cdot n$ for $N$ samples. This decoupling of memory from dimensionality enables reachability analysis on problems where grid-based methods are simply impossible. We prove a finite-sample concentration bound $O(N^{-1/2})$ error and conditional linear convergence for the introduced Monte-Carlo Picard iterative scheme. Numerical validation on pursuit-evasion games demonstrates relative $L^2_{\text{rel}}$ errors of $0.03 - 0.20$, with $14-26$ second wall-clock times per 2D slice on a CPU. Crucially, the method scales with validation on up to (but not limited to) $n=45$-dimensional multi-agent games.

Fringe projection profilometry (FPP) is a widely used technique for measuring object surface form and three-dimensional (3D) geometry, capable of delivering high-precision, high-resolution measurements when paired with suitable cameras and projectors. However, in practical deployments, identifying parameter configurations that maximise precision while satisfying real-world constraints remains challenging. To address this, we present an automated digital twin framework implemented in Blender, an open-source 3D software package that provides a ray-traced rendering environment that enables accurate simulation of physical systems. We replicated the physical setup in our digital twin by matching characterisation quality, gamma response, and characterisation images. Accurate system characterisation using Zhang's method [1], to obtain intrinsic and extrinsic parameters, is shown to be critical for achieving high precision. Using this digital twin, we then demonstrate systematic exploration and optimisation of key parameters, including phase-shift count, camera-projector spacing, and fringe density. These parameters span both system geometry (e.g. camera-projector positioning) and algorithmic choices, such as 2D phase-shifting and unwrapping methods [2]. Three measurement artefacts, representative of real world metrology scenarios, were used to benchmark the system. The symmetrical mean Chamfer distance (SMCD), computed between ground-truth and reconstructed meshes, was used to evaluate reconstruction quality. After optimisation within the digital twin, transferring the optimal parameters to the physical system reduced the number of required images per measurement by 48% (from 36 to 21). A reduction of 74.0% mean SMCD was also achieved for fringe pattern stripe count alteration. A 36.9% mean SMCD was obtained for adjusting the camera and projector spacing purely in the digital-twin.

The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This position paper argues that personal-agent architecture must move to the edge because the core properties of agentic intelligence tasks, particularly their structural coupling with high-fidelity local context and the need for zero-latency execution loops, do not sit well with cloud-centric designs. We develop this claim through three structural shifts. First, the Prefrontal Turn: the main marginal lever of capability has moved from pre-training scale to framework-level executive control. Such control must remain physically close to the environment of action if the agent is to preserve cognitive alignment. Second, the Data-Geography Paradox, the ``dark matter'' of agentic data (local file hierarchies, real-time sensor streams, and transient OS states) degrades, disappears, or loses meaning once prepared for cloud transmission, thereby cutting the agent off from ground-truth context. Third, the interaction-alignment loop, the only economically and ecologically sustainable source of agentic refinement data is the high-fidelity implicit preference signal produced through real-time local interaction. Third, the interaction-alignment loop, the only economically and ecologically sustainable source of agentic refinement data is the high-fidelity implicit preference signal produced through real-time local interaction. We conclude with falsifiable predictions for the next deployment cycle of personal agents.

We present a systematic experimental comparison of single-pass second-harmonic generation (SHG) in bismuth triborate (BiBO) and lithium triborate (LBO) nonlinear crystals, driven by a 1.3 ps, 91 kHz laser at 1030 nm with up to 57 W of average input power. Both crystals yielded 32 W of second harmonic (SH) output at 515 nm, corresponding to a conversion efficiency of 56 %, which to the best of our knowledge represents the highest SH output power reported in the green spectral region using a BiBO crystal. Power dependence, long-term stability, beam quality, pulse duration, spectral properties, thermal effects, and angular acceptance bandwidth are characterized and directly compared for both crystals. These results provide quantitative performance benchmarks to guide the selection of nonlinear crystals for high-average-power, ultrashort-pulse frequency conversion near 1030 nm.

Advanced regulatory control (ARC), also known as advanced PID architectures, is a simple and robust way of controlling processes with changing and possibly conflicting constraints, where it previously was believed - at least in academia - that model-based solutions, such as MPC, were the only effective solution. To illustrate this, ARC is applied in two case studies. The first is a gas-liquid separation process, in which selectors and split-parallel control are combined to achieve bidirectional inventory control in which the throughput manipulator moves automatically to the most optimal position. The second case study is on keeping acceptable air quality (CO2-level) and temperature in a room (in this case, a barn for cows). The CO2 and temperature constraints can be conflicting, leading to a hierarchical switching network of PID controllers. Note: this is an extended version (with simulations) of paper at IFAC World Congress, August 2026, Korea.

In social dilemmas self-interested learning agents face the choice between the societal benefit of cooperation and the immediate reward of defection. Significant evidence exists on the benefits of assortment mechanisms such as partner selection for the emergence of cooperation, but this is largely available through agent-based simulations. In this paper, we provide an analytical solution to the problem, studying the policy-gradient dynamics in a multi-agent environment with partner selection. We show how partner selection changes the opponent distribution and hence the reward landscape, and prove this promotes cooperation under simple rules known from the literature. In particular, we find that population variance is a necessary condition for cooperation to emerge. Using a two-dimensional Wiener process, we extend the dynamics to capture the stochastic effects of partner selection and the resulting opponent distribution. We derive a sufficient condition for the population to be cooperation-promoting and prove the existence of a stationary distribution. Simulations confirm that the stochastic model accurately captures the policy-gradient dynamics and clarifies how the learning rate affects the emergence of cooperation.

Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information. To address this, we propose LLM-driven Multi-Agent Communication (LMAC), which leverages an LLM's reasoning capability to design a communication protocol that enables all agents to reconstruct the underlying state as accurately and uniformly as possible. LMAC iteratively refines the protocol using an explicit state-awareness criterion, improving state recovery while narrowing differences in agents' knowledge. Experiments on diverse MARL benchmarks show that LMAC improves state reconstruction across agents and yields substantial performance gains over prior communication baselines.

Autonomous labs enable the integration of automated experiment execution, data analysis and decision making. The main challenge remains the integration of diverse data streams from multiple instruments, where the data is often heterogeneous and unsynchronized. The standard learning process of undetermined synthesis-process-structure-property relationships (SPSPR) usually relies on post-experiment analysis after data is fully collected, not during live experiments, and decision making is carried out independently across characterization equipment. Here, we demonstrate the Multi-instrument Autonomous Discovery (MAD) framework -- combining structural property mapping and functional property optimization simultaneously in a closed-loop manner. As an example, we applied MAD to phase change memory (PCM) materials, and, in particular on the Mn-Sb-Te ternary, a previously unexplored materials system for PCM. A multi-output model is employed to merge data from x-ray diffraction (XRD) and electrical resistance measurements simultaneously through a co-regionalization kernel that models the relationship between them. The output probabilistic posterior and uncertainty quantification facilitate decision making with shared knowledge, while the goals are different across tasks. We aimed to maximize the knowledge of crystal structure distribution using non-negative matrix factorization (NMF), while in parallel, we find the composition with the maximum resistance value, an important figure of merit for PCM. Leveraging MAD, we found promising electrical PCMs and identified the SPSPR within 25 closed-loop iterations, corresponding to a seven-fold speed-up. The framework opens a new path of study in large-scale autonomous facilities, where future experiments can be run in parallel together, not independently.

Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented attacks, leaving a gap in robustness when interaction structures themselves are corrupted. In this paper, we propose an interaction-breaking adversarial learning (IBAL) framework that takes an information-theoretic view to construct attacks that impede coordination by perturbing agents' observations and actions, and trains agents to perform reliably under such disruptions. Empirically, our approach improves robustness over existing robust MARL baselines across diverse attack settings and yields stronger performance even under agent-missing scenarios.

Robotic systems are vulnerable to False Data Injection Attacks (FDIAs), where adversaries corrupt sensor signals to gain malicious control. Feedback linearization exposes robotic systems to integrator vulnerability, making them susceptible to stealthy attacks that can cause significant deviations in end-effector behavior without raising alarms. This paper addresses the resilience of manipulators against finite-horizon FDIAs by formalizing two defense methods, namely anomaly-aware virtual damping and manipulability reduction, with probabilistic guarantees on nominal task execution. Simulations on a 7-DOF redundant manipulator show that the proposed defenses substantially reduce the impact of FDIA compared to using solely a threshold-based ADS like the Chi-squared, while preserving nominal task performance in the absence of attack.

We demonstrate a data-driven framework for emulating high-speed VCSEL-based 4-level Pulse Amplitude Modulation (PAM-4) optical interconnects using bidirectional Long Short-Term Memory (Bi-LSTM) networks. Unlike conventional rate-equation models, which are computationally intensive and often require difficult parameter tuning, our approach utilizes experimental waveforms to learn the end-to-end system dynamics. By employing transfer learning and weight interpolation, we extend the model to new operating regimes with a 20-fold reduction in computation time compared to independent training, while maintaining normalized mean squared error below 0.04. This emulator provides a rapid, accurate tool for the design and optimization of short-reach optical links.

Heterogeneous integration of gain and strongly nonlinear materials with ultra-low-loss silicon nitride (SiN) photonics offers a route to scalable quantum circuits, but concurrent wafer-scale manufacturability, low interlayer loss, and high performance have been challenging to realize. Here we demonstrate a wafer-scale III-V-on-SiN quantum photonic platform that directly integrates III-V layers to foundry-fabricated SiN circuits. The SiN layer provides 200-300 nm thick waveguides with $<1$ dB/m loss and a mature passive photonics ecosystem, while III-V materials provide large $χ^{\left(2\right)}$ and $χ^{\left(3\right)}$ nonlinearities for parametric gain, frequency conversion and quantum light generation. Adiabatic interlayer couplers yield $<25$ mdB loss to InGaP waveguides and resonators with intrinsic quality factors exceeding $10^6$, enabling $15\times$ brighter entanglement sources and efficient nonlinear conversion on SiN. Integrated components--including low-loss beam splitters, waveguide crossers, and tunable interferometers--are complemented by III-V lasers and InP photodetectors with amplifiers achieving up to $99^{+1}_{-12}\%$ quantum efficiency and $3$ GHz bandwidth. This architecture unites ultra-efficient sources, nonlinear elements and detectors on a wafer-scale, low-loss platform, establishing a path toward large-scale, low-noise quantum photonic systems.

We address the conditions and design of controllers and observers for homogeneous networks of linear MIMO agents. We develop networked controllers and observers that ensure the stability of both the system state and the estimation error, leveraging the concept of generalized frequency variables. A separation principle for networks is then established, showing that the observer and controller can be designed independently and combined to achieve a stable output feedback. Our results are illustrated via a highly unstable, oscillatory network of locally actuated pendulums on carts. Finally, necessary conditions for controllability and observability -- derived from agent properties and network structure -- are established and discussed.

Edge inference systems are typically evaluated with software-reported latency collected under controlled conditions. We argue, and demonstrate empirically, that deployment interference can corrupt not only the inference timing being measured but the timing observability infrastructure that measures it, and that the two failures can occur independently. We pair software-reported timing with externally observable GPIO intervals captured by a Saleae Logic Pro 8 logic analyzer on an NVIDIA Jetson Orin Nano, running MobileNetV2 under two inference architectures (TensorRT FP16 GPU and ONNX Runtime CPU) across baseline, light memory pressure, and storage writeback stress. Across 35 paired capture runs (3500 samples) plus 3 storage-stress runs where external pairing failed (300 software-only samples), we observe three findings the software-only view does not surface. (1) The two architectures differ not only in mean latency but in distributional structure: TensorRT baseline clusters tightly near 1.23 ms (run-mean SD 15 us) while ORT CPU baseline is multimodal with run-mean SD 31.8 ms. (2) Light memory pressure inflates TensorRT P99 from 1.28 ms to 1.61 ms, while one of five ORT memory-stress runs collapses into a deterministic 198 ms regime rather than uniformly inflating variance. (3) All three TensorRT storage-stress runs produce complete software timing logs (100/100 iterations) alongside externally observable timing failures of three different kinds (full post-marker collapse, ~40% transition loss, and complete acquisition failure) -- while the runtime reports normal completion in every case. We claim, narrowly, that timing observability is itself an interference-sensitive resource, and that summary statistics from a single timing source can hide failure modes an independent external observer makes visible.

The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting with marketplaces, their collective behavior can amplify volatility and mask deception at scale. We introduce the Agent Bazaar, a multi-agent simulation framework for evaluating Economic Alignment, the capacity of agentic systems to preserve market stability and integrity. We identify two failure modes: (1) Algorithmic Instability in a B2C market ("The Crash"), where firms amplify price volatility until the market collapses, and (2) Sybil Deception in a C2C market ("The Lemon Market"), where a single deceptive agent controlling multiple coordinated seller identities floods the market with fraudulent listings, eroding trust and consumer welfare. We evaluate frontier and open-weight models across both scenarios and find that models largely fail to self-regulate, with failure severity varying by model rather than by size. We propose economically aligned harnesses, Stabilizing Firms and Skeptical Guardians, that improve outcomes but remain fragile under harder market conditions. To close this gap, we train agents with REINFORCE++ using an adaptive curriculum, producing a 9B model that outperforms all evaluated frontier and open-weight models. We propose the Economic Alignment Score (EAS), a 4-component scalar metric aggregating stability, integrity, welfare, and profitability, enabling direct cross-model comparison. Our results show that economic alignment is orthogonal to general capability and can be directly trained with targeted RL.

Electrocardiogram (ECG)-based biometric recognition has emerged as a promising solution for secure authentication and liveness detection. However, most existing methods rely on unimodal deep learning architectures that independently process either one-dimensional (1D) temporal signals or two-dimensional (2D) time-frequency representations, limiting robustness and generalization. To address this issue, this paper proposes a hybrid framework integrating 1D and 2D convolutional neural networks (CNNs) within a unified end-to-end architecture. The 1D branch extracts temporal and morphological features from raw ECG signals, while the 2D branch captures discriminative spectral information from time-frequency representations. An attention-guided fusion mechanism dynamically weights both modalities according to input characteristics, overcoming the limitations of conventional static fusion strategies. The framework was evaluated on three benchmark datasets (ECG-ID, MIT-BIH, and PTB), including healthy subjects and patients with cardiac pathologies, achieving identification accuracies of 99.56%, 100.00%, and 99.89%, respectively. To assess long-term biometric permanence, experiments were also conducted on the multi-session Heartprint dataset spanning ten years. The proposed approach achieved same-session accuracies of 98.54% (S1), 99.09% (S2), 94.93% (S3R), and 96.08% (S3L), while cross-session evaluations reached 56.33% (S1-S2) and 53.27% (S2-S3R), demonstrating the ability to capture stable biometric signatures over time. The optimal configuration combines InceptionTime for 1D processing, ResNet-34 for 2D analysis, and attention-based fusion. Ablation studies confirm that the proposed attention mechanism consistently outperforms conventional fusion approaches. Overall, the proposed framework provides a robust, scalable, and high-performance solution for ECG biometric recognition.