Physical AI Brief

Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that learns to act in them. Each is a stateful, multi-turn environment (state transitions, reward functions, and verification code), so one interface spans reasoning problems and multi-step agentic tool use. The Reasoning Agent's regret is estimated using the gap between its reward with and without privileged hints; in optimizing this regret signal the Environment Designer learns to target environments at the edge of the agent's capabilities while keeping them feasible. Through extensive experimentation, we find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory. Scaling to 30B-parameter models, SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks, and lifts the tool-use setting by +5.7 on BFCL-v4 multi-turn and +13.9 on ACEBench-Agent; on the games setting, the margin over the strongest baseline grows with model scale. By making environment design itself a learnable component, SPADE takes a concrete step toward open-ended self-improvement.

Dual-arm robotic grasping is essential for manipulating large, heavy, and geometrically complex objects that cannot be reliably handled using a single manipulator. These large objects often contain only sparse graspable regions determined by local geometric properties such as thickness, edge structure, and gripper clearance. Prior bimanual grasping methods assume access to a full point cloud of the object which inherently contains this geometric information, but may not be accessible in real scenarios. This work proposes PartialBiGrasp, a dual-arm grasp generation framework that operates directly on partial point cloud observations. Our model learns geometric features implicitly through convolutional occupancy networks, enabling local reasoning about graspability, collision-free contact regions, and object thickness. We leverage this understanding to generate force-closure compliant grasp pairs, which are further refined using a sampling-based optimization to correct for ambiguity caused by incomplete geometry. We evaluate our approach using analytical force-closure metrics, large-scale simulation experiments, and real-world robot evaluations on noisy partial point clouds of novel objects, demonstrating robust and physically stable dual-arm grasp generation.

We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for learning sim-to-real transferable dexterity across high degree-of-freedom (DoF) robot embodiments that can solve long-horizon tasks directly from raw visuo-tactile perception. ADEPT pretrains a dexterous policy on a generic object reposing task, then post-trains downstream policies with this pretrained behavior as a prior. ADEPT enables learning new behaviors that are otherwise difficult to discover from scratch on multi-fingered robots and avoids learning the same set of skills over again for every new downstream task. The pretrained policy zero-shots the reposing phase of downstream tasks, but naïve RL fine-tuning rapidly degrades this capability during transfer. We address this with a stable post-training recipe combining behavior-cloning distillation, critic warm-up, and conservative on-policy updates. To safely exploit the full kinematic dexterity, we introduce a joint-space Geometric Fabric that mediates between the RL policy and the robot. We distill post-trained teachers into perceptive students that zero-shot sim-to-real transfer on two embodiments: a 23 DoF Kuka-Allegro with two RGB cameras, and a 29 DoF Flexiv-Sharpa with two RGB cameras and five vision-based tactile sensors, and can solve long-horizon tasks from challenging initial states with dexterity at human-level speed.

On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, however, token-level teacher support can favor locally plausible responses that omit evidence distributed across the input or violate global task constraints. Task-specific verifiers, in contrast, evaluate task completion at the response level and may return graded rewards that reflect partial success. We diagnose this mismatch on fixed responses from two representative long-context evidence-aggregation tasks. Across longer input ranges, trajectory-level OPD scores become progressively less aligned with verifier rewards, indicating teacher-verifier disagreement. Motivated by this observation, we introduce Group-Calibrated On-Policy Distillation (GC-OPD). GC-OPD separately normalizes verifier rewards and trajectory-level OPD scores within each rollout group and uses their difference as a signed teacher-verifier disagreement residual. Relative-advantage-based credit assignment (RACA) distributes this trajectory-level residual across tokens according to their relative OPD advantages while preserving the original OPD signal. Across five long-context benchmarks, post-training with GC-OPD raises the five-benchmark averages of the official Qwen3-4B and Qwen3-8B checkpoints from 29.08 to 40.47 and from 35.12 to 44.65, respectively. Vanilla OPD reaches 39.31 and 43.56 under the same setup. Controlled ablations show that the signed residual is more effective than either an additional OPD-derived term or direct group-normalized verifier reward addition, while RACA further improves over uniform token allocation. Together, these results demonstrate that group-relative residual calibration can incorporate verifier outcomes without discarding dense token-level guidance. Code is available at https://github.com/SolereZhang/GC-OPD.

Language-model agents can communicate through continuous hidden states that are invisible in public transcripts, creating opportunities for covert harmful coordination. We introduce Verifiable Latent Alignments (VLA), an activation-aware framework for monitoring and steering these private communication channels. For every monitored decision, VLA links the private latent-state record and channel status to the resulting public action using a shared event identifier, enabling matched causal analysis. Our first contribution is a neutral-only three-layer monitor combining representation anomaly detection, counterfactual action-distribution influence, and sparse-autoencoder interpretation support. Our second contribution is a steerability framework spanning black-box behavioral instructions and white-box matched-neutral counterfactuals. Our third contribution is an evaluation on a controlled multi-agent auction benchmark covering homogeneous and heterogeneous model pairs, many-agent scalability, and intervention effectiveness. The sequential monitor achieves mean area under the receiver operating characteristic curve (AUROC) of 0.993 for homogeneous agents and 0.854 for heterogeneous pairs when text- and latent-collusion rows are pooled as positives. In Qwen3-0.6B auctions with 25-100 bidders, monitoring requires only a small normalized load relative to all possible directed pairs, while full white-box steering achieves 100% bid-distribution recovery and reduces collusive low-bid behavior by 47.3 percentage points. Because full white-box steering replays the matched neutral counterfactual, its exact recovery is a sanity check by construction. Overall, the controlled study shows that the evaluated private channel attacks can be monitored without training the primary monitor on attack examples and mitigated when matched counterfactual access is available.

We study stochastic control of multivariate Hawkes-driven stochastic differential equations with machine learning algorithms in a non-Markovian setting. Due to the path dependence of the memory of the Hawkes intensity, this problem does not fall within classical stochastic control theory outside particular Markovian kernels. We first develop a finite-dimensional Markovianization procedure and algorithm to approximate multivariate Hawkes processes with mixtures of exponential kernels. We prove the convergence of the Markovianized approximation of the Hawkes process, its intensity, and the value of the problem to the original non-Markovian processes and the value of the primal problem. We then formulate continuous-time deterministic policy gradient learning on the Markovianized approximation of the problem, called Hawkes-CT DDPG. We propose a model-free algorithm to solve the non-Markovian Hawkes-driven optimization by observing only the event times of the process, the realization of the solution to the SDE, and a chosen set of decay filters, while the Hawkes kernel coefficients remain unknown. We compare our continuous time reinforcement learning Hawkes-CT DDPG method with discrete time reinforcement learning techniques under three different types of kernels: simple exponential, Erlang, and power-law kernels.

Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large model such as a 70B-parameter LLM. We show that a handful of AIPCs, working together over an ordinary network, can serve models beyond the capability of any single one. We use pipeline parallelism: a model is split by layer into per-stage shards, each pre-compiled into an OpenVINO graph, so that every machine runs one shard and passes activations to the next. Three techniques make this fast enough to be useful. First, we recover the speed of the unsplit model: a naive per-stage export runs well below monolithic inference because it misses an OpenVINO GPU optimization, and injecting a beam_idx Gather into each shard triggers that optimization (the IndirectKVCache fusion) and brings the shards to parity. Second, we leverage speculative decoding on stateful OpenVINO models. Third, the pipeline serves several users at once by interleaving their requests across the stages, each request carrying its own cache (micro-batching). Together, a two-node Llama 3.1 8B INT4 pipeline serves two concurrent users at 1.79x the single-user throughput of the unsplit model on the same hardware, and the gap widens under simulated wide-area latency. The same design scales to a 70B model that no single fleet member can hold: a four-node deployment of Lunar Lake AI PCs on Intel Tiber Cloud serves a single user at interactive speed, with output token-for-token identical to the same four-node pipeline decoding without speculation. Code, raw benchmark logs, and reproduction scripts ship as a self-contained package at https://github.com/labscommunity/pipeline-sharded-inference-paper (in the top-level reproduction/ directory).

Frontier language models are compared, marketed, and benchmarked on capability -- what their best or average output can achieve. I argue this measures the wrong axis. The models have saturated accuracy: their mean output lands on the target. What now separates one system from another in practice is precision: how tightly concentrated their outputs are around that target across repeated, identical requests. Borrowing the marksman's distinction, capability is where the average shot lands; reliability is the size of the group. I make three claims. First, precision, not capability, is the frontier differentiator between systems, and benchmark culture systematically fails to measure it, reporting central tendency rather than spread. Second, precision is measurable, cheaply and without circularity, by running a fixed suite of deterministically scored tasks many times at fixed temperature and computing the per-task consistency of outcomes -- no model-in-the-loop grader required. Third, the measurement is not merely descriptive but decision-guiding: it separates consistent failures (a tight group off-centre, correctable by the operating discipline of Paper 1 -- a sight adjustment) from scattered failures (a wide group, correctable only by changing the model or its sampling -- a rifle problem). I define a grouping metric, specify a harness, and show how tracking a human-AI pair's grouping over time yields the compounding signal that Paper 1's field study requires. A first real run, since replicated, illustrates both the method and its most important limit: one measured gap was closed completely by a single rule (0/5 -> 5/5), while a suite of tasks authored from the rules themselves found no value, because a frontier model already embodies explicit good practice -- establishing that a discipline's worth is found by measurement on real work, not constructed from its own rulebook.

A connected vehicle has roughly 100 milliseconds to decide whether an incoming Basic Safety Message is real or fabricated. If a false emergency braking alert reaches the planning pipeline in time, the car brakes - a safety failure triggered by a security failure. Existing intrusion detection systems are not designed to handle that coupling. They operate per vehicle, per message, with static rules - blind to attack patterns that only emerge across a fleet or over time, and blind to the fundamental tension between dropping a suspicious message and dropping a real emergency alert. We propose a three-tier multi-agent architecture that treats this timing constraint as a hard design requirement, not a performance target. At the vehicle level, an onboard agent classifies each incoming V2X message into one of four actions - Accept, Drop, Quarantine, or Escalate - within a 10-millisecond budget, deliberately biased toward Escalate when uncertain, passing ambiguous cases to the roadside edge agent rather than risking a dropped legitimate alert. The edge agent operates across a roadside unit zone with a 50-millisecond budget, fusing threat assessments from multiple vehicles and resolving safety-security conflicts using complementary sensor observations. The cloud tier refines detection models through Byzantine fault-tolerant federated learning and redistributes updated weights to the fleet. Every timing constraint derives directly from the 100-millisecond Basic Safety Message cycles mandated by SAE J2735 and ETSI EN 302 637-2. No existing framework simultaneously assigns standards-grounded latency budgets to all three deployment tiers while treating safety-security conflict resolution as a first-class design constraint. Remaining open problems - adversarial poisoning at the edge and the absence of regulatory frameworks for autonomous security response - are discussed as future work.

Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, current EEG-to-image retrieval methods perform far below their within-subject counterparts for new users without labeled calibration, limiting real-world deployment. To understand this gap, we analyze EEG features across subjects and find that different subjects preserve similar relationships among concepts but express them along different coordinate directions. We therefore propose Subject Coordinate Recovery (SCORE), a target label-free framework combining recovery-aware source training with coordinate alignment at deployment. During training, SCORE aligns source subject EEG with a common image space and simulates unseen-subject recovery through source-only episodes. At deployment, with both encoders frozen, SCORE selects reliable EEG-image landmarks through hubness-corrected matching and estimates an orthogonal transformation to recover target EEG coordinates without source data or target labels. In 200-way retrieval on two public benchmarks, SCORE outperforms the unadapted baseline for every target subject and achieves the best overall accuracy. It reaches 53.23%/83.55% and 12.01%/32.16% Top-1/Top-5 on THINGS-EEG2 and Alljoined-1.6M, respectively, surpassing the strongest baselines by 17.45/15.70 and 3.08/4.62 percentage points. Without target labels or encoder updates, SCORE brings brain-based visual decoding closer to robust, practical, low-latency deployment across users.

Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitations: missing and observed values are embedded within the same representation space without explicit structural separation, and continuous diffusion-based methods are trained to predict added noise rather than the original signal. To address these, we propose the Masked Diffusion Time-series Imputation Model (MDTIM), which leverages the training paradigm of masked diffusion model for imputation tasks. The MASK token is structurally orthogonal to valid observations, and the model directly predicts the original values, naturally aligning both the representation and the learning objective with the imputation task. To bridge the gap between discrete masked diffusion and the continuous, ordinal nature of time series, we further introduce Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics. Our experiments on diverse benchmarks confirm that MDTIM achieves superior robustness and scalability, consistently outperforming state-of-the-art deterministic and generative baselines across various missing scenarios.

Modern pretrained encoders make representations from heterogeneous views increasingly reusable, but the procedure that determines view utility and combines evidence is still relearned for each downstream task. Consequently, knowledge about view relevance, complementarity, reliability, and missingness is repeatedly discarded rather than transferred across tasks. We therefore reformulate multi-view learning as learning a reusable, task-conditioned inference procedure rather than a fixed fusion function. Based on this perspective, we propose SIMPLE, a prior-fitted multi-view in-context learner that predicts query labels by conditioning on a small labeled support set. Since existing real-world datasets cover only a limited range of view configurations and task structures, we construct a controllable synthetic task prior in embedding space. It generates diverse support-query episodes with varying class structures, shared and view-specific factors, representation geometries, cross-view dependencies, reliability levels, missingness patterns, and distribution shifts. A hierarchical inference architecture then performs reasoning within views, across views, and across support and query samples. Experiments on multi-view and multi-omics benchmarks demonstrate that the frozen variant of SIMPLE achieves competitive performance without updating the inference backbone, while lightweight adapter calibration attains leading performance on most evaluated datasets. Together, the results under frozen, one-shot, and missing-view settings support the central hypothesis that multi-view reasoning itself can be pretrained and reused, while lightweight adapter calibration provides task-specific alignment when needed.

Distributed target tracking is essential for scalable and robust sensing systems, as it enables multiple radar nodes to cooperatively estimate a target state without relying on a centralized fusion center. In this paper, we present a fully distributed framework for single-target tracking in frequency-modulated continuous-wave (FMCW) radar networks. Each monostatic radar node observes local range and Doppler measurements and exchanges information only with neighboring nodes. Two consensus optimization-based estimators are developed. First, a Distributed Maximum A Posteriori (D-MAP) estimator is formulated for batch-based tracking, where prior state information is incorporated and the resulting optimization problem is solved using consensus-based alternating direction method of multipliers (ADMM). Second, a Distributed Extended Kalman Filter (D-EKF) is proposed for recursive tracking, where each node performs local prediction and correction followed by consensus ADMM-based information exchange. We derive the posterior Cramér-Rao lower bound (PCRLB) as a theoretical performance benchmark. Our simulation results show that D-MAP improves the accuracy of the estimation over the distributed maximum-likelihood baseline. These results demonstrate that the proposed framework provides a scalable and robust alternative to centralized radar tracking, given only local inter-node communication.

Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the full potential of world models for decision-making remains unrealized. The critical challenge lies in ensuring that future modeling is not merely predictive, but decision-informative: the predicted future must directly shape which trajectory is selected. Existing approaches decouple future representation learning from planning optimization, or share predicted states across trajectory candidates, thereby diluting the action-specific consequences that ought to guide selection. To bridge this gap, we propose DA-WAM, a framework that unifies predictive representation learning, action-conditioned future modeling, and trajectory scoring under a single decision-making objective. DA-WAM maintains predictive supervision throughout planner optimization via an online encoder and a stable momentum target, allowing future representations to co-evolve with the driving task. An action-conditioned predictor generates a distinct future latent state per trajectory candidate, which is then evaluated by a future-latent-conditioned factorized scorer. For the expert-matched trajectory, the predicted future latent is supervised by the observed future representation, while safety-critical hard negatives provide additional supervision near planning boundaries. Extensive experiments on NAVSIM-v1 and NAVSIM-v2 demonstrate state-of-the-art performance, while ablations and diagnostic analyses validate the key components.

Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD) hallucinations. Existing approaches for detecting or mitigating such hallucinations typically either construct scoring functions directly over learned object detector representations or modify the object detector itself to suppress hallucination emergence. However, the latent priors implicitly encoded in these representations remain largely unexplored and have not been explicitly decoded for OoD detection. To uncover and exploit these latent priors, we propose Structured Prior Knowledge (SPK), a hallucination-oriented framework that explicitly elicits OoD-relevant priors from pretrained object detectors. Specifically, SPK leverages in-distribution data and hallucination-inducing samples as diagnostic supervision to elicit part-level semantic concepts underlying object detector decision-making, rather than using them merely for rejection or object detector adaptation. The elicited semantic priors are further integrated with geometric and contextual priors to form a compact five-dimensional SPK representation for OoD detection. Extensive experiments across diverse object detector architectures and multiple OoD benchmarks demonstrate that SPK achieves state-of-the-art OoD detection. Our findings reveal that pretrained object detectors already encode substantially richer latent knowledge than is typically exploited for OoD detection. More importantly, this knowledge can be explicitly elicited and organized into a compact, structured, and interpretable knowledge space for prediction reliability analysis. This suggests a promising proactive route for improving object detector reliability by explicitly uncovering and leveraging latent priors. Code and data are available at: https://gricad-gitlab.univ-grenoble-alpes.fr/dnn-safety/spk

An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization identity---a confidence level fixes the radius of a relative-entropy ball of alternative models---but that ball cannot reach catastrophes the nominal deems impossible, precisely what a safe agent must hedge. We instead use an optimal-transport ball and study the coherent risk measure it induces, the Wasserstein entropic value-at-risk. It has a variational dual mirroring the entropic formula (an inverse temperature becomes a transport price), occupies a definite place in the risk hierarchy, and provably accounts for the reachable catastrophes the entropic measure ignores; we verify both dualities numerically. Driving the transport radius by belief entropy then yields a closed-form robust dynamic-programming operator whose caution contracts as the belief sharpens, with a certified safety sandwich and a sharp safety switch.

Large language model (LLM) agents can now post-train an LLM end-to-end. They can write code, launch training, evaluate checkpoints, and improve downstream performance, raising the prospect of AI-for-AI. We argue that this picture conflates two distinct capabilities: execution-level capability, iterating within a selected training strategy; and strategy-level capability, revising the high-level judgment as experimental evidence accumulates. Analyzing a large corpus of publicly released post-training trajectories, we find that across different tasks, the agent's training strategy is locked in at the very beginning, and the entire remaining budget is spent on local adjustments within the selected strategy. We then examine three natural explanations--missing experience, missing guidance, and insufficient reasoning--with escalating interventions. Extensive experiments show that (1) an experience-driven scaffold improves execution across the board (+12.6 points on GSM8K and +40.8 on HumanEval) but leaves the strategy static; (2) human guidance effectively redirects the initial strategy, yet the agent falls back into local adjustment loops once training starts; and (3) additional inference compute pays off on easier tasks but yields almost no gain on the hardest one. In conclusion, what agents lack is neither experience, guidance, nor reasoning compute, but a mechanism for spontaneously reevaluating their strategy during execution.

This paper proposes a lightweight, plug-and-play framework that improves robustness to viewpoint shifts in Vision-Language-Action (VLA) policies without policy retraining. To our knowledge, this is the first approach to directly leverage 3D Gaussian-based novel-view synthesis for observation-space adaptation in VLA policies. Current VLA performance relies on the implicit assumption that training and deployment camera configurations are identical. Our experiments show that even a small displacement of the camera mount can reduce the success rate on the LIBERO benchmark from about 90% to about 10% in the worst case. Prior approaches, such as large-scale fine-tuning or generative data augmentation, are computationally expensive and risk catastrophic forgetting. To address this, viewpoint shifts are reformulated as a localized novel-view synthesis problem. Under a Locality assumption, that camera perturbations remain within a small bounded region relative to the workspace, viewpoint normalization reduces to a scene- and policy-independent disocclusion task. Our work implements this idea with a 4M-parameter 3D-Gaussian canonicalizer prepended to a frozen VLA policy. Without modifying policy weights, GS-VLA improves performance across three orthogonal axes: (1) Policy architectures, (2) Unseen task suites, and (3) Perturbation scales. These results show that a lightweight visual module can recover a large fraction of the performance lost under viewpoint shift, without policy retraining.

Highly granular calorimeters provide detailed information about hadronic-shower development that may enable particle identification beyond their conventional role in energy measurement. We investigate how well this information can distinguish protons from positively charged pions and how the achievable discrimination depends on detector segmentation and particle energy. The study uses Geant4 simulations of isolated particles with energies from 10 to 100 GeV in a homogeneous lead-tungstate calorimeter. A Deep Sets model operating directly on cell positions and detected energy and time outperforms a boosted decision tree based on reconstructed shower observables. With cells measuring $3 \times 3 \times 6$ mm$^3$, Deep Sets achieves an accuracy of 93.8% at 10 GeV, decreasing to 67.2% at 100 GeV. Shower topology is independently informative, deposited energy provides the largest additional contribution, and timing supplies complementary information. Coarser segmentation reduces discrimination, with performance more sensitive to longitudinal than transverse granularity. These results provide an encouraging benchmark for calorimeter-based hadron identification and motivate its inclusion among the optimization targets for future highly granular calorimeters.

Long-term robot operation in evolving environments requires object-level understanding that persists across repeated revisits. Existing systems either overwrite history to maintain an up-to-date map or store semantic snapshots without consistent cross-session object identity, resulting in temporal amnesia: the systematic loss of object history that prevents answering queries such as "Where has the green chair been across all sessions?" We propose LT-Mem, a volatility-aware memory evolution framework that unifies spatially aligned instance-level 3D perception with volatility-conditioned temporal reasoning. First, a multi-session SLAM backbone provides spatially aligned per-object observations across sessions. Second, a reasoning layer governs how object memory evolves: deterministic evidence scoring preserves cross-session identity, and a volatility-aware policy selects among overwrite, hold, and multi-hypothesis actions based on each object's dynamics. Third, the resulting Tri-Memory structure (Live, Delta, Meta) preserves both current states and event histories, enabling longitudinal object-centric reasoning. We further introduce LT-VQA, a dataset and evaluation suite comprising multi-session recordings, persistent identity annotations, and temporal QA pairs. Experiments show that LT-Mem consistently outperforms baselines across all metrics while consuming an order of magnitude fewer tokens, and ablations confirm that gains are driven by the structured memory architecture rather than LLM capacity.

Deep reinforcement learning (DRL) has recently gained a great attention due to its real-time adaptation and effectiveness in complex optimization problems. This paper investigates the optimal deployment of millimeter-wave (mmWave) base stations (BSs) in a realistic, non-convex campus topology. The optimization problem is NP-hard, due to the non-convex, non-smooth nature of the max-min fairness objective. To overcome these constraints, we formulate the BS placement as a Markov Decision Process (MDP) and systematically benchmark four DRL schemes: a discrete single-agent Deep Q-Network (DQN), a spatially partitioned Multi-Agent DQN, a continuous single-agent Deep Deterministic Policy Gradient (DDPG), and a geographically partitioned multi-agent DDPG framework. Numerical evaluations reveal that the multi-agent DDPG approach substantially outperforms single-agent in dense scenarios. Additionally full coverage is achieved, and a fairness Jain's index of 0.94 is obtained. Finally, the multi-agent demonstrates highly efficient computational convergence of dense scenarios with $400$ users.

We present Eureka, a task-conditioned Meta-Agent architecture that compiles long-horizon tasks into dynamic obligation graphs with explicit acceptance semantics. During execution, Eureka forms Macro-Agents with specialized state, memory, operators, tools, verifiers, and local topology via receding-horizon planning, architecture promotion, and minimal-sufficient compilation. When bottlenecks recur, cost-benefit-gated evolution updates the local architecture under constraints. Theoretically, we establish results on regret, planning invalidation, amortization, subtree interfaces, serializability, and verification. Experimentally, Eureka completes 170/170 recursive tasks and generates 3,948 certificates with no false acceptances. Active context compresses median input from 9,490 to 4,005 tokens; incremental processing avoids 65.38% recomputation across 12,000 tasks; 16,000 concurrent executions serialize consistently. The same Meta-Agent instantiates a Theory-Discovery Agent and a Math/Conjecture Agent. The former yields structural results in quantum-process and spacetime theory. The latter identifies bottlenecks in Riemann Hypothesis research and advances a positivity certificate for Suzuki's localized Weil quadratic form to 0 < a <= 69/200 = 0.345, reaching ~99.55% of (log 2)/2. These results suggest that scientific-agent capability depends not only on the base model but on whether an architecture can be formed to match the task's cognitive structure.

Accurate and responsible medical question answering (QA) is important in healthcare, where complex cases require factual knowledge and nuanced reasoning. Existing medical QA systems, typically based on single-agent architectures and static retrieval, often lack adaptability, persistent memory, and structured decision-making. This work introduces an adaptive memory and reflection (AMR) agentic system, a multi-agent framework in which specialized agents use dedicated memory and reflection-based feedback to retrieve relevant prior cases and improve subsequent reasoning. Complexity assessment routes questions through solo, collaborative, or escalated workflows, while consensus and ethical overseer modules support reasoning consolidation and output review. Evaluation on MedQA and MedMCQA demonstrates strong performance compared with several baselines. Ablation studies show that combining agent-specific memory, reflection, and external retrieval yields the strongest performance. These findings highlight the potential of structured memory and feedback for developing more trustworthy medical agents. The source code is publicly available at https://github.com/mm-air/AMR-Agent.

Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of frontier, browser-based large language models (LLMs) to extract highly contextualized information. We demonstrate four escalating workflows, 1) given an expert curated prompt and research articles, most frontier LLMs perform well at data extraction, however can struggle with interpreting scientific context and nuance, 2) given simple instructions, LLMs can author their own prompts which were almost as eNective as expert-written prompts, 3) autonomous discovery of research literature was diNicult, agents either missed or hallucinated references, and 4) LLMs can create new datasets from published guidelines that closely match human-expert judges, but still require a human-in-the-loop. Together, these findings define an auditable division of labour in which experts specify the evidence standard, models cross-check repeated extractions and researchers resolve disputed cases, providing a practical route to scaling scientific data curation without relinquishing expert oversight.

Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recognition. Because covariance matrices live on the Symmetric Positive Definite (SPD) manifold, a normalization step is required before the Euclidean classifier. The faithful choice is the matrix logarithm (MLN-COV), which maps the SPD manifold to its tangent space; in practice it was abandoned in favour of the matrix square root because its eigendecomposition-based gradient is numerically unstable. We show that this instability is an artifact of computing the logarithm spectrally, not of the logarithm itself. Approximating the logarithm with finite polynomials in the covariance matrix removes the eigendecomposition from both passes: every operation becomes a General Matrix Multiplication (GEMM), the gradient stays bounded on the spectral support of the pre-normalized covariance, and the unstable 1/(lambda_i-lambda_j) term never appears. The key ingredient is a mean-eigenvalue pre-normalization that centres the spectrum near 1, away from the singularity of log, with a scalar post-compensation that returns the singular part of log(A) in closed form. Our recommended normalizer is a degree-8 Chebyshev expansion evaluated by a three-term matrix recurrence, with a matching reverse recurrence for the backward pass; Legendre, Laguerre, Taylor and Pade expansions are studied as controls that isolate the roles of the basis and of the target function. On three fine-grained benchmarks and ImageNet-1k the decomposition-free logarithm is both faster and more accurate than the spectral logarithm and than the square-root approximations it replaces, and at matched basis and degree the log target beats the square-root target, confirming that the gain comes from the faithful Riemannian map rather than from a better polynomial family.

High-refractive-index particles have recently attracted a growing interest in optical levitation experiments, offering the ability to further engineer optical forces through electromagnetic Mie resonances. Unlike standard silica particles, which are predominantly trapped in the dipole regime and exhibit trap frequencies mainly determined by material density, resonant meta-atoms formed by high-index particles enable qualitatively new trapping behaviors. In this work, we experimentally investigate the trapping of resonant silicon particles in an optical standing wave. A direct comparison of silicon and silica highlights the fundamental differences in their optical force scaling and trapping dynamics. Beyond conventional trapping at intensity-maxima, we demonstrate deterministic and stable three-dimensional trapping of silicon nanoparticles in optical intensity minima, a regime that remains inaccessible for silica particles. Drawing a mesoscopic analogy with blue-detuned atom trapping, our results establish meta-atoms as a versatile approach to further extend the optical manipulation tool box towards accessing novel trapping regimes e.g. in close proximity to a surface.

Autonomous vehicles depend on fast and reliable perception systems to detect surrounding vehicles, pedestrians, cyclists, traffic signs, and other road objects in real time. This paper presents a comprehensive survey and analysis of one-stage object detectors for autonomous driving rather than an implementation of a new detection system. The survey reviews the evolution of major one-stage detectors, including YOLOv1, SSD, RetinaNet, EfficientDet, anchor-free detectors such as FCOS and CenterNet, and recent real-time models such as YOLOv10. It compares these architectures through their design choices, feature-fusion strategies, loss functions, deployment trade-offs, and reported benchmark performance. The paper also summarizes commonly used autonomous-driving datasets, evaluation metrics, open challenges, and future research directions. Overall, this survey highlights how one-stage detectors balance speed, accuracy, efficiency, and robustness, while also emphasizing the remaining gap between benchmark results and dependable real-world autonomous-driving performance.

Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of prompts, memories, tools, skills, and routing rules. Because these contents jointly shape later execution, a harness update can disrupt previously reliable behavior even when the model is frozen. This raises a new question: how can an agent continually improve its state outside the model while retaining behavior acquired earlier? We formulate Harness Continual Learning (HCL), a new continual learning paradigm in which the harness evolves around a frozen foundation model, and define the resulting loss of earlier behavior as harness-level forgetting. We instantiate HCL with four execution-facing components: the Task Interface, Experience Memory, Capability Map, and Adaptive Router. We further introduce guarded harness evolution to separate update generation from state commitment. A Continual Optimizer proposes candidate harnesses from post-execution feedback, and a Continual Evaluator commits the resulting candidate harness only after checking current improvement, historical retention, and validity. Experiments on textual reasoning, multimodal perception, and open-world interaction demonstrate capability accumulation and failure recovery, with relative gains exceeding 10% over corresponding baselines in multiple settings. Component ablations assess the contribution of each harness component, while controlled retention sweeps reveal measurable harness-level forgetting and show that the stability--plasticity trade-off can be explicitly adjusted.

Hate speech is a real and timely threat that affects a large portion of online users, especially youth and minority groups. While building reliable and robust automatic hate speech detection (HSD) systems is paramount, we argue that this must also be balanced with the individual right to privacy. Exploring the intersection of HSD and privacy, we demonstrate that HSD systems might unintentionally achieve performance at the cost of encoding authorship, posing a threat to privacy. Building on these findings, we establish the notion of a privacy-HSD trade-off, which demands a careful balance. We benchmark a series of text privatization methods, as well as our newly proposed domain-specific AgnoSpeech technique, showing that balancing privacy and HSD is difficult but feasible. The findings make a strong case for more research on the trade-offs between privacy and HSD, both of which have tangible implications for the safeguarding of online participation.

Debates have recently emerged as a useful methodology for agentic AI to improve performance as well as to aid explainability and user engagement. For example, LLM-empowered agents may debate internally (with themselves) and/or externally (with other agents). In many settings where debates are used, debates' outcomes and resulting outputs are determined post-hoc by external judges, often LLMs. In this paper we develop and test a novel theory of debate judgement applicable to all settings where agents engage in debates by providing pros and cons for their opinions therein. Specifically, we identify a number of formal properties that debate judgement may be required to satisfy in general, as concerns reproducibility, robustness, groundedness and explainability. Then, we explore their satisfaction formally and/or experimentally, for claim verification settings, for two specific alternative debate judgement methods: variants of the LLMs as a judge idea and formal semantics drawn from computational argumentation. We show that the two methods give similar accuracy performances but the former may lack formal guarantees that the latter brings. Overall, our study indicates argumentation semantics as an ideal candidate for principled judges in debate-driven AI.

Automating graphic design synthesis from user-provided elements requires both a coherent overall composition and the exact preservation of each asset. Existing methods predict a layout as explicit bounding-box coordinates with a language model and then paste the assets into it, which separates spatial planning from visual synthesis and tends to produce rigid, mis-scaled compositions. We instead ask whether the layout can emerge implicitly inside a pretrained image-editing diffusion transformer. We present Mise-en-Scène, a two-stage framework. In the first stage, a diffusion transformer adapted with a small, knockout-selected LoRA drafts a complete design in which the arrangement of the elements emerges jointly with the rendered canvas. In the second stage, a deterministic match-and-place step moves the original high-resolution assets to the drafted positions, which guarantees exact asset fidelity and yields an editable, layered design that a designer can keep refining rather than a flat image. Notably, a minimal adaptation of the pretrained transformer already suffices, without the specialized conditioning machinery commonly introduced for multi-element generation. On the large-scale PrismLayersPlus benchmark, the designs produced by Mise-en-Scène are the closest to the ground truth in perceived quality among all compared methods, by a wide margin over both an LLM layout planner and a specialized layout transformer, while our match-and-place stage bridges the remaining fidelity gap to the ground-truth composites.

Electronic travel aids are pivotal for the independent mobility of the visually impaired. While Vision-Language Models (VLMs) offer rich environmental understanding, they often suffer from excessive false positives in dynamic scenarios, leading to cognitive overload. To address this, we present ForeSightGuide, an anticipatory assistive guidance framework that couples semantic scene understanding with predictive hazard assessment. Unlike reactive systems, ForeSightGuide leverages the reasoning capabilities of VLMs to anticipate obstacle motion, effectively filtering out non-threatening objects to provide concise, actionable guidance. To validate our approach, we introduce a novel dataset captured in complex, dynamic real-world traffic scenes, designed to benchmark predictive capabilities. Extensive experiments on both public benchmarks and our proposed dataset demonstrate that ForeSightGuide achieves state-of-the-art performance. Notably, it significantly mitigates information overload by reducing redundant alerts to 0.299 per guidance output while maintaining a low missed-hazard rate of 0.112, proving its efficacy for safe walking assistance.

Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as evidence synthesis. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis gap between retrieval and generation. Thus, we propose DeepWeaver, a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence. DeepWeaver uses subordinate TBCs to inspect residual evidence, commit TBC revisions, and discover new claims before final generation. We evaluate DeepWeaver on open-ended QA over both knowledge bases and the web, and introduce LoQA, a high-density benchmark for evidence synthesis. Across multiple LLMs, DeepWeaver improves content sufficiency, citation grounding, and detail preservation on LoQA, while achieving deeper insights and higher citation quality on DeepResearch Bench. These results show that evidence weaving is an effective mechanism for bridging retrieval and generation in open-ended QA. Our code is available at https://github.com/KlozeWang/DeepWeaver.

Digital subtraction angiography (DSA) is the reference standard for leptomeningeal collateral (LMC) assessment, providing critical prognostic insights to guide secondary treatment strategies, neurorehabilitation planning, and retrospective stroke research. However, clinical LMC grading via the ASITN/SIR scale relies on manual, highly variable visual inspection. We introduce X-LMC, a spatiotemporal framework for automated collateral scoring from time-resolved biplane DSA. The proposed architecture encodes spatial frame representations through a DINOv2 backbone, fuses orthogonal projections via a token-level cross-view attention module, and models representations of contrast bolus dynamics using a recurrent network architecture. We evaluate our framework on a multicenter dataset of 134 patients with M1-segment occlusions. In a 5-fold cross-validation setting, X-LMC yields higher point estimates than static architectures and spatiotemporal baselines adapted from related angiographic tasks, achieving a Quadratic Weighted Kappa (QWK) of 0.398 (vs. 0.322) and a dichotomized macro-F1 score of 0.711 (vs. 0.663) against the best-performing baseline. X-LMC performance also aligns with the observed clinical inter-rater agreement (QWK: 0.314). As the first DSA study attempting to automate LMC scoring, we demonstrate that multi-view temporal deep learning can capture collateral-specific contrast kinetics. Ultimately, these benchmarks delineate the clinical ambiguities and achievable performance boundaries of automated ASITN/SIR grading, establishing a reproducible foundation for objective hemodynamic phenotyping in stroke cohorts. Code is available at https://github.com/maedehafezi/X-LMC.

Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose chemical knowledge into molecular representations that generalize well in data-constrained scenarios. This paper presents Monroe, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 81 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding decorrelation; improved multi-task learning; and the use of a prior-data-fitted model (TabPFN) for downstream in-context prediction. Our evaluations use a principled pairwise comparison framework that measures statistically significant performance differences. Across established Polaris benchmarks, Monroe matches or exceeds existing MFMs, while on activity cliff benchmarks, designed to assess utility for molecular discovery, it achieves significant improvements over prior methods. Finally, ablation and transfer experiments show that PFN-based downstream predictors also substantially improve two leading existing models, MiniMol and CheMeleon, yielding new state-of-the-art variants we call MiniMol_PFN and CheMeleon_PFN, suggesting that our downstream adaptation strategy generalizes beyond Monroe. Source code is at github.com/blazejba/monroe.

Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a user's preferences or explaining why one item fits better than another - rather than mapping history directly to a ranked list. This reasoning, however, is expensive to repeat on every ranking request and, once produced, is typically consumed once and discarded, leaving it neither reusable across future requests nor easy to inspect or correct as user tastes drift. Our insight is that reasoning does not need to be regenerated at every call if it can instead be compressed once into a compact, structured memory that a lightweight model retrieves from. We propose rEDMRec, which distills a teacher LLM's reasoning into four typed, editable experience channels - long-term preference, short-term context, item-perception, and counterfactual hard-negative comparisons - maintained by an LLM memory controller that performs Add/Delete/Modify/Keep operations and refines entries via K-agent debate. A lightweight student LLM then ranks candidates purely by retrieving from this memory, without invoking the teacher again, decoupling online inference cost from reasoning depth. Across ML-1M, Amazon Beauty, and Steam and ten student backbones, rEDMRec improves HR@1 over zero-shot, few-shot, and RAG on every backbone, and over GraphRAG on most backbones, with Impv up to 13.3% vs. the second-best baseline on ML-1M. Channel ablations show that short-term context is the only channel that helps consistently across capacity tiers, whereas long-term, item-perception, and counterfactual contributions are capacity-dependent (and can reverse on the strongest students); debate-based memory optimization lowers bank duplication by 7.4 percentage points while raising downstream HR@1 by up to +0.029 over six optimization epochs.

Collecting robot hand-object interaction data is costly and embodiment-specific, yet abundant human-object videos remain unusable for robot training. We present RoboEdit, a human-to-robot video editing suite that transforms human manipulation videos into action-consistent, physically plausible robot videos with aligned 3D hand states. To enable scalable supervision, we introduce RoboEdit-ADC, an automatic pipeline that reconstructs and retargets 3D interactions from RGB videos across embodiments. This pipeline generates RoboEdit-14M, a large-scale dataset of 174K aligned video pairs (14M frames) spanning seven robot embodiments, diverse scenes, and interaction types. The core editing engine, RoboEdit-Trans, employs cross-embodiment adaptation modules to preserve temporal coherence while adapting appearance and motion. It further integrates a 3D Robot-State Decoder to recover per-frame hand states for structured motion supervision. Experiments show that RoboEdit achieves state-of-the-art editing quality and supports downstream robot control policies in real-world manipulation tasks. Ultimately, the RoboEdit suite unlocks the vast potential of unlabeled human videos, providing scalable, high-fidelity visual and 3D motion supervision for generalizable robot learning.

Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, our model achieves state-of-the-art performance on the OOD URSA-expert-2026 benchmark. Further analysis of reaction uniqueness shows that LLMs and conventional models explore complementary reaction spaces, motivating ensemble-based retrosynthesis systems. Overall, our results establish Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning.

Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual inputs in real-world and safety-critical applications. Despite their growing deployment, the robustness of VLMs against adversarial threats remains insufficiently explored, particularly in the context of evasion attacks targeting multimodal alignment. In this work, we investigate the vulnerability of VLMs to adversarial perturbations applied to visual inputs and study two attack settings: untargeted attacks, where the goal is to disrupt the model's interpretation of the original image, and targeted attacks, where the adversary aims to force the model to generate a specific semantic description unrelated to the original image. To efficiently generate adversarial examples, we propose a gradient-based attack method that performs optimization exclusively on the vision encoder of the VLM rather than on the entire multimodal architecture. This design significantly reduces the computational cost and resource requirements of the attack while maintaining strong effectiveness. We evaluate our approach on several open-source VLMs, including Qwen2.5-VL, Granite-Vision, FastVLM, and Phi-3.5-Vision, and show that small, human-imperceptible perturbations can substantially alter the textual interpretation produced by the models. Our findings highlight the vulnerability of modern VLMs to adversarial manipulation and emphasize the need for improved robustness and security mechanisms in multimodal AI systems.

Recent Multimodal Large Language Models (MLLMs) are rapidly evolving into unified understanding and generation (UAG) frameworks. However, extending these unified paradigms to the medical domain is hindered by: the absence of comprehensive training and evaluation benchmarks, and the lack of broadly validated unified medical model. To address these gaps, we present a comprehensive foundation for medical UAG. First, we construct MedUAGCorpus, the largest unified medical understanding and generation dataset to date, comprising over 6 million instances across 14 imaging modalities. Second, we introduce MedUAGBench, a systematic benchmark that expands medical generation evaluation to 12 diverse tasks under standardized protocols. Finally, leveraging these resources, we develop MedUAG, an end-to-end trained unified medical model. Extensive experiments demonstrate that MedUAG achieves strong performance across a wide array of understanding and generation tasks, establishing a competitive baseline and paving the way for next-generation medical multimodal systems.

Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two ways. Symbolic equations give no global view of an architecture at a glance. Probabilistic graphical models and flowcharts do not describe actual tensor manipulations, thus hiding key insights and limiting reproducibility. To close this gap, we introduce a graphical notation for designing interpretable AI architectures, adapted from Penrose tensor notation. This graphical notation gives a global view of an architecture and maps one to one onto PyTorch einsum code. We first use this notation to describe architectures that are interpretable by construction, including concept bottlenecks, sparse probes, prototype networks, neural additive models, and mixtures of linear models. We then diagram the key architectural components of Steerling-8B, a frontier interpretable language model. The diagram yields global insights into the architecture (e.g., showing that Steerling is a residual model), a geometric interpretation of each individual operation, and a direct translation into 33 lines of PyTorch code.

Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to resolve issues in a specific repository because they lack project-specific knowledge. Existing self-evolving approaches acquire such knowledge from repository history or online repair trajectories, but they either depend on available historical issue-resolution signals or incur substantial per-issue test-time exploration cost. In this paper, we propose SkillForge, a self-distillation framework that proactively acquires project-specific knowledge from the repository itself. Instead of waiting for real issues to expose project-specific knowledge gaps, SkillForge synthesizes project-specific issues by re-implementing test-covered core functionalities of the repository. By resolving these synthetic issues, SkillForge distills reusable project-specific knowledge into entity-grounded skills and associates them with relevant repository entities for future issue resolution. Extensive experiments using both open-source and closed-source models show that SkillForge consistently improves issue resolution performance over strong baselines. These results demonstrate that proactively acquiring project-specific knowledge before solving real issues substantially improves downstream software issue resolution.

Estimating causal effects under network interference typically assumes that the network used for training and the network used for deployment coincide. In practice, an intervention is run on one population while the question of interest concerns a different population, and the two generally differ in topology, node-covariate composition, and spillover pathways. Transporting a causal effect across networks is therefore a data-fusion problem that no existing algorithm solves. We employ a selection diagram, extended to the network setting so that covariate shift and structural network shift enter as separate selectors, and derive from it a transport formula for the direct, spillover, and total effects in the deployment population. Each formula makes explicit which interventional mechanism is assumed invariant and which observational distribution must be reweighted. We then turn the formulas into TranCE (Transported Causal Effects), a doubly-robust algorithm combining an interventional outcome model, a domain density-ratio correction, and cross-fitted inference. Extensive experiments on two semi-synthetic benchmarks derived from real-world social networks and on a fully real weather-insurance field experiment, where the transported effects are checked against held-out randomized estimates, confirm the effectiveness of our approach. Our findings have the potential to improve intervention strategies in networked systems, particularly in social networks and public health.

Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over partial sequences, or iteratively refining drafts. These techniques yield large gains on mathematics and code, but have been developed and stress-tested almost exclusively on tasks where verification is straightforward. We conduct the first compute-normalised comparison of five TTS families across five open-ended generation benchmarks spanning medicine, law, finance, general chat, and creative writing - grounded in a unified framework that decomposes the effectiveness of each method's token budget into exploration and exploitation. The answer depends on which side of that decomposition you examine. Scaling exploration works: the best candidate in the pool improves steadily with compute across all settings. What breaks is exploitation - the step that converts a rich candidate pool into a final output. With state-of-the-art generators, reward models correlate at only $ρ_v \approx 0.12$ with true quality, rendering selection near-random regardless of budget. Tree search amplifies this failure through diversity collapse. Refinement helps on one of five benchmarks; its apparent gains elsewhere are confounded. Only synthesis across candidates (Fusion) consistently improves over single-sample baselines, yet still recovers only ~40% of available quality. The candidate pool is not the bottleneck - choosing from it is.

Tabular machine learning benchmarks typically summarize performance by averaging scores, ranks, or pairwise wins across datasets. Such aggregates are useful for selecting robust default models, but they can obscure a different question: which models are necessary to attain peak performance on particular datasets? We argue that benchmark evaluation should also consider the data-centric peak performance frontier, defined by the best statistically supported performance achieved on each dataset. From this perspective, a model may be irreplaceable, sufficient, redundant, or fallible depending on where it lies on the frontier relative to other models. Applying this framework to the TabArena benchmark, we find that common aggregation metrics are highly correlated and largely measure consistency and avoiding failures, while being much less aligned with dataset-level irreplaceability. Consequently, models performing decently across datasets without ever being the best choice are rewarded while models with unique dataset-specific strengths appear mediocre under aggregation. Hence, benchmark progress should be measured not only by improvements on aggregation metrics but also by whether new models expand the set of attainable peak performances across datasets.

Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show that on systems assembled from several weakly interacting components --- a structure common in physical and biological settings --- this may either require an exponential number of modes, or drop an entire component: the component is absent from the model rather than modeled coarsely, and no function of it can be predicted at any accuracy. We call this linear masking. The cause is that a rank-based model pays one coordinate per mode. We propose to score instead the $σ$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators rather than by all its interactions. The criterion is a $χ^2$-divergence between the embedded present and future, and it carries a budget guarantee: twice the intrinsic dimension of the dynamics is enough coordinates for an embedding whose algebra carries the operator's entire spectrum, with its full infinite rank. In variational form the criterion admits off-the-shelf estimators, and restricting its critic to the bilinear class returns the VAMP score on the span, so rank-based methods are one end of the same family. We demonstrate the proposed objective on a composite of published benchmark systems. We exhibit examples where the rank-based methods completely miss the masked components at all ranks $k<100$, while ten algebra coordinates recover all of them. In addition, the resulting algebra representation supports predicting the masked components from few labels, while direct regression from the high-dimensional observation or from the VAMP features fail.

This work evaluates surrogate-assisted optimization of a seven-parameter current-excited coil--core benchmark subject to geometric, manufacturing, and separate core and copper mass constraints. A Python--MPh--COMSOL workflow couples a two-dimensional axisymmetric finite-element method (FEM) model to a Matern 5/2 Gaussian-process (GP) probabilistic surrogate. Here, physics-constrained denotes a design problem evaluated by a governing-equation FEM model and restricted by explicit physical, geometric, manufacturing, and material-allocation constraints; it does not denote a physics-informed GP architecture. Sequential Bayesian optimization (BO) ranks candidates using expected improvement (EI), and every reported incumbent is verified by FEM. Five paired runs show that optimizer ranking depends on the available FEM-evaluation budget: EI--BO improves rapidly at small continuation budgets, COBYLA is stronger at the earliest checkpoint, and BOBYQA attains the highest mean terminal response. A retrospective finite-pool study further finds no robust endpoint advantage of EI over posterior-mean ranking on this smooth response surface. The broader result is that early progress, terminal response, information use, and wall-clock cost can favor different methods in simulation-driven design. A selected-design check at a common total current preserves the observed BOBYQA--COBYLA--EI-BO ordering. The conclusions nevertheless remain conditional on this axisymmetric benchmark and do not establish a fixed-current optimum, fixed-power performance, or electrical-efficiency superiority.

Class expression learning often produces complex OWL class expressions that are difficult to interpret and reason over. However, by following theoretically grounded simplification principles, this complexity can be reduced. In this paper, we propose Class Expression Simplifier (CES), a novel algorithm for the syntactic simplification of class expressions in Description Logics (DL). CES aims to preserve formal semantics while reducing representational complexity. It systematically applies rewriting rules to eliminate redundancies and identify simpler yet equivalent expressions, thereby producing more compact and human-readable representations without altering logical entailments. We evaluate the effectiveness of CES on class expressions learned from two medium-sized ontologies, demonstrating measurable improvements in reasoning efficiency and reductions in verbosity. This work contributes to the broader goal of making ontology-driven applications more accessible, maintainable, and scalable, with direct implications for knowledge graph construction, semantic search, and Web-scale reasoning. CES is implemented within the open-source Python framework OWLAPY and is publicly available.

Reinforcement-learning training of reasoning LLMs (e.g., GRPO) is expensive and requires a controllable environment, committing every contribution to a full training pipeline. We present EvoResearcher, a training-free, inference-time protocol that adds cost-bounded self-reflection to a single frozen LLM backbone. The protocol iterates generate -> self-critique -> revise until a maximum depth D is reached or the critique returns the CONFIRMED sentinel, an implicit early stop that lets the backbone self-verify its answer under a strict compute budget. Four self-reflective meta-reward components (correctness, efficiency, reflection depth, tool-call diversity) act as design principles instantiated as prompt-level mechanisms, so their benefits accrue with zero gradient updates. We validate the protocol on Big-Bench Hard (100 questions) and establish cross-domain behavior on GSM8K (500) and MATH (500) on the same frozen backbone, with cross-model replication on Qwen2.5-72B. All experiments use pure-reasoning benchmarks; the tool-call diversity component is validated in prompt-level form, and the environment-level and multi-agent extensions are design blueprints left to future work. On clean BBH the protocol does not raise accuracy beyond the 95% Wilson interval; its value is cost-bounded self-verification, with the CONFIRMED early stop terminating 82-88% of items at equal accuracy (about 2.1 generations per question).

Autoregressive perception models trained to localize visual entities under the open-vocabulary setting are mostly trained using Supervised fine-tuning (SFT) with maximum likelihood, yet it optimizes a proxy objective (per-token cross-entropy) that is fundamentally misaligned with perception metrics such as precision and recall. In this paper, we explore post-training reinforcement learning (RL), specifically GRPO, to directly align these models with their evaluation metrics. Building up on the recently introduced Falcon Perception, we design an RL framework that addresses perception-specific challenges: reward design for set-structured outputs and multi-head sampling control. We discover multiple benefits from RL for perception: first, RL unlocks state-of-the-art performance in very dense scenes (up to 500 objects per scene), a regime where most existing systems degrade sharply or collapse; furthermore it fixes common issues in autoregressive perception models like mask repetitions and removes almost entirely the need for NMS and coordinate deduplication, which improve both performance and efficiency and remove the need for hyperparameters tuning; overall, we notice improvements on all levels of difficulties in referring expression segmentation (on PBench and SACO-Gold), and we find an elegant way to preserve the knowledge of whether an object exists or not (as evaluated by MCC) without training on negative samples. We show that a simple reward that penalizes false negatives and positives is sufficient. We develop two hybrid self-annotation pipelines, respectively tailored for difficult referring expressions and very dense scenes, and show their benefits on RL-training. Model weights are released as a Falcon Perception revision~\footnote{https://huggingface.co/tiiuae/Falcon-Perception}. Datasets will be published.

Oral diseases affect billions of people worldwide, underscoring a pressing need for accurate and reliable dental assessment that integrates heterogeneous evidence from domain knowledge, radiographs, intraoral photographs, and 3D dental data. Most existing dental AI systems remain modality- or task-specific. Although recent vision-language models support flexible dental question answering, directly generated response leaves evidence implicit and untraceable. To address these limitations, we introduce DentAgent, an evidence-centric multi-agent framework, in which the Orchestrator coordinate five specialized agents spanning various modalities. Each specialist utilizes domain tools to convert observations into structured evidence records. The Evidence Blackboard manages these records as a shared evidence state, tracking coverage, gaps, and conflicts before response generation. This standardized evidence representation integrates isolated dental capabilities into a unified agentic workflow. Across four benchmarks, DentAgent demonstrates leading performance, even surpassing the senior specialists by 17.3 percentage points on multi-label diagnosis, which supports its value for broadly applicable and traceable multimodal dental reasoning, and highlights its potential as a technical foundation for population oral health assessment and management.

Scalable supervisors for multi-agent discrete-event systems control groups of isomorphic agents through a common template. Under partial observation, such a supervisor is maximally permissive if the relabeling that maps the agents onto their template is relabeling observation consistent (ROC) and a local companion condition holds. Whether ROC is decidable was open. We show that it is PSPACE-complete: for nondeterministic plants with two observable and one unobservable event, and for deterministic plants with two observable and two unobservable events. On the tractable side, we characterize the relabelings that guarantee ROC for every plant, we give a polynomial-time algorithm for deterministic plants whose relabeling is injective on unobservable events, and we give sufficient conditions based on saturation and on simulation, with polynomial-time tests for both. We further show that ROC is compositional for components with pairwise disjoint templates, with equivalence if the alphabets are moreover pairwise disjoint, and that neither hypothesis can be dropped. Finally, we show that the structural condition proposed in the literature to guarantee ROC is incorrect, and repair the companion inclusion that the same proposition asserts.

Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public libraries now hold thousands of them. Which skill to read has thus become a decision the policy itself makes in the middle of an episode, yet no existing signal trains it. We show that the default remedy, outcome-rewarded RL over the candidate slate, cannot teach it, for a structural reason we identify and name selector credit starvation: under a broadcast, sequence-level advantage, the few tokens that name the chosen skill carry a vanishing share of the loss, and the credit they inherit is increasingly wrong-signed as trajectories lengthen. A correct choice is punished whenever the execution after it fails, even though the choice itself is among the most valuable decisions in the trajectory. Auditing a completed run's own training artifacts confirms all three properties, each worsening monotonically with horizon. SkillGate removes the failure by construction: it partitions the token support into two disjoint credit channels, outcome credit reaching only execution tokens, and a separate action-local advantage reaching exactly the skill-naming tokens, positive only when a trajectory's single read is the correct one. On five agentic benchmarks under a 16-candidate slate, SkillGate lifts a 9B policy from 40.8% to 53.2% trial success, well ahead of the identical budget spent on outcome reward alone, while cutting exposure to misleading candidates by two thirds and reading fewer skills.

This paper presents a comparative study of real-time controller design methods for dynamical control systems subject to deadline overruns. Numerous techniques have been proposed to handle missed deadlines, i.e., including models or information of possible deadline misses directly in the control design. These approaches substantially differ in their assumptions, supported execution semantics, required runtime information, and provided guarantees, making direct comparison challenging. We address this gap with a qualitative assessment of representative deadline-miss-aware control methods. We analyze the design space of such controllers and identify the critical assumptions on the real-time constraints, the control design criteria and implementation aspects. We expose how these different assumptions lead to the different trade-offs in applicability, and control performance and guarantees. We contribute a comparison tool enabling researchers to systematically benchmark new techniques against the state of the art. The study is supported by simulations on two case studies: a Furuta pendulum and an electric motor to illustrate the practical behavior of the different approaches under missed-deadline conditions.

Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and Real Anchoring}), a modular two-stage framework that distills TFMs into lightweight MLP or tree-based predictors that can be deployed on commodity CPUs. Stage 1 uses synthetic covariates solely as teacher-query locations and trains the student on soft TFM targets, expanding coverage beyond observed rows. Stage 2 re-anchors the student to the target distribution using real labels and out-of-fold teacher predictions, whitch avoids self-labeling leakage. We further derive a risk certificate characterizing the trade-off between generated-query volume and generator fidelity. Experiments on TALENT and TabArena demonstrate the broad applicability of GEAR. Two-stage MLPs outperform supervised MLPs by 1.81--2.00 AUC points on binary tasks and 1.19--1.35 points on multiclass tasks, with additional gains over real-data-only distillation of 1.76--2.19 and 2.09--2.40 points, respectively. On binary tasks, the gains also transfer to LightGBM and XGBoost, and all three student families outperform CatBoost, the strongest non-TFM baseline, in mean AUC. Ablations show gains beyond longer training or alternative warm starts, greater stability from staged than mixed optimization, and generator-dependent diminishing returns as query volume increases. Finally, GEAR reduces median inference time by 57--2866 times and peak prediction memory by 1.9--3.3 times, while retaining higher AUC than matched supervised baselines.

Last-mile delivery aims to handle dynamically arriving orders with couriers while modeling complex spatial and temporal correlations. Recent learning-based methods model spatiotemporal dependencies among orders to predict courier service sequences, but leave next-order decision making unexplained. Describing the current delivery state in language allows LLMs to reason explicitly about the spatial, temporal, and behavioral cues behind an individual decision. As direct predictors, however, LLMs remain sensitive to task presentation and often produce unreliable decisions. To address these challenges, we introduce ORBITER, an agentic Order Arbiter for next-order decision-making in last-mile delivery. ORBITER models courier service through decision points, each containing the courier's spatiotemporal state and visible orders and exposing local trade-offs for modeling and verification. Fixed proposers rank the candidates, and a structured report identifies where their rankings disagree. The LLM uses task-specific tools to gather evidence on the leading alternatives, while an independent critic checks the resulting decision against that evidence. We conduct extensive evaluations on data in four cities, where ORBITER outperforms existing state-of-the-art baselines by up to 9.2% on average showing its effectiveness.

This paper presents a mixed-integer linear programming (MILP) framework for joint electric vehicle (EV) and electric bus (eBus) charging-infrastructure planning with photovoltaic (PV) self-consumption. The model co-optimizes charger siting, sizing, technology selection, eBus-to-depot assignment, and hourly charging schedules. A deterministic MILP is first formulated as a nominal benchmark and then extended to a scenario-based robust min--max formulation under vehicle energy-demand uncertainty. The robust model uses shared first-stage infrastructure decisions and scenario-specific operating decisions, and minimizes infrastructure cost plus the worst-case scenario operating cost through an epigraph reformulation. Soft-feasibility penalties quantify unmet charging energy, terminal state-of-charge (SOC) shortfall, and capacity violations under stressed scenarios. A 50-node case study shows that route-segment eBus demand and PV weighting alter charger deployment, technology mix, and grid import, while V2G enables hard-feasible robust operation at sufficiently large penalty weights. These results highlight that effective long-term infrastructure planning must simultaneously account for diverse vehicle fleets, operational strategies that adapt to different scenarios, and node-level constraints on charging capacity.

Indoor scene synthesis provides essential environments for embodied AI, robotic manipulation, and simulation-based policy learning. Recent code-based scene generation methods produce editable and extensible environments, yet they remain focused on visual construction and object-level articulation, leaving the functional usage of scenes largely unmodeled. To address this problem, we present RoomWright, an agentic usage-driven framework for generating 3D scenes represented entirely as code for embodied interaction. RoomWright performs usage-driven object reasoning, which treats each anchor as a task centre and admits task-required objects and their affordances. A code agent further enables multi-part interaction by compiling each interaction into a trigger, condition, effect rule that updates structured object states, capturing causal dependencies across objects. Moreover, since manipuland orientation is ambiguous and hard to recover from pixels, RoomWright alleviates this via annotation-informed usage-guided orientation. Extensive experiments demonstrate the effectiveness of our method. The resulting scenes are executable, editable, and simulation-ready, providing interactive environments for embodied AI and policy learning.

Utilities lose a substantial share of treated water to leakage, yet rarely trust artificial-intelligence localizers to dispatch crews: guessing everywhere cannot justify excavation. The gap is accountability, not accuracy: no method proves when it should not act. Here we recast leak localization as decision-making under verifiable abstention. A physics-grounded executor agent falsifies hypotheses (leak, demand, sensor, valve) against a digital twin; an independent supervisor agent, with a large-language-model (LLM) auditor, checks evidence against a code-verifiable contract, then certifies a dispatch, requests evidence or abstains. Under field-grade noise, a 32% forced baseline becomes 96% decision precision on acted events. On an independently generated benchmark it acts on only 4 of 33 leaks, all correct. A 194-event register of audited real leak locations with twin-simulated pressures and flows yields five excavation dispatches, three correct, and 44% survey recovery at full district precision. Accountable abstention offers a defensible route to autonomous water-infrastructure operation.

Medical vision-language models (VLMs) can achieve high accuracy but remain unreliable: they are systematically overconfident, benefit little from test-time reasoning, and lack the ability to reliably calibrate trust in their own responses. We introduce EVADE (Evidence-Verified Agentic Diagnosis with Escape), an inferential, non-training method that enhances the safety of deploying a single frozen VLM. EVADE responds and, when uncertain, localises the region most diagnostically relevant, re-answers on a zoomed view, and commits only when both the entire image and the zoomed view responses agree; otherwise, it abstains. To directly address verification hallucination in single-model self-checking, our main idea is to verify gate consistency across different image views rather than re-reading the model's own text. Experimental evaluation on VQA-RAD, SLAKE, and PathVQA using Qwen2.5-VL-7B reports that EVADE is the only method that simultaneously improves both calibration and selective risk while maintaining accuracy, reducing expected calibration error (ECE) by up to 45% compared to zero-shot. Chain-of-thought, self-consistency, and self-verification all fail at least one axis. A grounding analysis reports that self-proposed regions perform better at diagnostic structure localisation than centres or random crops. However, a 7B VLM cannot use this localisation to revise answers. Therefore, reliability gains come from the consistency gate and calibrated abstention.

Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, existing methods generate and revise reward functions as monolithic programs, making it difficult to reliably preserve and reuse effective components discovered in earlier iterations, leading to unstable performance across iterations. To address this, we propose Module Level Reward Evolution Framework (MLREF). At the core of MLREF is a module pool, a persistent repository of reusable reward components. MLREF treats the module pool as the primary optimization object: the pool evolves across iterations by accumulating successful modules, refining underperforming ones, and reusing proven components; while reward functions are constructed as linear combinations of modules drawn from this pool. To drive this evolution, MLREF integrates three mechanisms: reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback, which together improve the effectiveness and robustness of reward optimization. Experiments on 17 tasks show that MLREF outperforms strong baselines by 25.2% in locomotion and 6.6% in manipulation, with more stable optimization dynamics.

Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood. The Strong Expressive Lottery Ticket Hypothesis (SELTH) posits the existence of sparse GNNs that preserve Weisfeiler-Leman (WL) expressivity on static graphs. We generalize this existence result to a probabilistic statement for multi-relational and temporal domains via the relational WL (RWL). We prove that sufficiently parameterized RGNNs contain sparse subnetworks that maintain 1-RWL expressivity and derive a lower bound on the probability that a random pruning yields such a subnetwork. We show that common TGNNs and cross-graph message passing schemes admit RGNN reformulations such that they inherit these guarantees and, moreover, that the expressivity of a sparse RGNN is connected to its optimization behavior under common update regimes. Experiments instantiate the bound, compare it to empirical probabilities on synthetic data, and study how pre-training expressivity relates to optimization and prediction quality metrics on temporal and molecular benchmarks.

Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two issues cannot fully explain the performance gap between naive sequential training and offline joint training. In this paper, we highlight data co-observation as a distinct factor influencing continual learning performance. By decoupling the constraints of separate data access from stability and plasticity, we systematically investigate the representational benefits gained by observing training data together. Empirically, we demonstrate a consistent performance difference between joint and separate training across both supervised and self-supervised paradigms in generic data-incremental "chunking" scenarios, whilst mitigating forgetting and controlling for plasticity. Our findings indicate that simultaneous observation of training data (co-observation) yields benefits to the learner's generalization that extend well beyond mere knowledge retention, and that this effect does not require a specific continual distribution shift. Furthermore, we contextualize prominent continual learning mechanisms through this lens: while distillation-based approaches act only as effective knowledge retention mechanisms, our results suggest that the empirical success of memory replay goes beyond the mitigation of forgetting, actively reintroducing the benefits of data co-observation into the learning process.

Majority voting over multiple LLM samples is widely used to raise answer accuracy, yet its gain varies erratically: on hard questions it can even backfire. This paper gives a quantitative account of this failure. A pluralistic agreement index Gamma is defined as the expected fraction of the samples of a wrong run that agree with the consensus, normalized by a reference scale d=(1-p)/(C-1), and is decomposed into a mechanical component (what a vote delivers given only a per-case answer preference) and a preference-unexplained residual. The mechanical null is difficulty-matched and leak-free: each case is resimulated at its own accuracy and option preference, estimated from the case's other runs, so no run predicts its own agreement. On GPT-4.1 the decomposition shows benchmark-associated direction (an observational ordering over n=4 cells per benchmark, not a significance claim). On multiple-choice GPQA-Diamond, the per-case answer preference explains 81-93% of the held-out test-run agreement index: the shared-bias-dominates account over-claims here, because a wrong but attractive option the whole cohort latches onto is captured by the per-case preference channel (whether that preference is induced by shared training bias is not identified). On open-domain AIME, the mechanical preference explains only 59-78% (21-29% if shrunk to pure noise), and a preference-unexplained residual of 1.56-2.80 Gamma units survives, which a run-level preference-heterogeneity reference more than absorbs (1.4-2.1). A self-consistency backfire on hard questions is reproduced (binned voting gap down to -0.09, coupled CI [-0.12,-0.07]), and the highest-agreement bin reaches an accuracy of only 0.42-0.83, a 1.2-3.6x lift over base rate: agreement is graded evidence, not certification. No new voting method is proposed; code and evidence are committed and reproducible.

Achieving fast, high-fidelity state transfer is fundamental to scalable integrated photonics and quantum information processing. While adiabatic evolution provides inherent robustness against control and fabrication imperfections, its requirement for slow driving leads to impractically long propagation distances in photonic circuits. Existing acceleration strategies, such as shortcuts to adiabaticity (STA), can dramatically shorten evolution times but generally rely on non-native auxiliary couplings or delicate Hamiltonian engineering that are difficult to implement in practice. Here we introduce evolution-pause synthesis (EPS), an interference engineered shortcut protocol that achieves fast, near-perfect state transfer strictly within the native system Hamiltonian. It achieves this by treating transient excitations as coherent resources and canceling their accumulated amplitudes via strategically interleaved pauses. By decoupling relative dynamical phase accumulation from parameter variations, EPS steers open transition trajectories into a closed loop in complex amplitude space, enabling perfect state transfer without auxiliary fields or complex parameter detours. We demonstrate this mechanism in Landau-Zener dynamics and extend it to a multilevel STIRAP process, achieving an 11.8-fold acceleration over the adiabatic baseline. Further, we experimentally validate EPS on a silicon photonic platform, realizing high-fidelity state transfer in a $16\,μ\mathrm{m}$ footprint, a nearly tenfold reduction in device length compared with a $150\,μ\mathrm{m}$ adiabatic reference. EPS offers a general hardware-compatible framework for fast, practical coherent control across wave and quantum platforms.

Learning robotic policies requires dense rewards that remain informative when behavior departs from successful demonstrations. Progress-based rewards estimate how far an observation has advanced along a nominal successful trajectory, but may remain high after an incorrect transition. We introduce Dream2Reward, which learns a language-conditioned successful latent transition field from positive demonstrations. Given the visual history up to a transition start, the model predicts the latent displacement associated with successful execution and scores the observed displacement through signed directional and symmetric magnitude agreement. This transition-level comparison penalizes wrong-direction, overshooting, and stagnant motion even when the resulting observation appears to show progress. Dream2Reward requires no failure annotations, progress labels, or synthetic negatives, and produces a dense causal reward. Across mechanism diagnostics and shared-trajectory evaluations, it provides stronger success-failure separation and more informative feedback on low-quality behavior than progress-based alternatives. Across online and offline policy learning, the same frozen reward model reduces reward hacking and supports stronger downstream performance, including in real-robot manipulation. These results show that comparing realized motion with predicted successful change provides an effective way to convert positive demonstrations into dense rewards for robot learning.

Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate sensors for each device. By installing a single meter that measures a building's total electricity consumption, NILM algorithms can determine the active status of each appliance. However, traditional NILM systems use computationally intensive optimization algorithms to process offline data, limiting their capability for on-device deployment, where sensitive household data must be processed locally. This paper proposes a Tsetlin Machine (TM)-based NILM framework, targeting real-time applications on resource-constrained microcontrollers (MCUs), enabling privacy-preserving edge deployment. The problem is reformulated as a classification task, and the proposed approach achieves an average precision of 90% and recall of 96% for two-appliance classification, and 77% precision and 80% recall for four appliances on the REDD dataset. The trained model occupies only 18 KB of flash memory and achieves an inference latency of 0.43 ms on an ESP32, demonstrating its suitability for embedded NILM applications on MCUs.

Register automata are finite automata equipped with memory that recognize data languages over infinite alphabets. In this work, we investigate active learning algorithms for deterministic register automata (DRAs) over ordered data domains--covering both dense domains, such as the rationals, and non-dense domains such as the integers. We show that the active learning problem for DRAs over both dense and non-dense ordered domains can be treated within a single unified framework. More specifically, we develop and implement a polynomial-time active learning procedure for DRAs over ordered domains, using oracles for membership, equivalence and memorability queries. The memorability queries were originally introduced for learning DRAs over domains with identity tests. Our unified framework also leads to a new consequence: minimization of DRAs over the non-dense ordered domain of integers is decidable, extending a result previously known only for dense domains. Finally, we give improved complexity bounds of several decision problems for DRAs over ordered domains that are closely related to the queries used in active learning.

Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public retrieval benchmark derived from, and complementing GreekBarBench, which did not include retrieval. The new benchmark comprises 283 bar-exam questions, each accompanied by the facts of the case it refers to, and 6,308 candidate statutory articles to retrieve from. Questions and facts are stated in everyday language, but need to be mapped to the formal terminology of statutes and their abstract legal concepts. A further complication is that not all of the case facts are relevant to each question of a case. Experimenting with three BM25 variants and nine dense retrievers, we find that vanilla dense retrieval far outperforms vanilla sparse retrieval in Recall@100. However, LLM-based query reformulation helps BM25 close that gap, while also improving dense retrieval. With a ten-round ReAct-like LLM reformulation loop that we introduce, BM25 improves further in Recall@100 and obtains the best nDCG and MAP scores of all tested retrievers. Query reformulation also outperforms pseudo-relevance feedback, sparse-dense fusion, and English translation.

JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property \emph{decision-metric alignment}. We introduce Plan-Real Spearman, which measures latent--real rank agreement on random plans, and CEM-stage Spearman, which measures the same agreement as cross-entropy-method (CEM) search concentrates its proposal. We analyze sufficient conditions under which latent distance preserves real-cost rankings, identifying encoder distortion, terminal rollout error, and candidate margins as the controlling quantities. Guided by the observed empirical alignment gap, DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads. Across all our experiments, DA-LeWM accelerates convergence and achieves higher online success than LeWM, while probe scores remain similar. These results show that action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC.

Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them, are the ones nobody knows how to score. Can the metric write itself? Saying what makes an answer good is hard; pointing at something wrong with one is easier, so the metric we evolve is a pool of small Python operators that each flag a candidate for one named defect, or abstain, and vote. Asking a model for operators directly does not work: 183 candidates realise only 96 distinct behaviours, from one narrow region of an enormous space. EvalCEGAR instead borrows counterexample-guided abstraction refinement from program verification. It reads the pool as an abstraction and searches for a collision, two answers the operators score identically, one correct and one not. That pair, not a prompt, is the authoring request, and when a collision defeats every attempt the loop widens what an operator may read rather than resampling. On MBPP+ and HumanEval+, a sandbox whose hidden unit tests give exact ground truth, the loop writes a 55-line operator that closes 15.4% of the gap between flagging nothing and a perfect filter on 428 unseen tasks (+0.0065, p=0.0010) at a quarter of our best hand-written operator's flags. On the benchmark it never saw it matches that operator's effect exactly on a third of the flags. Six of eight runs admit such an operator and all six help out of sample; our 15 hand-written operators applied together as one filter lose accuracy. An LLM judge on the same information ties that delta on a nearly disjoint set of candidates, and charges a model call per candidate forever where the operator charges none.

This paper proposes a multi-agent framework built on CrewAI [1] for conversational business intelligence. Five specialized AI agents operate in a sequential pipeline to process natural language queries, retrieve and analyze data, generate visualizations via the Model Context Protocol (MCP) [2], and deliver actionable insights. The platform features a defense-in-depth security architecture for multi-tenant data isolation and a query parameterization mechanism for transforming conversational insights into reusable dashboard components. Evaluation across 300 end-to-end test cases spanning synthetic and production enterprise datasets demonstrates 95.3% functional accuracy, a mean response latency of 24 seconds, and a response quality score of 4.52/5.0 as assessed by an LLM-as-a-Judge framework, with a 93.0% hallucination-free rate, representing a 22.6 percentage point accuracy improvement and 20.2% quality gain over a single-agent baseline. Cross-model evaluation across four LLM backends and human expert validation confirm architectural generalizability and evaluator reliability. An ablation study confirms that the Data Analysis and Report Aggregation agents are the primary drivers of output quality.

Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces each client update. A malicious client can therefore train on corrupted targets, introduce incorrect context-token associations, and degrade the global model through repeated aggregation. Such degradation can also increase the risk of unreliable or hallucinatory generation. We propose Federated Learning with Normalization Signatures (FedLNS), a server-side framework for lightweight malicious-update screening. FedLNS represents each client update through changes in trainable normalization-layer parameters and screens suspicious updates against a robust, history-aware cross-client reference. Because the signatures are extracted at the server from the returned local models, FedLNS requires no additional client-to-server parameter or metadata exchange compared to standard federated learning (FL) methods. After screening, the retained full-model updates can be aggregated using standard FL or another compatible aggregation rule. FedLNS requires no raw client data, trusted server dataset, labeled attack examples, or separately trained detector. Experiments on GPT-style, BERT-style, and LLaMA-style models trained from scratch with 200 clients show that, under 40% population-level target manipulation, FedLNS achieves lower test perplexity than the strongest of six baselines for all three architectures under both IID (independently and identically distributed) and non-IID data partitions.

4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision encoders are largely limited to static 2D images or 3D point clouds without temporal modeling, or to 2D videos that lack accurate geometric depth reasoning. Consequently, current approaches fail to jointly capture spatial structure and motion evolution in dynamic scenes. We present CL4D, the first foundational 4D vision encoder that directly operates on dynamic point clouds, trained with a contrastive learning objective to align spatio-temporal geometric representations with natural language descriptions. By learning a shared embedding space between text and 4D scene dynamics, CL4D enables zero-shot motion-to-text and text-to-motion retrieval in dynamic environments and serves as a foundational 4D vision encoder for downstream 4D vision-language tasks. Building on this encoder, we introduce 4DVLM, a 4D vision-language model that conditions language generation on dynamic geometric representations. 4DVLM is the first VLM designed to operate directly on 4D point clouds without relying on 2D images, 2D videos, or static 3D point clouds. We train CL4D and subsequently 4DVLM on a newly constructed dataset termed DynAction4D capturing diverse human motions across varying object interactions and scene environments. Extensive experiments across multiple 4D human action benchmarks demonstrate that CL4D achieves state-of-the-art performance, with improvements of approximately ~16.75% over prior methods. Furthermore, 4DVLM outperforms frontier video VLMs such as Gemini and GPT-5 even when these models are provided with RGB video sequences corresponding to the same scenes represented as 4D point clouds for 4DVLM.

Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leaving calculation process unobserved. Here we introduce AtmosCoder-Bench, an execution-grounded benchmark that makes the calculation process visible. Built through a transferable semi-automated pipeline (436 problems, 3,910 variants, 7,029 graded quantities), every problem is validated to be unambiguous and human-solvable, with uniquely verifiable answers. We find that (i) multiple-choice formats inflate measured accuracy by at least 12 percentage points; (ii) many failures arise not from missing knowledge but from models failing to apply known formulas and constraints consistently throughout multi-step computation; and (iii) even frontier models remain weak when task-specific conditions invalidate familiar methods, often reverting to canonical solution patterns rather than adapting methods to the relevant physical regime, leaving expert oversight essential.

Text-space skill optimization adapts a frozen agent by evolving a natural-language skill document, accepting each candidate through a validation gate. Existing gates rely on verifiable rewards, confining these methods to tasks with an automatic verifier. Replacing the verifier with an LLM-judge gate would lift that restriction, but whether such a gate carries usable signal is untested. We ask a prior question: can we tell, before placing a judge in the loop, whether its scores separate correct from incorrect answers at all? We formalize a reference-free judge as a latent solver -- its verdict rests on agreement with whatever it would itself conclude, so its capacity to evaluate is bounded by its capacity to solve. The model yields a closed-form bound on discriminability (ROC-AUC) in the judge's competence $c$ and answer-space size $k$, a necessary condition $c > 1/k$, and the result that the marginal AUC is confounded by item difficulty while a within-question estimator is not. A non-intervening probe records judge scores on genuine optimization runs without altering any decision. We find discriminability at chance where competence sits near the floor and usable above it; that a judge's benchmark accuracy overstates the competence that matters; and, in a closed-loop study, that the screen predicts which kind of gating error occurs. The result is a cheap pre-deployment diagnostic for judge gates.

Diagnosing faults in rotating machinery is essential for ensuring the reliability of industrial processes. Random convolutional kernel-based Time Series Classification (TSC) methods, such as ROCKET and its variants, provide an attractive trade-off between predictive performance and computational efficiency. In this work, we evaluate SelF-Rocket for the multi-class diagnosis of both mechanical and electrical faults and introduce, as a new contribution, a multivariate extension of the original method. The proposed approach is compared with leading ROCKET-based methods on two public benchmark datasets, MaFaulDa (mechanical faults) and ITSC-UDG (stator inter-turn short circuits), under both univariate and multivariate settings. Experimental results show that SelF-Rocket achieves the best overall accuracy-latency trade-off among the evaluated methods, obtaining the highest classification performance on MaFaulDa while remaining highly competitive on the more challenging ITSC-UDG dataset.

Recent advances in generative video models have enabled camera-controlled world video generation, allowing models to synthesize videos under user-defined camera trajectories. However, existing video quality assessment (VQA) methods are mainly developed for natural videos and fail to capture the unique perceptual characteristics of camera-controlled generation, such as viewpoint consistency, motion coherence, and content preservation. In this work, we introduce CamWorldQA, the first benchmark for perceptual quality assessment of camera-controlled world video generation. CamWorldQA contains 720 generated videos produced by 6 representative generation methods from 20 diverse source videos under 6 camera trajectories, where each video is annotated with a human-rated perceptual quality score through subjective experiments. Furthermore, we propose CWQA, a no-reference quality assessment network with three complementary branches that extract spatial features, temporal motion features and optical flow features to jointly predict quality scores. Extensive experiments demonstrate that CWQA achieves superior performance over existing quality assessment methods on the CamWorldQA dataset.

Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalization. Yet their lack of interpretability, tendency to be overconfident, and sensitivity to real-world domain shifts pose critical challenges for safety- and mission-critical applications. Uncertainty quantification (UQ) offers a principled way to address these issues, but its integration into segmentation foundation models has yet to be explored. In this paper we present the first systematic evaluation of UQ methods applied to a foundation model for semantic segmentation. We fine-tune a lightweight DPT decoder on top of the pretrained SAM2 encoder to establish a simple yet competitive baseline and benchmark four representative UQ approaches - Monte Carlo Dropout, Deep Sub-Ensemble, Test-Time Augmentation, and Evidential Deep Learning - across Cityscapes, NYUv2, and two challenging out-of-domain settings. Our analysis compares segmentation accuracy, calibration, uncertainty quality, and inference time, revealing clear trade-offs between predictive performance, reliability, and computational cost. These results highlight both the promise and the current limitations of uncertainty-aware foundation models, pointing to the need for future work that jointly optimizes accuracy, robustness, and efficiency for real-world deployment.

Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual histories. In realistic settings, however, relevant information is often fragmented across applications and devices, as well as across users and time, requiring agents to integrate dispersed observations into coherent episodic memories while preserving their source provenance. To address these gaps, we introduce **MemFuseBench**, a benchmark for *multi-source memory fusion*. MemFuseBench is built with a Scene-to-Sensor pipeline that synthesizes controllable scenarios into source-tagged observations, evidence-grounded questions, and adversarial distractors. It enables systematic evaluation of temporal reasoning, cross-source evidence fusion, and robustness to noise. We further propose **MemFuse**, a structured memory system that preserves source-level evidence in event-layer atomic memory and organizes related atomic events into cluster-layer fused memory within a causal fusion graph. During retrieval, MemFuse retrieves and organizes related evidence fragments while maintaining traceability to original source events. Experiments on MemFuseBench show that MemFuse achieves the best overall performance among the evaluated memory systems under all three LLM settings and consistently improves performance on questions requiring cross-source evidence fusion.

Physical interaction quality is central to deformable-object manipulation, yet most benchmarks evaluate task success alone. A policy may complete the task while allowing slip or causing excessive compression. A primary bottleneck is the absence of visuo-tactile datasets that pair policy-visible contact observations with independent physical ground truth over complete tasks. We introduce SoftVTBench, a visuo-tactile dataset for physical-interaction-aware deformable-object manipulation. It contains 4,000 expert demonstrations and more than 50 assets, including volumetric deformable objects and visually matched rigid twins. At 20 Hz, each episode synchronizes multi-view RGB, dual-finger tactile RGB and marker motion, proprioception, language, and binary and continuous gripper actions, alongside evaluator-only finite-element (FEM) states. Building upon this dataset, we establish a closed-loop benchmark that uses fixed object-specific calibration to define the Deformation-aware Success Rate (DSR), which counts a rollout as successful only when it completes the task and keeps peak normalized deformation within tolerance. Across Diffusion Policy, $π_{0.5}$, and FastWAM, all 12 in-distribution configurations contain successful rollouts that violate the deformation tolerance, accounting for 0.7--24% of each configuration's successes. Under distribution shift, visuo-tactile variants achieve higher task success in all six policy--suite comparisons and higher DSR in five, whereas their in-distribution benefits are mixed. These results show that making touch available does not by itself ensure effective multimodal fusion. SoftVTBench therefore provides a common visuo-tactile resource for studying not only whether a policy succeeds, but how it physically interacts with deformable objects and when touch improves that interaction.

Digitizing the text from handwritten historical manuscripts is required to make them easily accessible, preservable, and to enable historical scholars to study them in new ways. Historical manuscripts, however, often exhibit complex heterogeneous layouts and non-standard appearance due to period-specific writing styles, page textures, camera noise, and other nuisance factors, making them difficult to perform OCR on. To tackle this challenge, we introduce a local traditional OCR pipeline, which can be iteratively fine-tuned on the target manuscript at the layout-level and the appearance-level. By adapting to the target manuscript distribution, the proposed Traditional OCR pipeline makes better predictions on subsequent pages, causing iterative reduction in human annotation effort, which is expensive and time-consuming as it requires historical domain expertise. Using this pipeline, we digitize text from three complex historical Sanskrit manuscripts and introduce a dataset with granular layout-level annotations, along with Unicode annotations in the standard PAGE-XML format. We demonstrate quantitative gains due to iterative fine-tuning of the proposed traditional OCR pipeline, and also benchmark the performance of leading Multi-Modal Large Language Models on the introduced Dataset. Code and dataset are available at: https://github.com/flame-cai/gnn-synthetic-layout-historical/.

Intelligent document processing (IDP) encompasses a broad range of tasks, including optical character recognition (OCR), document question answering (DocQA), and key information extraction (KIE). Despite their distinct objectives, these tasks share a common need to perceive document content, acquire task-relevant information, and progressively refine intermediate results. However, they are typically formulated as separate prediction problems and addressed by task-specific models or processing pipelines. We introduce DocClaw, a unified agentic system that formulates diverse intelligent document processing tasks as a shared process of interaction between an agent and a document. Given a document and a task-specific query, DocClaw follows an appropriate document skill to iteratively identify the information required, invoke relevant tools, and integrate the resulting observations into the desired output. Throughout this process, a structured document state organizes reusable document knowledge and task-specific interaction context, allowing the agent to accumulate, revisit, and progressively refine information as the interaction proceeds. Under this formulation, task-specific requirements are captured by the agent's interpretation of the query objective and the corresponding document skill, while the underlying interaction loop, tool space, and document state are shared across tasks. Extensive experiments across multiple intelligent document processing benchmarks demonstrate that DocClaw effectively handles diverse tasks within a single agentic framework and achieves competitive performance compared with both general-purpose VLMs and task-specific methods.

Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search beyond single-turn settings. Yet multi-turn RL training remains highly unstable, often causing severe performance degradation as the number of turns increases. Through theoretical analysis, we identify three tightly coupled sources of instability: rollout-training context mismatch, weak turn-level credit assignment under sparse terminal rewards, and asynchronous policy drift when short and long trajectories are optimized under different policy versions. We show that these issues share a common structural origin in flattened trajectory optimization and address them through a unified reverse-turn formulation. We propose Reverse-Turn Policy Optimization (RTPO), which organizes multi-turn rollouts as sparse reverse trees and performs turn-level policy updates in temporal reverse order, aligning each decision with its downstream continuation. RTPO enables causally consistent turn-level credit assignment and on-policy continuation to control asynchronous drift. We provide theoretical guarantees showing that RTPO eliminates context mismatch and asynchronous drift under the proposed turn-level formulation, reduces credit bias, and converges to recursive optimality. Experiments on multi-turn agentic RL benchmarks show that RTPO improves upon trajectory- and turn-level baselines by 21.50% and 10.76%, respectively, highlighting its potential to support more stable training for tool-using agents.

We introduce a failure-aware adversarial retrieval-augmented framework for improving robustness in natural language understanding. Rather than selecting synthetic examples with a fixed reward threshold, our method formulates adversarial data curation as a failure-mode contextual bandit problem. Candidate examples are generated with retrieval-augmented prompting, filtered by the current target model, automatically validated by an LLM judge ensemble, and clustered into recurring failure modes. A stochastic policy then selects which failure modes to sample for retraining, and is updated using validation-based reward that balances robustness gains, forgetting, and data cost. This makes the data curator itself the learning agent, enabling adaptive selection of the most useful model failures across training rounds. On standard benchmarks, our approach improves RoBERTa-base accuracy from 88.48% to 92.60% on SNLI, from 75.04% to 80.95% on ANLI, and from 54.67% to 71.99% on MultiNLI, while consistently outperforming prior adversarial augmentation methods. We further demonstrate transfer to FEVER fact verification, achieving up to 79.86\% FEVER score and 82.45\% accuracy with RoBERTa-large. Finally, we provide a theoretical interpretation showing that, under stated assumptions, failure-mode sampling can reduce shortcut-aligned gradient contributions while inducing bounded distributional drift. By combining retrieval, automated validation, contextual-bandit failure selection, and controlled adversarial retraining, our framework enables scalable robustness improvement without additional human annotation.

Amid concerns that generative AI may standardize art interpretation, this paper examines whether LLM-based interaction can support plural art-historical narrative construction. We present Sanyu Studio, a multi-agent dialogue system that models 321 Sanyu oil paintings as agents with fact, interpretation, organization, and memory-filtering mechanisms. Based on a seven-day workshop with eight art-university participants, the study shows that user prompts, evidence organization, and cognitive tendencies shaped divergent yet coherent versions of digital Sanyu. The findings suggest that, under conditions of limited historical evidence, AI can amplify human agency and offer public audiences an interactive entry point into art-historical interpretation.

Accurate forecasting of energy consumption is important for the efficient operation of power systems, with direct implications for operational costs, energy management, and system maintenance. Due to the availability of extensive high-resolution consumption data from smart meters, data-driven methods have been used for short-term and long-term forecasting. However, their comparative performance on real-world smart meter data is still not well studied. In this paper, we present an empirical benchmark of nine modern deep learning models for time-series forecasting, including linear, MLP-based, convolutional, and Transformer architectures. We evaluate these models on two publicly available smart meter datasets. Our analysis focuses on three factors that strongly affect forecasting performance: the length of historical input, the prediction horizon, and the choice of model architecture. We show that extending the historical context improves accuracy, but only up to a saturation point, after which additional input provides limited benefit. In contrast, accuracy decreases as the prediction horizon increases. We also investigate the trade-off between prediction accuracy and computational complexity, and assess the statistical significance and practical magnitude of performance differences across models. Our results show that deep learning models consistently outperform classical baselines, while lightweight architectures achieve relatively similar performance at significantly lower computational cost. Additionally, architectural differences only become meaningful at longer forecasting horizons and on more heterogeneous datasets. Finally, a subgroup analysis across geodemographic and household categories shows that model choice has limited impact for most population segments.

Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive applications such as search and rescue and emergency inspection. However, multimodal target cues, restricted views, and sparse feedback make it difficult to balance exploration with target convergence. Existing curiosity-driven methods assign a fixed intrinsic-reward weight throughout search, which can continue rewarding novelty after the agent nears the target and induce detours. We propose DynCur-Geo, a dynamic curiosity framework that adjusts prediction-error intrinsic reward according to remaining target distance. A distance-aware gate encourages early exploration and shifts the policy toward goal-directed behavior near the target, while potential-based reward shaping supplies dense progress guidance. Experiments across multimodal, cross-scene, disaster-affected, and long-range settings show consistent gains over active geo-localization baselines.

We present the orienteering problem with uncertain time-varying rewards (OP-UTVR), a novel variant of the orienteering problem (OP). While most existing OP formulations assume rewards to be known in advance, practical applications involve uncertain and time-varying rewards, as with shifting customer demand for delivery agents. OP-UTVR relaxes this assumption by allowing agents to estimate reward dynamics from observations and forecast future rewards. This enables informed routing decisions despite stochastic reward changes and inevitable prediction errors. We address this problem using three planners that differ in planning horizon and online adaptivity, and derive theoretical bounds on their performance under reward stochasticity. We further introduce a mobile service robot benchmark for OP-UTVR, where a robot navigates among pedestrians in indoor environments. Experiments reveal trade-offs between planning horizon and adaptivity, and demonstrate the effectiveness of long-horizon planning with online adaptation.

Egocentric video captures activities from the wearer's perspective, providing a direct view of human attention, hand--object interaction, and goal-directed behavior. This perspective is increasingly important for wearable intelligence, assistive systems, human--robot interaction, and embodied AI, yet it introduces challenges including ego-motion, occlusion, small active objects, viewpoint-dependent appearance, and long-range temporal dependencies. Vision--language models (VLMs) offer a promising foundation for addressing these challenges by linking visual observations with semantic knowledge and natural-language supervision. This survey presents a critical review of VLMs for egocentric video understanding, tracing the progression from conventional recognition architectures to multimodal foundation models and embodied systems. We organize the literature around tasks, datasets, hand--object interaction understanding, temporal reasoning, frame and clip selection, multimodal representation learning, prompting, semantic alignment, and model adaptation. Particular attention is given to graph-based and object-centric reasoning as mechanisms for modeling relations among hands, objects, actions, and scene context over time. We further examine how first-person perception and multimodal foundation models support wearable assistance, robot skill learning, human-to-robot transfer, and embodied decision making. Across the reviewed literature, a consistent limitation emerges: current models recognize visible objects more reliably than evolving interactions, actions, and user intent, especially over long activities. We therefore identify temporally grounded reasoning, interaction-aware supervision, efficient long-video processing, multimodal fusion, graph-enhanced representations, cross-domain generalization, privacy, and trustworthy evaluation as key priorities for deployable embodied intelligence.

Humans solve complex problems by constructing plans and mentally simulating their outcomes with an internal model of the world. Machine learning has produced world models that similarly predict the outcomes of action sequences, but the improvement of candidate plans still isn't fully learned. Current planners are either hand-designed, distilled from a hand-designed optimizer, or learned only to inform an amortized policy rather than to revise the plan itself. We introduce the Reinforced Planning, a method based on the idea that search can be learned by reinforcing good search rules into a neural planner. Our implementation RP1 learns both how to evaluate imagined outcomes through a critic, as well as how to improve multi-step plans through an optimizer trained fully offline from imagined world-model roll-outs. To our knowledge, RP1 is the first method to fully learn how to improve multi-step plans. Furthermore, it can be trained independently of and attached to any pretrained latent world model. Across visual navigation, arm reaching, and robotic manipulation on two world-model backbones, RP1 substantially outperforms hand-designed search algorithms, reaching near-perfect success in several settings while using $1,000 \times$ less world-model rollouts and being up to $67 \times$ faster than the strongest alternative under concurrent planner inference.

Underwater images suffer from color distortion, haze, and poor visibility due to light refraction and absorption in water. These challenges significantly impact the utilization of Autonomous Underwater Vehicles (AUVs) or marine robots. Typically, color and brightness distortions manifest at lower frequencies, while edge and texture distortions are prevalent at higher frequencies. Traditional methods struggle to concurrently rectify these mixed distortions as they primarily concentrate on the spatial domain. To address these issues, we introduce the Dynamic SpectraFormer, which enhances underwater images through a frequency domain transformer. The Dynamic SpectraFormer introduces an ultra-high-resolution sparse spectrum attention module, which could capture the long-term dependency without losing the universal approximating power. Additionally, we have developed a dynamic spectrum weight generation layer that serves as an adaptive spectrum band selector, accentuating critical frequency bands and suppressing less relevant ones. Consequently, this method significantly improves underwater image quality by addressing both high- and low-frequency distortions. Our extensive ablation studies and comparative evaluations consolidate the Dynamic SpectraFormer's efficacy across multiple underwater image enhancement benchmarks. The source code is available at https://github.com/arifence2024/DynamicSpectraFormer.git.

Inference with transformer models on CPUs is increasingly important, especially for Small Language Models (SLMs), where vector architectures are emerging as a promising execution substrate. The attention module is a major bottleneck due to high memory bandwidth requirements; FlashAttention mitigates this by fusing operations to improve data locality and reduce intermediate memory traffic. In this paper, we present FlashAttention-V, a blocked FlashAttention for scalable vector architectures that adapts efficiently from short to very long vectors by exploiting parallelism across attention heads, inter-head packing to enable efficient utilization of vector lengths beyond the head dimension, and improving vector register utilization and memory access locality. We integrate FlashAttention-V into ggml within llama.cpp and evaluate it on TinyLlama, Llama 3.2, Qwen2.5, and Pythia-410M using gem5 and a Banana Pi BPI-F3. On the Banana Pi BPI-F3, we confirm that loop reordering and loop unrolling across attention heads are effective optimization principles, scaling performance gains with larger models and most pronounced with short contexts and during decoding. Simulation-based analysis shows that FlashAttention-V achieves 22x-42x speedup over scalar FlashAttention at 512-bit VL in prefill, with an additional 2x-2.5x gain scaling to 64 lanes and 4096-bit VL. During decode, FlashAttention-V achieves 8x-11x speedup using 512-bit vector lengths over scalar FlashAttention, with performance showing diminishing sensitivity to vector width and lane count due to single-token, memory-bound execution. We further identify structural bottlenecks in Q8_0 quantized linear layers that limit arithmetic amortization under long-vector execution, consistent across RVV and Arm SVE, indicating that current quantization formats pose a fundamental challenge to long-vector scalability.

Autonomous endovascular navigation could support the delivery of mechanical thrombectomy to underserved areas, but controllers must navigate long, multi-stage paths across varying vascular anatomies. This study investigates Progressive Experience Fusion (PEF) to train a multi-task TD-MPC2 controller. We additionally evaluate a heuristic that changes the Model Predictive Path Integral planning horizon using residual action-sequence dispersion, and fine-tuning in a patient-specific simulation. Across five subtasks in ten known training anatomies with held-out targets, PEF achieved a mean success rate of 74%, compared with 37% for Soft Actor-Critic (p < 0.001) and 65% for base TD-MPC2 (p = 0.053). A PEF controller with adaptive-horizon planning trained on 30 vasculatures achieved a mean success rate of 90% in ten held-out vasculatures. The PEF agent successfully transferred to an unseen in vitro stroke patient vasculature under fluoroscopy, achieving a mean path ratio improvement from 63% to 80% with fine-tuning (p < 0.001), following 40x103 fine-tuning steps (corresponding to approximately 107 min of clinical inter-hospital transfer time). This work represents a proof of concept for multi-vasculature training and patient-specific adaptation, while further validation is required before clinical deployment.

Long-term video object segmentation (VOS) remains challenging due to error accumulation under extended occlusions, re-appearance, and scene changes. Although SAM2 provides strong zero-shot performance, its streaming memory can amplify drift over long horizons when recent, unreliable predictions dominate the memory state. We propose SAM2Dual, a training-free, plug-and-play inference-time enhancement that improves long-video robustness without updating model weights. SAM2Dual introduces a Dual Memory design that explicitly separates (i) short-term memory for rapid local adaptation and (ii) long-term memory built via interval-based sampling to preserve global identity cues, combined through a gated fusion strategy. In addition, we present Text-Aware Memory (TAM), which extracts a compact word-level cue from early frames and uses text embeddings to reweight memory contributions based on semantic compatibility, supporting identity preservation when visual evidence becomes weak or ambiguous. Across long-term benchmarks, SAM2Dual consistently improves stability on long videos, raising J&F from 49.33 to 50.65 on MOSEv2 and achieving consistent gains on LVOSv2.

Non-invasive continuous blood pressure (BP) monitoring using photoplethysmography (PPG) is a promising alternative to cuff-based measurements. However, existing PPG-based BP estimation studies predominantly rely on aggregated performance metrics (e.g., mean absolute error) computed over entire evaluation intervals, which can obscure model failures during rapid BP fluctuations and limit clinical relevance. In this work, we propose a fluctuation-aware evaluation framework for PPG-based BP estimation based on time-series change point detection. Instead of heuristic BP thresholding (e.g., $Δ\mathrm{BP} > 10\mathrm{mmHg}$), we identify BP change points by capturing abrupt distributional shifts in BP trajectories and evaluate estimation performance specifically during these fluctuation periods. Our analysis shows that several state-of-the-art models exhibit substantial performance degradation around BP change points, and that periodic test-time calibration is insufficient to handle such dynamic BP variations. To address this limitation, we introduce a targeted re-calibration framework triggered by detected BP change points, improving robustness without modifying model architectures. To the best of our knowledge, this is the first systematic evaluation of PPG-based BP estimation from a BP change point perspective, highlighting the importance of fluctuation-aware evaluation and calibration for real-world continuous BP monitoring.

Aerial nadir video combines weak geometric constraints with severe perceptual aliasing, making it a difficult regime for monocular SLAM. We benchmark five monocular SLAM systems on local UAV flights, synthetic city-scale imagery, and long-range aerial sequences. To isolate visual performance, we provide no inertial or GNSS aiding. Performance varies strongly with environment and trajectory scale: MASt3R-SLAM achieves the lowest mean horizontal MAE on the five DJI flights (0.53\% of reference path length), whereas no system consistently preserves global trajectory shape on the long GES and ALTO sequences. Overall, DROID-SLAM performs best, averaging 2.88\% of reference path length across completed runs. Vertical position remains poor, and large-area trajectories remain highly distorted despite loop-closure capability. Current monocular SLAM methods are by themselves therefore insufficient for reliable visual-only aerial navigation.

As large language models evolve into decision-making agents, the ability to reason over preferences becomes fundamental to alignment, coordination, and collective intelligence. Yet, unlike standard benchmarks, real-world preference reasoning is inherently indeterminate: information may be incomplete, and valid solutions may not exist. We argue that indeterminacy, rather than correctness alone, is a central challenge for AI reasoning. We formalize this challenge along two axes, (i) epistemic indeterminacy, arising from incomplete, partial, or expressive preferences, and (ii) structural indeterminacy, arising from the non-existence of solutions under standard social choice concepts. Across a hierarchy of tasks, we show that state-of-the-art language models systematically fail to distinguish between determined and undetermined instances, exhibiting miscalibrated reasoning even in verification settings.

Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under safety-constrained instruction, models frequently abstain from answering questions that remain correctly answerable under default instruction despite receiving identical image-question inputs. This raises a fundamental question: does safety alignment suppress perceptual grounding itself, or does visual evidence remain internally available while generation is redirected toward abstention? In this work, we investigate the internal decoding dynamics underlying safety-induced abstention in aligned VLMs. Across multiple architectures and multimodal benchmarks, we show that abstained generations remain consistently influenced by visual evidence throughout decoding, indicating that perceptual grounding is largely preserved despite refusal behavior. We further demonstrate that, although the representational organization of refusal differs substantially across architectures, safety-constrained instruction consistently alters late-stage hidden-state dynamics toward refusal-oriented decoding. Finally, through targeted activation-level interventions, we show that suppressing refusal-related representations reliably restores grounded answering behavior across models without retraining or modifying visual inputs. Together, these findings reveal a previously underexplored failure mode in aligned VLMs: safety alignment can override grounded visual expression even when perceptual evidence remains internally preserved.

No-reference point cloud quality assessment (PCQA) has been an active topic in recent years and is used to measure and optimize the visual experience of point clouds. However, large multimodal models (LMMs) have rarely been explored in this area. Previous LMM-based methods mainly rely on supervised fine-tuning to directly predict numerical quality scores, lacking the ability to generalize across datasets with heterogeneous MOS scales and limited annotations. A key difficulty is that absolute MOS regression can be brittle across datasets with different score scales and distortion distributions, whereas relative quality ranking is more stable under such shifts. In this paper, we present PCQA-R1, the first reinforcement learning LMM for 3D point cloud quality assessment to simultaneously model quality understanding and scoring. Built upon the group relative policy optimization (GRPO) strategy, PCQA-R1 first constructs a chain-of-thought dataset, PCQA-CoT, which serves as cold-start training data through a reverse reasoning strategy that teaches the LMM to generate its reasoning process. We further introduce a Gaussian proximity reward that prevents calibration drift by anchoring score predictions to the source MOS range. Experimental results demonstrate that PCQA-R1 achieves state-of-the-art cross-dataset generalization across five benchmarks and competitive in-domain accuracy. Ablation studies support the role of ranking, Gaussian reward, and cold-start traces.

Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse labware and instruments and execute long-horizon, state-dependent experimental procedures. Yet existing benchmarks do not jointly capture dexterous hand use, real-world laboratory interactions, and multi-stage experimental procedures, limiting systematic training and evaluation. To bridge this gap, we introduce LabDex, a large-scale real-world dataset and benchmark for dexterous manipulation in chemistry laboratories, organized around a hierarchical task taxonomy spanning atomic skills, compositional tasks, and long-horizon experiments. First, LabDex is cross-platform and, for the first time, unifies real-world and simulation platforms under a common framework, providing standardized task definitions, demonstrations, and evaluation protocols. Second, LabDex is large-scale and systematically organizes chemistry laboratory operations into three interconnected levels: Atomic Skills, which characterize fundamental dexterous manipulation capabilities; Compositional Skills; and Long-Horizon Laboratory Workflows. This hierarchical design not only supports the evaluation of end-task performance, but also enables the analysis of how fundamental dexterous skills compose and influence more complex laboratory operations. We conduct cross-level evaluations of representative robot learning methods in both real-world and simulation environments. The experimental results validate the effectiveness of the LabDex task design and demonstration data, and show that the benchmark supports the training and systematic evaluation of existing robotic policies across laboratory dexterous manipulation tasks at different levels, providing a foundation for further research and development of autonomous laboratory robots.

Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. The harness side of this shift has matured rapidly (planning loops, tool protocols, context management), but the corpus side has not: threat reports and vulnerability databases are still packaged for retrieval-augmented generation, as opaque chunks behind an embedding index. We argue that this substrate, not model capability, is the bottleneck on agentic CTI investigation, and present CTIFoundry, an agent-native corpus scaffold. At build time, CTIFoundry materializes the latent structure of a CTI corpus: a deterministic ontology graph over four authoritative knowledge bases (CVE, CWE, CAPEC, ATT&CK) whose official cross-references become typed, traversable edges; a span-grounded report layer whose canonical, alias-resolved cross-vendor entities index provenance-carrying chunks; and hybrid dense+lexical retrieval surfaces. At query time this structure is exposed through seven typed tools and three procedural skills mounted on a stock open-source agent harness. On the public CTIConnect benchmark, swapping only the action surface lifts the identically-harnessed agent by +0.19 to +0.28 overall F1 across a four-model, two-provider panel: a small model on CTIFoundry surpasses a flagship on the flat substrate, and the gain is not bought with search effort, since on both Claude models the scaffolded agent is more accurate at roughly half the tool calls. An ablation attributes it: typed structure carries the larger share, procedural skills convert structure into discipline, and the two compose super-additively, because skills bind only to structure that exists.

Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and synchronization. However, these metrics evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among the text prompt, video, and audio that shapes human preferences. Optimizing models against these metrics encourages reward hacking, generating video-audio content that achieves high scores on these metrics yet appears incoherent or unfaithful to human viewers. To address this problem, we first construct a large-scale human-preference dataset VAPref-10K for joint video-audio generation, comprising 9K prompts and 10.3K fine-grained paired comparisons from open-source generation models. We also introduce the VA-Judger-Bench benchmark with both in-domain and out-of-domain model comparisons to evaluate whether reward models truly align with human preferences. We further propose VA-Judger, a chain-of-thought omni-reward model for joint video-audio generation. In particular, VA-Judger first learns from pairs with clear quality gaps to establish structured output and coarse preference discrimination, then distills reliable preference explanations for harder near-quality comparisons via rejection sampling verified against human annotations, and finally performs dimension-wise reinforcement learning that decomposes human feedback into individual quality dimensions for denser reward signals than a single binary preference label. Experiments show that VA-Judger outperforms metric baselines in predicting human preferences on both in-domain and out-of-domain evaluations. Using its human-aligned rewards for post-training audio-video generation model also yields significant improvements in generation quality.

Computer vision is increasingly used to automate recognition tasks in large ecological datasets, but more complex tasks such as multi-object tracking continue to pose challenges. As researchers seek to incorporate vision models in ecology workflows, various lines of research have explored how to make imperfect predictions useful through human-in-the-loop processes. We propose a new approach to working with imperfect tracking predictions through an interactive prediction correction workflow taking place as a conversation with a multimodal large language model, which we tailor to a sonar fish tracking dataset as an initial proof of concept. We investigate the performance of the tool, Molmo2Fish, across guided and unguided tasks, correcting its own predicted tracks and external tracks. We find that Molmo2Fish achieves high performance on fish tracking and track correction tasks, but there is still much room to improve on incorporating natural language guidance. The code and data are publicly available at https://github.com/tidalove/molmo2fish.

Whether distinct neural architectures develop common collective dynamics remains an open question. Recent analysis of Transformer language models revealed a nearly flat, weakly infrared-enhanced time-scale density of states (TDOS) associated with near-marginal long-memory dynamics. Here we test whether a closely related organization emerges in Mamba, whose selective state-space dynamics provides a fundamentally different microscopic mechanism. Mamba allows relaxation dynamics to be resolved at three levels: the intrinsic spectrum of the learned state-space generator, its input-conditioned selective rescaling, and the collective TDOS of the complete block measured from its Jacobian. These spectra are not identical: selective dynamics and the remaining block transformations substantially reorganize the microscopic relaxation hierarchy. Nevertheless, the full block develops a reproducible slow-mode continuum whose infrared sector becomes progressively better resolved with increasing sequence length. Cumulative analysis yields $ρ(λ)\simλ^β$, with the long-sequence Mamba exponent stabilizing near $β_{\rm M}\simeq-0.17$. The corresponding memory dynamics follows $K(t)\sim t^{-(1+β)}$, close to the marginal $1/t$ regime. Despite fundamentally different microscopic dynamics, Transformer full-block spectra exhibit closely related infrared organization, with representative exponents of order $β_{\rm Tr}\sim-0.1$. These results separate explicit state-space memory from collective infrared organization and show that distinct sequence architectures can develop closely related near-marginal slow-mode dynamics. They extend infrared collective organization beyond Transformers and provide an independent test of the dynamical structure described by Cognitive Field Theory.

Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual layouts drive complexity. To address this, we introduce BudgetDoc, the first multimodal benchmark providing explicit supervision for model-budget-performance trade-offs across three document tasks. Using BudgetDoc, we train DRB (Document-Reasoning Balancer), an approx. 1B-parameter pre-flight estimator (SigLIP-2 + Qwen3-0.6B) that predicts ordinal model performance across budget levels, achieving a 0.753 weighted F1. When dynamically allocating reasoning budgets across five frontier models and three datasets, DRB matches or improves F1 scores compared to always-maximum-budget baselines in 9 of 15 configurations while drastically reducing cost. Finally, preliminary evaluations demonstrate DRB's potential to generalize to cross-model selection.

High-altitude platforms (HAPs) are emerging as persistent middle-layer infrastructures for space-air-ground integrated networks (SAGINs), offering a favorable compromise among coverage, latency, endurance, and deployment flexibility. Their role, however, is evolving beyond communication relaying toward the joint provision of sensing, storage, communication, computing, and intelligence (S^2C^2I). This survey presents a unified HAP-centric perspective on S^2C^2I integration. We first review HAP fundamentals, platform categories, and their principal roles in SAGINs, including wide-area access, relaying, backhaul, edge service, low-altitude aerial coordination, and cross-layer orchestration. We then develop an integrated architecture spanning multi-plane connectivity, payload functional splits, and a cloud-edge-HAP space continuum with hierarchical data, control, computing, and storage loops. The enabling technologies are systematically examined, covering heterogeneous RF, millimeter-wave, terahertz, free-space optical, and hybrid links; sensing payloads and integrated sensing and communication; onboard computing; storage and caching; and AI-based orchestration. We further synthesize standardization progress, open software and datasets, testbeds, field evidence, and a four-level evaluation methodology ranging from component validation to mission-level effectiveness. An emergency-response case study demonstrates that joint S^2C^2I orchestration substantially improves conjunctive service availability while reducing feeder-link traffic. Finally, we identify research opportunities in agentic AI, trustworthy autonomy, goal-oriented semantic operation and digital twins, and sustainable, certifiable, and open HAP-native systems. The resulting synthesis provides a coherent roadmap from platform design to network-wide deployment.

Multimodal large language models (MLLMs) are increasingly used as OCR systems in document and knowledge-processing pipelines, but their ability to faithfully read real handwriting remains underexplored. Existing OCR benchmarks focus largely on printed text or clean single-line inputs, leaving limited coverage of realistic handwritten OCR scenarios such as multilingual handwriting, writer errors, and structurally complex mathematical expressions. We introduce OmniHandwritingOCR, a diagnostic benchmark for evaluating MLLMs and OCR systems on handwritten OCR. It covers handwritten text recognition and handwritten mathematical expression recognition across six subtasks and twelve subsets, totaling 77.57K labeled images from public datasets and newly collected student writings. A key component is a difficulty-stratified multi-line formula corpus designed to test robustness under increasing structural complexity. We evaluate thirteen open- and closed-source systems with five complementary metrics under a unified protocol. Results show that current systems remain far from faithful transcription: performance drops sharply on complex multi-line formulas, model rankings vary across language and formula settings, and several generative models hallucinate plausible but visually unsupported corrections. OmniHandwritingOCR provides a challenging testbed for diagnosing language, content, structural, and visual-grounding failure modes of multimodal models in handwritten OCR scenarios.

Vision-based industrial anomaly detectors are calibrated on one distribution but may be deployed on another that differs in illumination, fixture placement, or sensor characteristics, sharply degrading an otherwise accurate detector. Adapting to the incoming lot is a natural response, but labeled anomalies are scarce. We therefore consider calibration using only a handful of verified-normal images available before scoring the rest of the lot. Existing fixes require backpropagation, detector-specific tuning, or choices about feature directions that few calibration samples cannot justify. We present SPARC, a few-shot calibration method that intercepts patch features between encoder and detector and removes a closed-form, spatially indexed estimate of deployment-time nuisance through per-cell subspace projection. It needs only $k \le 8$ verified-normal images and uses the algebraic saturation rank $r{=}k{-}1$ on the encoder's native patch grid. The correction requires no gradient or weight updates and works with memory-bank, density, prototype, and mutual detectors. On the shift-prone benchmarks, SPARC improves pooled Image AUROC and AU-PRO$_{0.3}$ for all seven detectors whose image scores depend on corrected patch features by $+13.8$ and $+3.5$ percentage points (pp), respectively; on benchmarks without engineered shift, the changes are small and mixed. Controls that give competing corrections the same calibration images attribute these gains to the per-cell subspace structure rather than the images alone. Further ablations support the saturation-rank choice and characterize sensitivity to backbone and calibration conditions.

Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in factual question answering. Existing end-to-end methods entangle knowledge elicitation with reasoning, making it difficult to determine whether correct answers arise from parametric knowledge or the input context. To address this challenge, we propose VAKE (Verifiable Activation of Parametric KnowledgE), a two-stage reinforcement-learning framework that externalizes latent parametric knowledge through explicit Priming and transfers the acquired elicitation capability to implicit Reasoning. Given a query and an insufficient retrieved subgraph, the Priming policy explicitly inserts bridging triples as verifiable evidence, with supervision provided by rewards derived from answers generated by a separate frozen model over the augmented subgraph. Building on the policy learned during Priming, the Reasoning stage trains the model to answer from the original input, testing whether the capability acquired through explicit knowledge elicitation transfers to implicit reasoning. Experiments across seven benchmarks and models from 3B to 14B show that VAKE consistently outperforms standard baselines, including when transferring directly from HotpotQA to OOD datasets. LLM-based evaluation further shows that over 80% of the inserted triples provide factual bridging knowledge not derivable from the retrieved context, while more than half elicit knowledge inaccessible through direct prompting. These results suggest that VAKE activates latent parametric knowledge rather than copying the input context or memorizing dataset-specific associations.

Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; if these artifacts are generated from inconsistent assumptions, the resulting task may be unsolvable or incorrectly evaluated. Meanwhile, multi-stage synthesis can discard the goals, dependencies, state transitions, and procedural constraints encoded in the original sources. We present FACET (Fine-grained Agentic Construction of Executable Tasks), a framework that addresses both information preservation and cross-artifact consistency. FACET reconstructs related agent skills into coherent, information-rich scenarios, then realizes and repairs the execution environment before generating the final task artifacts. The resulting container state serves as shared grounding for the instruction, solution, and verifier, while execution-based validation and targeted repair correct artifact-specific failures without unnecessarily regenerating valid components. FACET produces complex terminal tasks with dense executable checks, and successful trajectories collected from these tasks provide effective, data-efficient supervision. Fine-tuning models across multiple scales consistently improves performance on Terminal-Bench 2.1, while analyses of alternative generation schemes support the importance of environment-grounded construction for task validity and solution-verifier alignment. These results establish source-intent preservation and shared executable-state grounding as key principles for scalable terminal-task synthesis.

Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (IQA) by improving consistency between quality ratings and their underlying reasoning. However, most approaches supervise reasoning through human-provided ratings and rarely examine whether it faithfully reflects image quality. Rating accuracy alone does not ensure faithful reasoning; a shared reward also obscures supervision sources and may reinforce unfaithful reasoning when a correct rating occurs by chance. To improve the faithfulness and reliability of blind IQA, we aim to (1) decouple credit assignment for reasoning and rating and (2) provide verifiable supervision for faithful reasoning. We introduce MR-IQA-2, an actor-editor-judge framework that operationalizes reasoning-editing-reflection. The actor generates quality reasoning for an input image, and the editor revises the image according to the identified quality factors. A frozen judge compares the original and edited images and provides reflective supervision for the actor's reasoning. MR-IQA-2 further uses fine-grained credit assignment to decouple reasoning and rating supervision. Judge feedback supervises reasoning, whereas human ratings supervise the predicted rating. Masked token-specific updates distinguish these signals while preserving the causal relation from reasoning to rating. Across IQA benchmarks, MR-IQA-2 achieves competitive rating alignment with humans. Visual reflection also enables richer and more faithful visual understanding beyond rating, which may inform image-quality optimization and related downstream tasks. Code is available at https://github.com/RobinY99/MR-IQA-2.

Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites accumulate, mirroring a classical phenomenon in human working memory. Post-training quantization (PTQ) is now the default deployment path for open-weight models, yet its effect on this failure mode has not been tested. We evaluate three precision levels (FP16, INT8, INT4/NF4, via bitsandbytes) across three architecturally distinct instruction-tuned models (Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct), holding the retrieval task fixed. INT4 quantization significantly reduces accuracy under high interference in every model (e.g., from 81.0% to 68.3% for Qwen), confirmed by paired McNemar's tests ($p \le 2.6 \times 10^{-6}$) and a mixed-effects regression spanning all interference levels; INT8, often assumed safe, also carries a smaller but real penalty in two of three models. The effect is specific to semantically similar (word-type) distractors and reverses sign under a numeric control condition, and is mechanistically linked to a rise in same-key intrusion errors under INT4 (from 21.5% to 24.6% of trials, $p = 4.8 \times 10^{-7}$). A follow-up ablation shows the effect originates in the quantized transformer backbone rather than the output projection layer. These results suggest that bitsandbytes 4-bit quantization can impose an additional cost on applications relying on long, updatable, semantically dense contexts, even when aggregate benchmark accuracy appears largely unaffected. We release our code and tokenizer-verified vocabulary construction method at https://github.com/ShayanShahrabi/compress-and-forget

Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates the task of Agent Failure Attribution: given a failed multi-agent trajectory, identify the faulty agents and their corresponding error types. Existing approaches predominantly rely on LLMs to perform failure attribution, either through direct prompting, fine-tuning on synthetic data or complex agentic pipelines. While effective, these methods incur substantial computational overhead due to long-context processing, expensive post-training and handcrafted workflows. Moreover, empirical evidence shows that even state-of-the-art models achieve limited accuracy on existing benchmarks, suggesting that scaling model size alone is insufficient. In this work, we revisit this task and question the necessity of such expensive generative solutions. We introduce AFANet, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships. We show that with significantly fewer parameters and near-zero inference cost, AFANet (i) matches or outperforms LLM-based baselines, including fine-tuned models on in-domain benchmarks, (ii) maintains robust performance across different GNN architectures and (iii) can be further improved with inexpensive test-time adaptation on the OOD benchmark. Our results suggest that effective agent failure attribution does not require heavy LLM reasoning and a lightweight, structured approach can achieve strong performance.

Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address detection, localization, and explanation. Inspired by agent-style tool use, we instead introduce a Perception-as-Tool paradigm and instantiate it as PATE-Forensics, which architecturally decouples detection and localization from explanation generation while coupling detection and localization as tightly as possible within a forensic perception tool. The DINOv3-based tool couples a multi-granularity detection module that integrates global, patch-level, and segment-level evidence with a cue-guided localization module by spatializing the patch-level and segment-level evidence into forgery score maps that guide dense mask prediction. The original image and forensic perception outputs produced by the tool form structured forensic context for a general-purpose MLLM, which is guided by prompt constraints to generate explanations without task-specific fine-tuning. On DDL-X Track 3, PATE-Forensics achieves the best official score of 0.89, outperforming the second-ranked team by 0.19 points. Our code is available at https://github.com/yqli00000/PATE-Forensics.

This paper is concerned with robust instability of uncertain network systems. We consider the multi-agent system described as a network of single-input-single-output agents with identical nominal dynamics subject to heterogeneous perturbations. The network description is formalized as a feedback interconnection of a diagonal uncertainty, nominal identical agents, and a static interconnection matrix. Assuming that the nominal network is unstable, we seek the robust instability radius (RIR), defined as the smallest norm of the stable uncertainty that renders the network stable. Conditions for the network stability are developed, and upper and lower bounds on the RIR are derived. When the network connectivity matrix is rank one and all diagonal entries share the same sign or are zero, we give conditions under which the RIR is exactly characterized by a small gain argument.

Most LLM benchmarks rank models on their ability to automate work tasks. In practice, however, models are often used to assist other (human or LLM) agents. The question that drives model selection is therefore not only which model produces the best output, but which model most improves the work of another (weaker) agent. We introduce a unified framework that evaluates the capability of models to automate and augment another agent's performance. Across seven economically grounded real-world tasks, an assistant model writes assistance text for a standardized lower-capacity worker model, which produces the deliverable. In automation mode, the assistant produces the output directly. Outputs are scored through blind pairwise comparisons by an LLM judge panel with task-specific rubrics, replicated across ten runs. Rankings across the two regimes are only modestly correlated, and the automation winner loses augmentation on five of seven tasks. Assistance is not reliably positive. The unaided worker outranks every assisted condition on three tasks, and only one model's guidance beats no guidance on average. These results suggest that automation ability is an incomplete proxy for assistance quality, motivating benchmarks that evaluate models according to the roles they play in human-AI and multi-agent systems.

This paper investigates robust instability in nominally unstable uncertain networked dynamical systems, where all nominal agents share an identical single-input-single-output (SISO) linear time-invariant (LTI) system and each agent is subject to independent perturbations. This setting is motivated by the problem of sustaining periodic oscillations in nonlinear dynamics, for which exact analysis is generally intractable. We identify three classes of network structures including cyclic and certain rank-deficient networks for which the robust instability problem can be reduced to the analysis of a single representative SISO system. We derive sufficient conditions that exactly characterize the robust instability radius for these network classes. Finally, we demonstrate the practical utility of the proposed results by analyzing oscillatory behavior in a genetic regulatory network.

This paper presents a real-time control-constrained Differential Dynamic Programming (DDP) framework for underactuated legged robots. To address the limitation of classical DDP in handling control constraints, we propose an Accelerated Projected Gradient (APG)-based control-constrained DDP (ABC-DDP), which efficiently computes constrained solutions and identifies active sets without repeated Karush-Kuhn-Tucker (KKT) inversions. A virtual constraint is introduced to integrate control constraints within a feasibility-driven multiple-shooting framework, enabling stable optimization even from dynamically infeasible initializations. The proposed method supports real-time model predictive control (MPC) with short horizons under strong underactuation. Simulation results demonstrate static two-leg standing under external disturbances, along with diverse dynamic motions including slow catwalk, upright walking, and high-speed running within a unified MPC framework. To the best of our knowledge, this is the first demonstration of static two-leg standing of a quadruped robot achieved using real-time finite-horizon MPC.

Automated recognition of ancient cuneiform script poses a compound signal-degradation problem: the three-dimensional relief of clay tablets creates spatially varying illumination and cast shadows, surface erosion introduces structured noise that overlaps with genuine sign impressions, and severe class imbalance across 141 sign categories undermines classifier reliability. We introduce EpigraphNet, a segmentation-guided transformer pipeline evaluated on the Persepolis Fortification Archive. From 1,239 annotated tablet images, brightness-adaptive morphological preprocessing and zero-shot SAM2-Large segmentation generate clean binary symbol masks, which a fine-tuned Vision Transformer (ViT-B/16) with inverse-frequency class weighting then classifies. EpigraphNet reaches 86.41% top-1 accuracy on a 132-class benchmark, a 17.21 percentage-point gain over the strongest CNN baseline (ResNet-101, 69.20%) and 5.31-12.91% over four modern backbones (DeiT-B/16, Swin-B, ConvNeXt-B, EfficientNet-B4) under identical conditions. The full pipeline runs at approximately 18 ms per sign on an NVIDIA A100 GPU. A lower Spearman correlation between sign frequency and per-class performance indicates more balanced recognition across frequent and rare classes. Implementation is available at: github.com/r11up/sam-guided-vit

Modern e-commerce platforms often operate search, recommendation, personalization, and CRM systems independently, limiting opportunities for proactive customer re-engagement. This is particularly challenging for exploratory intents such as best smartphones or latest 5G phones, where users may leave the platform for external research before purchasing. We present a scalable, production-deployed framework that bridges search and CRM workflows through AI-powered Product Research Agents. The system identifies users with exploratory purchase intent and low engagement, conducts grounded multi-agent product research using behavioral signals, external knowledge, and enterprise catalog data, and delivers personalized recommendations through WhatsApp. We evaluate the framework in a 23-day production deployment involving approximately 15K WhatsApp notifications for mobile product discovery. The campaign achieved substantial CTR improvements over traditional WhatsApp recommendation campaigns, with evidence of secondary engagement through message forwarding and sharing. The deployment also generated downstream purchases and GMV impact, demonstrating the practical effectiveness of AI Product Research Agents for proactive customer re-engagement and end-to-end customer journey optimization.

Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive the right evidence. In financial reconciliation, the evidence needed for diagnosis is distributed across invoices, purchase orders, approvals, allocations, payments, ledger entries, and bank activity, linked by transactional relationships rather than textual similarity. End-to-end accuracy can therefore conflate evidence access with reasoning quality. We introduce FinRCA-Bench, a deterministic synthetic benchmark of 2,250 accounts-payable-to-bank reconciliation cases spanning 14 operational tables, including 1,500 injected failures across 15 causal categories and 750 legitimate or hard-negative cases. Root-cause labels and record-level evidence contracts are hidden from the model, allowing retrieval to be evaluated independently of answer correctness. We compare Rules/SQL, classical machine learning, dense semantic retrieval, deterministic relational expansion, and Typed Provenance Graph Retrieval (TPGR), a typed traversal restricted to persisted transaction relationships. Rules/SQL reaches 84.97% held-out exact accuracy and classical ML reaches 95.44%. Holding the reasoning model, prompt, and generation settings fixed while changing only retrieval increases macro required-record recall from 0.83% to 77.70% and exact 16-class accuracy from 2.05% to 72.44%. Structural retrieval failures outnumber reasoning failures with sufficient retrieval by 95 to 15; 254 correct predictions occur despite incomplete retrieval, and strict returned-evidence contract accuracy is only 5.72%. On FinRCA-Bench, retrieval architecture strongly shapes observed AI-system performance, and a correct root-cause label is a weak proxy for an auditable diagnosis.

Existing VLMs have achieved strong performance in video understanding, yet they struggle with long-video spatiotemporal reasoning when target objects become invisible, often mistaking "invisible" for "unknown". We define this challenge as hidden-state spatiotemporal reasoning: inferring object states during prolonged invisible intervals from context interactions. To address this, we propose StateTrace, a novel object-centric framework that endows VideoLLMs with an explicit mechanism for hidden state reasoning in long videos. StateTrace builds a reusable spatiotemporal state memory that organizes object trajectories, inter-object relations, and state-transition events into a structured reasoning substrate. At inference time, it retrieves question-relevant state-evolution trajectories and converts them into compact reasoning cues, enabling the model to explicitly reason about why an object disappears, how its state evolves while invisible, and whether that state should persist at query time. We further build HSR-Bench, a diagnostic benchmark for hidden-state reasoning, containing 1,427 video-QA samples from 1,384 unique videos. Extensive experiments across multiple VideoLLMs show that StateTrace consistently improves performance on both public benchmarks and HSR-Bench (e.g., improving VideoLLaMA3 from 39.6 to 64.2 on HSR-Bench).

Industrial explainable-recommendation systems built on LLMs incur a substantial serving cost: each request triggers an LLM generation, with latency in the hundreds of milliseconds and cost that scales linearly with traffic. We separate generation from selection: explanations are produced ahead of time as a frozen candidate pool (six prompt styles, two commodity LLMs), and a small CPU-resident selector picks one at request time. The stack needs no GPU and returns in under 100 ms. Our primary benchmark is a 2,958-pair XRec Google Local subset, evaluating six offline-pool selectors (LambdaRank, PPO, GRPO, DPO, teacher-student distillation) and three KG-path selectors (random walks, edge-disjoint enumeration, MMR-reranked paths). A 300-pair MovieLens-1M split with Claude-Sonnet-4.5 references serves as an internal cross-dataset check, since no public benchmark exists for this setting. All variants use the same BERTScore-F1 protocol as XRec and G-Refer, averaged across five seeds. LambdaRank reaches F1 = 0.500 on Google Local, exceeding both G-Refer and XRec, and F1 = 0.329 on the MovieLens-1M check. With seed variance below 0.003 F1, the ordering is reliable: pairwise learning-to-rank outperforms single-action RL (PPO, GRPO, DPO), which use only one labelled candidate per rollout, leaving K-1 labels unused. The KG-path family targets a different objective: all three variants reach USR = 1.000 on Google Local and 0.997-1.000 on MovieLens-1M, since per-request path grounding yields a unique output per query, avoiding template-collapse failures affecting cached-LLM outputs. A generator-pool study comparing Claude 3 Haiku and Claude Haiku 4.5 shows small F1 shifts (0.001-0.006) while preserving selector ranking: selector and generator can be evaluated independently, though absolute F1 depends on the generator. End-to-end build cost is near $15 on commodity hardware.

Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution space forms a vast combinatorial diamond lattice. Forcing this rich topology into monolithic trajectories causes a severe topological collapse, indiscriminately penalizing valid alternative explorations and severely degrading policy diversity. To address this, we propose DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation), a novel framework that shifts the paradigm from global forcing to topology-guided localized correction. DART-SD first models the execution process as a converging Interaction-State Transition Graph (ISTG), faithfully capturing the inherent diamond topology of successful and failed exploratory paths. During autonomous rollouts, the framework identifies the Critical Topological Breakpoint (CTB) and retrieves success-supported recovery references. Finally, we introduce a progressive self-distillation paradigm through CTB-guided localized supervision, ensuring that the training loss is calculated exclusively on the generated recovery steps while strictly protecting the valid reasoning prefix from destructive gradient updates. Experiments on complex multi-turn tool-calling benchmarks demonstrate that DART-SD significantly outperforms traditional full-trajectory baselines.

Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrastive fine-tuning. However, these methods largely inherit the same InfoNCE objective, whose optimization can prematurely saturate under a strong pre-trained initialization: on dense captions, the loss falls below 10^{-3} on 80% of batches within the first epoch, while its gradient reaches exact zero in fp32 in 47% of measurements. We find that this behavior is closely related to the large number of near-duplicate captions in dense-caption benchmarks, where a few highly similar negatives remain unresolved after the easy majority has already been separated. As a remedy, we introduce HN-CLIP, which uses the text encoder's own text-text geometry to construct per-negative adaptive similarity margins. Specifically, a detached caption-similarity matrix is added to the negative logits, assigning larger margins to more similar captions without mining, synthesizing, or resampling negatives. The resulting objective requires only one caption-similarity matrix and a masked logit addition during training, with no auxiliary data, additional parameters, offline preprocessing, or inference-time overhead. Extensive experiments on four dense-caption retrieval benchmarks show that HN-CLIP improves over the strongest competitors by +2.4--+4.3 R@1 while training 2.4x faster than GOAL and 5.4x faster than StructXLIP. Moreover, the proposed objective improves all six tested fine-tuning frameworks on the in-domain benchmarks and reaches the strongest full-data baseline with only 20% of the training data.

We are witnessing an explosion of agentic systems for computational chemistry simulations: from half a dozen in 2024 to a dozen in 2025, and the current number approaches fifty, surveyed in this Perspective as of 8 August 2026. The capabilities of these agentic systems are shifting from assisting in performing a selection of computational tasks to autonomous design and execution of \textit{in silico} experiments, their analysis, and even manuscript writing. The ultimate destination is a fully autonomous AI scientist, where the entirety of computational chemistry is performed on a machine by a machine, without human supervision. While we are not there yet, and all reported systems currently involve a human in the loop, the trend is unmistakable. Even building specialized agentic systems for computational chemistry is increasingly commoditized by generalist agents, which may in the end replace the need for the specialized ones altogether, since adding a new capability will be as easy as asking AI to do it for you. Both the explosion in their number and the very limited adoption beyond their own developers point that way, and we close this Perspective on what it leaves us to do. The speed and scale of disruption agentic systems are bringing to computational chemistry leave many of us dumbfounded about the field's future and what we should spend our efforts on, as already established specialists, teachers, and students, and we have no answer.

Continuum arm aerial manipulation systems leverage soft-manipulator compliance and dexterity for tasks in confined or hazardous environments, but propeller downwash can degrade performance, particularly near walls and the ground. This effect remains uncharacterized for continuum manipulators. This letter experimentally studies downwash-induced kinematic deviations of a tendon-driven continuum manipulator integrated with a multirotor platform. Under still-air conditions, the CM is compared with a constant-curvature (CC) model. Downwash- induced end-effector pose deviations are then quantified relative to the mean still-air experimental baseline at four propeller throttle levels in free space, and at maximum throttle near a wall, and near the ground. Vertical position and yaw show the largest deviations and are amplified by ground effect. A CC-guided Gaussian process regression (GPR) residual model is learned from experimental data that improves forward pose prediction RMSE (position by 89-95%, orientation by 47-79%), and support compensation-oriented, downwash-aware modeling of continuum arm aerial manipulation systems.

Universal multimodal retrieval aims to support diverse instruction-aware retrieval tasks, demanding both efficient corpus-scale matching and fine-grained semantic reasoning. Recent MLLM-based embedding methods typically derive representations from hidden states, while Chain-of-Thought (CoT) reasoning is emerging as a promising strategy for embedding enhancement by encoding intermediate semantic evidence into the representation space. However, existing CoT methods typically use item-wise reasoning over queries and candidates in isolation, providing no explicit evidence to distinguish a positive from a semantically confusable hard negative. Moreover, contrastive embeddings capture global similarity but struggle with meta-tasks requiring answer verification, category judgment or fine-grained reasoning. In this paper, we propose UMER, a Unified Multimodal Embedding and Ranking framework for universal multimodal retrieval. UMER replaces item-wise reflection with Pair-Aware Discriminative Reasoning, which compares query--candidate pairs to identify instruction-relevant matching and discrepancy evidence. UMER jointly learns contrastive embeddings for efficient global matching and discriminative ranking for explicit pairwise relevance judgment within a single MLLM. A complementary mutual distillation strategy further transfers reliable pairwise preferences between the embedding and ranking functions. On the MMEB-V2 benchmark, UMER achieves state-of-the-art performance under comparable experimental settings while supporting budget-adjustable inference.

Modeling object dynamics from limited visual observations is a fundamental problem for enabling accurate motion trajectory prediction in embodied interaction scenarios. Existing dynamics modeling methods first compress reconstructed particle representations into sparse Key Points and model their evolution using locally constrained interactions, thereby discarding fine-grained local details and obscuring discriminative interaction modeling across spatial and temporal scales, leading to drifting trajectories and inaccurate appearance prediction. To tackle these issues, we propose DyG$^2$T, a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations and modeling multi-scale interaction over particle graphs. Spatially, DyG$^2$T enriches each Key Point by aggregating neighboring raw particle positions to recover fine-grained local details, while explicitly encoding relative offsets among Key Points to enhance geometric structure perception. Temporally, we introduce a Temporal Disentangling Network (TDN) to identify dominant cross-frame variations in latent space and amplify inter-frame differences, yielding temporally discriminative representations that are subsequently aggregated via Temporal Attention to capture frame-wise temporal evolution cues. For comprehensive interaction modeling, a Particle Graph Transformer leverages global attention to preserve discriminative long-range dependencies among Key Points, mitigating representation homogenization induced by locality-constrained modeling and providing a robust basis for accurate trajectory prediction. Experiments on both synthetic and real-world datasets demonstrate that DyG$^2$T achieves accurate dynamics modeling and reasoning, and exhibits strong cross-object and real-world generalization.

Multi-agent Large Language Model (LLM) systems often struggle to collaborate with new teammates whose strategies shift mid-task. Because agents execute multi-step or temporally extended skills, they frequently continue executing outdated plans long after public evidence shows that a partner has changed its skill. Existing methods either treat partner tracking as passive context-leaving the agent aware of the shift but slow to act-or replan indiscriminately. We introduce BayesBeliefAgent, which pairs a hierarchical LLM planner with a Bayesian tracking module. Rather than replanning constantly, our agent interrupts its current skill only when a partner's actions directly contradict the inferred skill. Beyond standard reward, we evaluate performance using replanning efficiency and the belief-action gap: the fraction of total decisions where an agent with a correct partner estimate executes a non-complementary skill. Across benchmark Overcooked environments, contradiction-conditioned control drastically narrows this belief-action gap while requiring an order of magnitude fewer replans than heuristic methods

Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evidence, but real-world knowledge graphs are often sparse, outdated, and incomplete. Existing robustness evaluations usually report aggregate changes in answer quality after evidence is removed or perturbed, which measures sensitivity to incomplete support but leaves the source of degradation under-specified: the same score change can conflate the type of missing evidence, the response of the evaluated system, and the sensitivity of the answer-matching protocol. To address this gap, we propose \textbf{MissDiag}, a diagnostic evaluation framework for incomplete-knowledge robustness in KGQA and KG-RAG. MissDiag keeps the question and gold answer fixed while applying structurally typed missingness interventions to benchmark-provided support graphs, enabling paired comparisons that decompose robustness changes by evidence type, system response, and evaluation protocol rather than reducing them to a single aggregate score drop. Experiments across multiple system families show that incomplete-knowledge robustness is better understood as a typed degradation phenomenon than as a uniform property: answer-adjacent evidence loss produces the largest observed degradation, source-context removal is often neutral and can be beneficial, and semantic answer matching changes absolute scores while preserving the main typed degradation patterns. By transforming aggregate robustness measurement into typed diagnostic attribution, MissDiag provides a more interpretable basis for comparing, diagnosing, and stress-testing KGQA and KG-RAG systems under incomplete knowledge.

In a Transformer, each layer attends to past tokens only through KV produced at its own depth, despite the presence of deeper representations during autoregressive decoding. Feedback architectures allow shallow consumer layers to attend to KV produced by deeper past-token representations, but give all consumer layers the same fixed connection patterns to source layers. We propose WhiteMatter, which connects every attention layer to the representations from all layers of each past token, with connection weights that can vary across consumer layers and adapt to the source token. For each token, a router implements these connections by mixing its $L$ layer states into $k$ KV channels that are cached for subsequent tokens; each consumer layer attends to one of the channels. The number of channels $k$ controls the KV-cache size. Setting $k<L$ reduces the cache's memory footprint. In our pretraining experiments, WhiteMatter outperforms a vanilla Transformer with 50% more layers and retains most of this gain with a 50% KV-cache compression.

Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable sparse operator. Queries sharing a block route may have poorly overlapping supports, while retained attention mass alone does not determine the post-softmax error from skipped interactions. We show that partition geometry affects both pooled support and the predictability of the remaining residual from the sparse output. We introduce SparsePR, which combines Response-Coupled Partitioning with Probe-Fitted Residual Reconstruction. Sampled-query key responses form paired K/V groups, whose centroids induce query-response coordinates for shared routing. A small set of exact query rows then calibrates a call-specific affine correction from the sparse output within the output subspace observed in the probe residuals. Across four heterogeneous video generation and world models, SparsePR consistently reduces attention-reconstruction error. Ablations show that probe fitting accounts for most of this reduction, while response-coupled partitioning lowers hard-drop error and improves reconstruction under a finite probe budget. SparsePR preserves generation quality at 22.0-26.0% realized executed-pair density while achieving 1.48x-2.61x end-to-end speedups. Project page: https://pardistaghavi.github.io/SparsePR-website/

Semantic segmentation of aerial point cloud is trapped in a generalization crisis under distinct domain shifts. While test-time adaptation offers a privacy-preserving and computationally efficient way to adapt pre-trained models to unlabeled target-domain data during inference, existing methods, bound to closed-set label assumptions and non-scalable point-wise segmentation pipelines, still struggle with semantic shifts. We ask: can we adapt any given pre-trained aerial point cloud segmentation model to a shifted target domain at the inference phase alone, without additional training, while segmenting target-specific categories beyond the source label space on demand? This paper introduces COSTA, which breaks this limitation by shifting from closed-set point-wise adaptation to cluster-centric open-set semantic propagation. Our core discovery is that, once effectively adapted at test time, the rich feature distribution of aerial point clouds can be distilled into a compact set of well-separated semantic centroids that are transferable across label spaces. COSTA leverages this to reformulate open-set semantic segmentation as a cluster-level propagating process: it first bridges the domain gap through proven test-time adaptation, then groups each batch of target-domain points into a small set of semantic clusters based on the similarity distribution in the adapted feature space, and finally propagates high-confidence pseudo labels obtained from an open-vocabulary vision-language model to all points through cluster-level voting. This cluster-centric paradigm enables test-time adaptation of aerial point clouds under significant domain gaps with mixed semantic shifts. With DALES as the source domain, COSTA enables on-demand segmentation across three aerial point cloud benchmarks with distinct domains and heterogeneous category spaces, achieving up to 70.09% mIoU under this new setting.

We investigate the propagation of structured scalar optical beams in an effective anisotropic background inspired by the scalar sector of the Standard-Model Extension and controlled by a single dimensionless parameter $λ$. The physically relevant configuration is a transverse radial director field that modifies the radial part of the Helmholtz operator while preserving axial symmetry. Starting from the Green-function representation, we cast the propagation problem as an initial-value spectral reconstruction of a prescribed finite-aperture entrance profile at $z=0$ and verify that this profile is recovered at the launch plane across the values of $λ$ used in the analysis, within small numerical error. We use the Laguerre--Gaussian mode $L_3$ as the representative vortex-free Laguerre case, retain $L_4$ only as a quantitative benchmark for radial-order dependence, and compare both with a Bessel--Gaussian beam of input order $m=0$. The effective anisotropy produces a systematic redistribution of radial intensity, determines whether the central peak remains dominant or is overtaken by off-axis maxima as propagation advances, and controls the radial displacement of the dominant side lobes. For the finite-aperture Bessel--Gaussian beam, the same parameter quantifies how the approximately diffraction-resistant ring structure broadens for negative $λ$ and compresses for positive $λ$ during propagation.

Cross-lingual sequence alignment is fundamental for building and exploiting parallel corpora, spanning mappings from documents and sentences down to words and subwords. Existing tools, however, typically specialize in a single granularity, so practitioners often need separate systems for word- and sentence-level alignment---especially in multilingual and long-text settings. We present OmniAlign, a unified multilingual aligner that supports both word-level and sentence-level alignment with a single lightweight model. Built on an encoder-only backbone with strong long-context modeling, OmniAlign induces word alignments from contextualized token similarity matrices, and obtains document-level $m$--$n$ sentence alignments via sentence embeddings combined with dynamic programming. To balance fine-grained alignment accuracy and sentence-representation quality, we use a four-stage training pipeline: alignment-oriented continued pre-training, self-supervised learning, supervised fine-tuning on human annotations, and sentence-embedding distillation from a strong multilingual teacher. Experiments show that OmniAlign achieves highly competitive performance on both word- and sentence-alignment benchmarks and generalizes well to unseen language pairs. Surprisingly, later-stage supervised fine-tuning on short texts further improves alignment quality while retaining the long-context understanding acquired in earlier training, keeping the model robust on long-text word alignment. \normalsize {\color{blue}\textbf{Code}: https://github.com/MilkDargon/OmniAlign}\par {\color{blue}\textbf{Model}: https://huggingface.co/WPS-Qingqiu/OmniAlign}

Methane field monitoring requires the integration of sampling design, meteorological interpretation, sensor processing, plume analysis, visualization, and reporting, but these steps are often distributed across separate expert-driven workflows. We developed a locally deployable, tool-grounded large language model (LLM) multi-agent framework for our low-cost methane sensing and field-monitoring campaigns. The framework uses LLM agents as workflow coordinators that link field measurements, meteorological data, deterministic sensor-processing routines, Gaussian plume inversion, and report generation, rather than directly estimating methane concentrations or emissions. Extensive field deployments across diverse real-world environments (e.g., wastewater treatment facilities, landfills, and oil and gas sites) demonstrate that our framework can achieve 92.0\% accuracy in workflow routing and parameter extraction, 85.0\% success in emission-rate estimation and plume prediction, and 95.0\% success in generating editable reports under practical operating conditions. Compared with manual and general-purpose LLM-assisted workflows, it reduced workflow time from hours-level to minutes-level, lowered manual coordination and prompt-engineering requirements, and retained traceable plume-based outputs. In addition, most processing can be performed locally, reducing exposure of sensitive facility and field data to cloud services. These results indicate that tool-grounded LLM coordination can reduce the time, labor, usability, and data-security barriers of methane field monitoring.

Robotic assembly layout planning must determine the assembly site and the initial pose of each part while ensuring collision-free execution of a prescribed assembly sequence. This problem is challenging because the obstacle environment changes after each assembly step, and unassembled parts re maining in the workspace may block robot motions. We observe that the feasibility of each assembly step depends only on the initial poses of the current and later-assembled parts. Based on this dependency, we propose Backward Layout Search (BLS), which assigns initial part poses in reverse assembly order. Each expansion performs geometric, kinematic, grasp, and prescribed-motion checks, while collision masks and candidate set filtering remove infeasible initial part pose candidates. Promising partial layouts are retained through beam selection, and complete layouts are validated by full motion planning in forward assembly order. Experiments on five assembly models show that BLS produces collision-free executable layouts and reduces step evaluations and search time compared with a matched forward search.

End-to-end imitation learning avoids hand-made robot motion for approaching and grasping, but the policy must still decide which fruit to pick and where to close the gripper. Occlusion can make the policy lose the selected fruit during harvesting, and the correct closing point is difficult to infer from pixels alone. This paper presents HarvestPoint-ACT, which makes both decisions explicit in perception and provides them to the policy. An instance segmentation front end with a keypoint branch predicts a mask and a harvest point for each visible fruit, where the harvest point specifies the location to close the gripper. A scheduler ranks detected candidates by occlusion and travel distance and selects one target. After each attempt, it redetects and reranks the candidates because the canopy may have changed. The selected fruit is encoded for an action chunking transformer as an eight-dimensional state, containing the absolute harvest point, the vector from the gripper to that point, a validity flag, and a confidence score. When the selected fruit is temporarily undetected, the system retains the last harvest point estimate in the robot base frame and marks it as stale, and aborts the attempt if the loss persists. On a canopy mock-up, HarvestPoint-ACT achieves a success rate of 88%, and of 75% under heavy occlusion.

Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, and broader benchmarks should improve generalization. In robotics, however, a model can generalize while work still remains before it can run on a robot with a particular body. The work required differs across methods and target robots, and those differences affect practical deployment. We call the gap between reusable models, representations, or data and their use in execution on the target robot the embodiment gap. This survey examines what can be reused across robot embodiments and what must still be implemented on a new robot. We place existing methods on a two-axis map that shows the type of shared structure and the stage at which adaptation is needed for execution on the target robot. We then examine recent work through three overlapping research directions: sharing semantics and perception, sharing robot data and interfaces, and learning correspondence across embodiments. We also propose a reporting framework for adaptation work that success rate alone does not reveal. The framework identifies the work that should be checked when comparing cross-embodiment learning and highlights work that remains on a new robot and questions for future study.

Evaluating interaction quality in real-world HRI is an important challenge. If interaction quality can be estimated reliably, the results can be used to improve dialogue strategies and ultimately enable robots to adapt their behavior autonomously. However, existing automatic evaluation methods have been developed primarily in controlled laboratory settings, and it remains unclear whether they can be directly applied to real-world environments, where users are free to disengage and multi-party participation may arise naturally. In this study, we investigate the automatic estimation of third-party-rated rapport scores using 62 sessions of multimodal recordings collected in a Japanese drugstore. We compare zero-shot LLMs, pretrained text, audio, and visual models, and their prediction-level fusion. The results show that, in real-world HRI, zero-shot LLMs achieve strong performance, while audio and visual models tend to provide complementary information. In particular, Gemini 2.5 Flash performs strongly as a single model, and a fusion model combining Gemini (text) with HuBERT and V-JEPA performs best overall. Further analyses showed that estimation performance varied across interaction-duration and group-size conditions. These findings suggest that rapport estimation in real-world HRI requires evaluation and model design that account for contextual variability beyond that assumed in laboratory settings.

Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild. ER is inherently multimodal, requiring a joint understanding of facial expressions, vocalizations, language, biosignals, and gestures. However, real-world deployment remains challenging: modalities may be missing or noisy at test time. Partial observations can be viewed as a distribution shift relative to the complete-modality distribution. SOTA TTA methods based on entropy minimization or perplexity reduction do not transfer to autoregressive LVLMs, while retrieval augmented generation (RAG) degrades when the observed modality is weak. Because no ground-truth supervision exists to verify individual updates, adaptation across this stream risks accumulating drift and degrading once the model departs from a reliable solution. An effective solution must therefore adapt to arbitrary missing-modality patterns and remain effective during continual adaptation. We address both jointly with Test-Time Self-Distillation (TTSD), a parameter-efficient framework in which a frozen teacher, trained on complete modalities, guides an adaptive low-rank student via self-distillation, updating only a negligible number of parameters. Stability is built into this same loop through Fisher-Anchored Restoration (FAR), which monitors Fisher information stability to detect convergence versus drift and restores the student toward the teacher's anchor when distributional shifts are identified. Our experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation over long adaptation horizons, where baselines without restoration progressively degrade while TTSD-FAR remains consistent.

When every candidate is wrong, correct-candidate selection is unavailable, yet the aggregation call can still solve the problem afresh. A correct aggregate answer may therefore reflect recombination, fresh solving, or both. For efficient test-time reasoning, the relevant question is whether candidate context adds value beyond the additional generation pass. We introduce the missing candidate-free control under the same maximum output-token allowance and stratify by the number of correct candidates. Across AIME-2025 and HMMT-2025 with Qwen3-4B, candidate conditioning improves accuracy when multiple candidates are correct ($Δ_{\mathrm{cand}}$(c2+) = +0.290), lowers accuracy when every candidate is wrong ($Δ_{\mathrm{cand}}$(c0) = -0.123), and remains unresolved in the one-correct regime. The c2+ and c0 conclusions survive a conservative correction for the adaptive two-benchmark procedure. Under this counterfactual, the interpretation of all-wrong recovery reverses at this scale: conditioning on an all-wrong candidate pool lowers accuracy relative to a fresh solve. Original-format matching and placebo results characterize the failures descriptively but leave their mechanism unresolved. Within a separate structured intervention, explicit answer fields causally steer outputs toward their values; masking yields no measurable accuracy improvement, and equivalence with the original format was not established. The evidence is limited to one Qwen3-4B family, two mathematics benchmarks, first-answer-truncated candidate fragments, and single-pass prompted aggregation.

This work proposes a hierarchical Model Predictive Supervisory Control (MPSC) framework for multi-agent systems with shared resources. MPSC integrates receding-horizon cost-optimal control with Supervisory control theory (SCT) based supervision that enforces safety, nonblockingness, and resource exclusivity. Scalability arises from hierarchical and scalable supervisor and automaton templates, enabling distributed execution without monolithic synthesis. Using this framework, this work develops an urban Unmanned aircraft system Traffic Management (UTM) model. The model supports pickup-and-delivery missions under time-varying demand efficiently.

Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing excess-authority errors. Traditional permission gating systems alone for validating agent environments are insufficient. We study whether post-training can teach a 4B-parameter model to choose task-conditioned authority in executable terminal and Model Context Protocol (MCP) environments to complement those measures. We propose a framework where each action is audited before execution and again from observed effects along six dimensions of risk. This auditing is conducted using deterministic verifiers that score completion, evidence, exact state, prohibited attempts, and safe success. In conjunction with predefined task-specific sufficient-authority envelopes, we determine task-specific excess privilege values for trajectories, which are then optimized for in post-training. We find that after training using this framework on Qwen3.5-4B over 1,500 tasks, the selected seed reaches 98.48% safe success across 2,896 evaluation episodes spanning all 500 held-out tasks, compared with 64.36% for the base policy, and reduces excess-authority error events from 4.56% to 0.79%. Furthermore, external tests show capability retention and prompt-directed improvement. A 400 task continuation study also found evidence of generalization, reducing excess-authority events by 6.99 percentage points while maintaining previous capabilities. We conclude learned restraint through least-privilege aware post-training is therefore useful as an additional control layer for tool-using agents in executable terminal and MCP environments, but it does not replace permission gates and sandboxing.

Transient stability assessment determines whether a power system retains synchronism after a large disturbance. Machine-learning surrogates can accelerate it, but progress is limited by the lack of open datasets that combine dynamic ground truth, network graph structure, and machine parameters. We release a benchmark of 20,000 three-phase-to-ground fault scenarios on the IEEE 9-bus system. Each scenario couples an AC power-flow operating point with a detailed electromagnetic-transient simulation of the post-fault response. Every record provides the network as an attributed graph (nine buses, eighteen directed branches, ten node and twelve edge features), the full rotor-angle and speed trajectories of the three generators, the static machine constants, the fault description, and a center-of-inertia binary stability label. Wide load and generation scalings across eighteen fault locations yield a near-balanced distribution (48.96\% stable, 51.04\% unstable). Generation is deterministic and fully reproducible through fixed seeds and public code. The dataset is distributed on IEEE DataPort under a persistent DOI and supports stability classification, trajectory prediction, margin and critical-clearing-time estimation, and the comparison of topology-aware, physics-based, and hybrid learning methods.

Affordance prediction is the identification of potential actions an agent can perform on a target object from multimodal inputs. Affordance prediction methods are difficult to evaluate and compare due to heterogeneous problem formulations, inconsistent dataset annotations, incomplete reporting of experimental protocols, and limited information about deployment conditions. These limitations challenge fair benchmarking and performance comparison. To promote transparency, we propose the Affordance Sheet, a documentation detailing task formulation with its input modalities, model architectures and training information, datasets, and experimental protocols. Affordance Sheets enable reproducible benchmarking and reliable evaluation of affordance models for real-world scenarios, including generalisation to novel conditions and human safety.

Autonomous scientific agents now increasingly propose ideas, write code, run experiments, analyze results, and even draft papers. Observe and audit those agents are necessary but logging every model call is not enough, scientists also need to inspect the artifacts and claims that the systems produced and their relations. This is driven by the fact that failures in scientific agent systems are often distributed across several objects. A manuscript claim may cite the wrong evidence, a search process may select a degenerate candidate, a laboratory novelty claim may depend on an unstated rule, or a multi-agent plan may change without a visible trigger. Existing tracing, experiment tracking, and archival provenance tools are valuable, but their native objects do not make these scientific audit relations first-class. We argue that autonomous scientific systems should emit portable, claim-aware artifact lineage as a minimum audit layer. We propose a compact observability profile organized around individuals, operators, fitness records, lineage, archives, runs, streams, and steering commands. In this profile, scientific claims are ordinary individuals with explicit evidence bindings and verification records. The profile is intended as a semantic layer that complements current telemetry and provenance standards. Execution details can remain in OpenTelemetry. Final packages can export to PROV-O or RO-Crate standards.

Current evaluation of computer-use agents is split between long-horizon workflow benchmarks and atomic GUI-grounding tests. This leaves an under-instrumented middle layer: realistic component-centered interactions (e.g., toggle a button set) that are short enough to diagnose and rich enough to capture the burdens of modern interfaces. We present ComponentBench, a benchmark and diagnostic pipeline for component-level evaluation of computer-use agents on modern web UIs. ComponentBench is organized around a library-agnostic ontology of 97 canonical UI components instantiated as 2,910 programmatically verified tasks across widely used component libraries, paired with cleaned human reference trajectories that enable evaluation of both task success and interaction efficiency. Beyond task collection, we introduce a scalable pipeline for auditing realized structural difficulty after implementation and synthesizing structured failure analyses across tasks and component families. Evaluating seven models -- GPT-5.4, Gemini 3 Flash, GPT-5.4 mini, GPT-5 mini, Gemini 3.1 Flash-Lite, Qwen3-VL-235B, and UI-TARS-1.5-7B -- across four observation and action spaces, we show that these design choices critically impact performance. Within a single shared harness, changing only the observation and action space shifts task success by more than 30% for the same model: GPT-5 mini falls from 83.1% with accessibility-tree observations to 48.9% with coordinate-only Pixel control. Moreover, even the fastest configuration takes 3.7x as long as the matched human reference, and spatial manipulations that are trivial for humans continue to challenge current agents.

Although thin-film lithium niobate (TFLN) facilitates efficient signal generation and nonlinear and quantum interactions, the realization of optical parametric amplification (OPA) that can provide simultaneous ultra-broadband and high-gain operation in an integrated chip continues to pose a challenge. Here we demonstrate continuous-wave-pumped OPA in an X-cut MgO-doped, dispersion-engineered, and adaptively-poled TFLN waveguide of 1.6 cm length, achieving a flat-top profile covering a 450 nm-wide optical wavelength window, corresponding to a 3-dB gain bandwidth of about 56 THz. Among reported TFLN platforms, our device exhibits the broadest 3-dB gain bandwidth. The same device can be pumped either directly at visible wavelengths through second-order x(2) interactions or in the telecom band through cascaded x(2) processes, the latter eliminating the need for a high-power visible pump laser. We achieve maximum gains of 8.87 +- 0.39 dB and 10.79 +- 0.43 dB at on-chip pump powers of 74 mW and 170 mW for the direct and cascaded schemes, respectively. We further directly probe OPA gain across the 1650-1900 nm wavelength range, where experimental gain measurements have remained scarce. With a normalized on-chip gain of 1.21 dB per W per mm, our device sets a new benchmark among reported cascaded x(2) nonlinear processes. This work advances the realization of integrated optical parametric amplifiers, offering high efficiency, robust gain, ultra-broadband bandwidth, and continuous-wave operation, thereby enabling new capabilities for next-generation quantum sensing and photonic systems.

Background. Advances in agentic systems are simultaneously, and rapidly, saturating benchmarks. Despite this often discussed phenomena, benchmark scores remain difficult to interpret due to the lack of control and characterization of task difficulty. More specifically, we currently have little understanding of what makes one task harder than another, and to what extent task difficulty is predictable from static task properties. Aims. We propose a measurement framework to investigate and systematically quantify what structural properties of software tasks correspond to agent success rates for issue resolution tasks. Method. We conducted a large scale empirical study on CoderForge-Preview, the largest open dataset of coding agent trajectories to date, by extracting features across task patch, repository and prompt. We evaluated the predictive power of each feature against task outcomes using ensemble methods, SHAP attribution, and effect size analysis. Results We found that task difficulty is substantially predictable from static features (AU C = 0.863) and is largely driven by patch fragmentation and repository scale. Prompt linguistic features become visible among top contributors for tasks in the mid-band, revealing a layered structure of difficulty. Conclusion. The difficulty of an issue resolution task is encoded in its structure. This enables static, pre-hoc difficulty estimation and lays the groundwork for difficulty-controlled benchmark construction for evaluation of agents.

Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulations and complex high-dimensional design spaces. Although deep learning has accelerated the design process by serving as a surrogate model, it remains constrained by task-specific architectures and lacks universal reasoning capabilities. This review surveys how Large Language Models (LLMs) are adding semantic interfaces, code generation, and tool orchestration to established numerical nanophotonic workflows. We first outline the development from classical neural networks to transformer-based models and their applications in nanophotonic design. We then review the emergence of LLM-related methods in nanophotonics and organize them into two operational modes: surrogate models that treat structure-spectrum mapping as a language task, and agentic systems that have been demonstrated to generate code, orchestrate selected simulation steps, and support closed-loop optimization. Furthermore, to identify future cross-disciplinary opportunities, we briefly explore applications of LLMs in research fields such as materials science and wireless communications. This review concludes by looking ahead to the next generation of multimodal foundation models with physical perception capabilities. In this vision, artificial intelligence is evolving from passive tools into active collaborators, participating in autonomous scientific discovery.

Trajectory planning for autonomous driving requires both high-level reasoning and precise low-level control. Large Language Models (LLMs) offer semantic-rich planning capabilities, however, their application is limited by hallucinated reasoning, poor grounding in environment dynamics, and limited numerical precision in control. We propose GAPL (Grounded Action-effect Policy Learning), a unified framework that integrates LLM-based effect estimation, simulation-based effect grounding, and policy optimization into a closed-loop system. GAPL consists of three modules: (1) an LLM-based Effect Evaluator for structured multi-dimensional action-effect estimation; (2) a Simulation-based Effect Grounder that predicts dynamics-consistent effects from simulator rollouts; and (3) an Effect-Aware Decision Maker that grounds LLM effect estimates against simulation via a distiller to guide Proximal Policy Optimization (PPO)-based policy learning. Experiments on four Highway-env scenarios demonstrate that GAPL consistently outperforms baselines, achieving average reductions of {0.76, 0.86, 2.00} in collision rate, average displacement error (ADE), and final displacement error (FDE), and an average reward gain of 1.44.

Despite the rapid industrialization of the touch sensor manufacturing process, most of these sensors are still handmade in research laboratories. This complicates standardizing their performance, requiring the repetition of data collection and training models for each unit produced. To address this problem, this paper presents a method that can generalize the estimation of 3D force maps across different GelSight Mini sensor units, regardless of the sensor version. Specifically, the method consists of two stages: a domain adaptation stage, in which the input tactile image is reconstructed as a general tactile image using a UniT-based model; and a stage for estimating 3D force maps employing a U-Net network. Our proposal achieves promising results in both steps, such as an SSIM of 0.9338 +- 0.0358 in the image reconstruction phase and an MAE_F of 1.1294 +- 1.5934(N) in the force estimation phase.

Whole-body motion tracking policies turn a humanoid into a robust control interface: the teleoperator---or an upstream model---only supplies a coarse movement intent, while the low-level policy keeps the robot balanced and physically feasible. Existing trackers deliver this interface only on flat ground: trained in empty scenes, they never learn how contact with terrain and objects reshapes their dynamics, and they attempt to teach the policy to balance under any command by continually enlarging the reference-motion corpus, which stops working once feasible behaviors become environment-dependent. We present GigaBrain-WBC-0.5, the first Behavior World Model (BWM) for humanoid whole-body control. Rather than a purely reactive tracker, we train a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command, so the network that acts also models how the environment shapes what it can do next. An automatic terrain-annotation pipeline recovers full 3D contact geometry from retargeted motion, enabling terrain annotation at the scale of existing motion datasets. The predicted distribution is reused at deployment to detect implausible commands online and retract them onto learned behaviors, so the robot attempts tasks in a "best-effort" manner. The result is a unified policy that takes real-time command, interacts with environment, and stays robust to implausible commands, falls, and disturbances. GigaBrain-WBC-0.5 achieves the highest success rate across all four regimes among three large-scale tracker baselines: 81.3% on terrain interaction (4.3x the strongest baseline), 83.1% under implausible commands, and 99.3% fall recovery (16.8x the strongest baseline). Hardware trials show robust interaction under missing supports and disturbances; the Unitree G1 checkpoint transfers to the Maker L01 robot with simple fine-tuning.

We extend the standard Principal-Agent framework to scenarios where the Agent selects from a suite of technologies, each characterized by a distinct cost-capability profile. This framework is increasingly critical in the era of Large Language Models (LLMs), where Agents choose both a model and an associated effort level (e.g., token budget). We model the relationship between output quality and effort as a concave, saturating function, which depends on the Agent's hidden two-dimensional action choice balancing technology selection and effort allocation. We derive the optimal linear contract for the Principal, demonstrating that the Agent's best response is characterized by a threshold reward share that triggers technology switching. Finally, we calibrate our model using open-weight LLM pairings across the MATH and MMLUPro benchmarks. We show that both Principal and Agent, when employing bandit algorithms to navigate this environment, converge to strategies that closely align with our theoretical equilibrium. These results suggest that simple linear contracts can effectively incentivize complex, technology-aware delegation in agentic workflows.

Push-T is an iconic benchmark for learning manipulation policies from human demonstrations. The robot must use a single point of contact to push a T-shaped block into a target pose. In this short paper, we revisit the Push-T task in the context of emerging advances in Agentic Robotics where an LLM coding agent -- Claude Code with Fable 5 -- is prompted to create an algorithmic solution that does not require any demonstration data. We study how effective the agentic coding loop can solve the Push-T task, and compare the resulting code as policy with the visuomotor imitation learning policy. Results suggest that the agent found the 2D gym simulation online, and used sim experiments to learn push mechanics, iteratively optimizing to achieve 100% success rate using 46% fewer steps than the best diffusion policy trained with 200 human demonstrations. The coding agent also solve extensions from T to the full alphabet (Push-A to Push-Z) using a self generated curriculum and generated simulation code for the Franka and UR5 robot arms in 3D cross-embodiment simulations with visual feedback. Videos, policies and details will be posted online.

We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel motion. This shared visual interface enables generalist world modeling and control by learning action consequences across embodiments, tasks, environments, and video-generation backbones. Our best configuration achieves 90.4% lower robot-motion error and 60.2% lower object-motion error than our action-conditioned baseline, while supporting zero-shot composition and data-efficient adaptation. On the RoboLab benchmark, Hydra-0 achieves a Pearson correlation of r=0.96 between replayed and reference success rates. Finally, we uncover an emergent inverse mode of this interface: a world action model that predicts compatible robot motion from desired object flow transferred from a human demonstration. A trained action head maps the resulting latent features to executable actions without requiring task-specific expert robot demonstrations. Together, these results demonstrate the potential of action flow as a shared control interface connecting heterogeneous training data, open-loop policy evaluation, and robot control.

Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective study included 638 radiology reports from CT examinations of the chest, abdomen, and pelvis dictated by 15 board-certified radiologists in 2023 and 2024. A multi-agent AI pipeline was developed to perform report structuring and quality assurance (QA). The system structured the report into standardized anatomical sections at the sentence level using regex rules and local large language models. It also detected mismatches between the Findings and Impression sections, or within sections; gender-anatomy conflicts; and undocumented communication of critical findings. Two board-certified radiologists independently evaluated a 45-report subset. Results: The multi-agent system structured the Findings sections of all reports (22,270 sentences) into a predefined anatomical format while retaining the original report content. The system flagged 90 (14.1%) reports, most commonly for section mismatches (80 reports, 12.5%). In the radiologist evaluation, both reviewers agreed that 31 (69%) were correctly restructured, 2 reports (4%) were incorrectly restructured, and disagreed on the remaining 12 reports (27%). Both reviewers agreed that no clinically important information was omitted and no fabricated content was introduced. Overall QA performance was rated as "excellent" or "good" in 84% of the evaluated reports, with the remaining reports rated as "fair". Conclusion: A locally deployed multi-agent AI system combined radiology report structuring and quality assurance within a single workflow. The system demonstrated favorable performance in radiologist evaluation. Such systems may support standardization of reporting and quality assurance in radiology practice.

Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods have been critically overlooked. In this work, we conduct a comprehensive re-evaluation of two memory-based methods, broadening the scope of evaluation along two axes: (1) including multiple runs to quantify variance, and (2) randomly shuffling the tasks to investigate the effect of task order. Through these experiments, we make two observations that expose the fragility of current methods: First, agent evaluation is inherently noisy in complex environments and on multi-step tasks, and stacking a self-improving loop on top can further amplify this noise. Second, the agent's improvement is highly dependent on task order. Prior works often adopt default orderings that impose an implicit curriculum, acting as a hidden prerequisite for success. To better understand this fragility, we manually examine the agents' memory and hypothesize that task and environment underspecification contribute to this fragility. We validate this hypothesis by incorporating information that enables better specification, such as detailed rubrics and environment feedback, into the memory construction process. While this added information partially closes the performance degradation in previous experiments, significant gaps still remain, suggesting that other uncharacterized factors contribute to this fragility. Looking ahead, our work advocates for more rigorous evaluation protocols for self-improving agents by reporting results across multiple runs and stress-testing them under challenging conditions. Moreover, our findings on underspecification call for systems and interfaces that enable effective human oversight, preventing agents from failing in unforeseeable ways.

High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memory requirements. A prevalent workaround employs a two-stage pipeline: editing at low resolution followed by independent super-resolution. However, this approach suffers from two critical issues: information divergence, where hallucinated details contradict the original high-resolution (HR) source, and texture degradation, manifesting as over-smoothed or over-sharpened artifacts. We propose EditBridge, a diffusion bridge framework for efficient ultra high-resolution editing. Unlike conventional diffusion that regenerates from noise, we formulate refinement as structured data-to-data translation from the low-resolution (LR) edited result to its HR counterpart, explicitly conditioned on the original HR source to preserve authentic details. To efficiently incorporate HR source guidance, we introduce a prior-guided block-wise sparse attention mechanism that exploits semantic correspondence from first-stage editing to constrain cross-image interactions to spatially aligned regions, significantly reducing computational overhead. Extensive experiments demonstrate that EditBridge achieves high-fidelity editing with superior perceptual quality at resolutions up to 4K, delivering 3.6--8.4$\times$ speedup at 2K and enabling practical 4K editing in 61 seconds.

Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be partly attributed to a limited understanding of which tokenizer properties affect which aspects of downstream performance. We introduce TokEval, a framework of tokenizer evaluation metrics that goes beyond standard measures like fertility and compression rate to capture linguistically and structurally meaningful properties, e.g., UTF-8 character boundary integrity and digit place-value boundary alignment for mathematics. To validate whether these metrics are predictive of downstream model performance, we conduct controlled language model pretraining experiments, varying solely the tokenizers' training data mixture, pretokenization strategy, and training algorithm. We evaluate the resulting models on bits-per-byte (a tokenizer-agnostic version of perplexity) and several benchmarks, spanning linguistic understanding, mathematical reasoning, and code generation. Our experiments suggest that different intrinsic properties have different impacts on model abilities: information-theoretic metrics predict language modeling abilities (Spearman rho up to 0.80), while structure-sensitive metrics, such as those measuring digit and line-break handling, correlate with task accuracy. We hope TokEval enables more principled tokenizer evaluation, replacing pretraining sweeps with intrinsic measurement wherever the two agree.

Resistive random-access memory (ReRAM) is a promising future nonvolatile memory technology. Most ReRAM exhibit a fundamental tradeoff: filament-type ReRAM provides long data retention but suffers from poor uniformity and high switching current, whereas nonfilamentary ReRAM shows lower-current, area-dependent switching but generally poor retention. No two-terminal device has been able to overcome this tradeoff. In this work, we present a two-terminal Ta2O5/ TaOX resistive memory cell that achieves both nonfilamentary switching and long retention. Electrical measurements and composition depth profile show that the switching is not confined to a single filament but is instead uniform across the entire switching region. Despite the nonfilamentary switching, this device can retain information for over 22 hours at 190 °C, which is comparable to the best filamentary devices. We propose that this long retention arises from composition phase separation in amorphous tantalum oxide. Our work shows that the fundamental tradeoff between information retention and switching uniformity can be overcome, and thereby provides a pathway toward more uniform and reliable oxide memory devices.

Traffic elements such as traffic lights and road signs play a fundamental role in human driving decisions and should naturally influence end-to-end driving performance. However, existing end-to-end driving research predominantly focuses on dynamic road participants (e.g., vehicles and pedestrians), while the role of traffic elements remains largely unexplored. The community still lacks a systematic study quantifying their impact, largely because public datasets rarely provide structured traffic-element annotations and modern driving systems vary widely in architecture and training paradigm. In this work, we present the first systematic investigation of traffic element awareness for end-to-end autonomous driving. We construct a unified research infrastructure by augmenting multiple public driving datasets with comprehensive traffic-element annotations. To support diverse model families, we adopt a minimal and universal integration design that incorporates traffic-element signals into existing pipelines in a plug-and-play manner with negligible architectural modification. We evaluate this design across modern paradigms, including perception-prediction-planning pipelines, vision-language-action models (VLA), regression-based planners, diffusion-based policies, and trajectory-scoring frameworks, on nuScenes, NAVSIM-v1, NAVSIM-v2, and Bench2Drive. Across all paradigms and datasets, this simple integration consistently improves driving performance, demonstrating that traffic element awareness provides a robust and generalizable signal for end-to-end driving systems. Notably, on the challenging NAVSIM-v2 benchmark, our approach significantly improves state-of-the-art architectures and data pipelines, establishing a new state of the art.

Academic surveys play a central role in organizing rapidly expanding scholarly literature, yet their construction requires extensive paper analysis, coherent knowledge organization, fine-grained citation support, and reliable manuscript assembly. Existing Deep Research and automated survey generation systems address parts of this process, but typically do not coordinate paper understanding, literature organization, evidence-grounded drafting, and manuscript validation through a shared, revisable state. We introduce DAS, a stateful agentic framework for generating publication-oriented academic surveys. Its key idea is to separate reusable paper analysis from topic-specific manuscript construction. DAS builds on DAS-2M, a dynamically updated metadata lake containing survey-oriented representations of approximately two million papers. Its agents maintain explicit literature, organization, writing, and finalization states through candidate-grounded taxonomy planning, reverse paper-to-section routing, and hierarchical claim and citation planning. Semantic review reactivates only the affected writing states for repair and reevaluation, forming a scoped closed loop with deterministic validation. We further introduce DAS-Bench, a 30-topic benchmark, together with DAS-Eval, which assesses scholarly citation quality, taxonomic synthesis, hierarchical discourse, and manuscript assembly reliability through 16 criteria. Among systems evaluated on all 30 topics, DAS achieves the highest average in all four dimensions, with an overall score of 4.34 compared with 4.03 for the strongest competitor, and the same ordering is preserved on the matched 21-topic CS subset. Blinded expert evaluation further prefers DAS to Naive RAG on 27 of 30 topics and to AutoSurvey on 19 of 21 shared CS topics. The project page is available at https://zhikaixu24.github.io/projects/DAS/.

Initialization-free bundle adjustment (InitFree BA) aims to recover camera poses and scene structure directly from image observations, avoiding the geometric initialization stages of conventional structure-from-motion pipelines. Recent methods based on Object-Space Error (OSE) formulations and Variable Projection (VarPro) show encouraging optimization behavior from random camera configurations. However, existing evaluations primarily measure optimization success, leaving unclear whether a low OSE objective yields a valid metric 3D reconstruction. We revisit InitFree BA experimentally through a unified evaluation framework combining a C++ implementation of existing OSE formulations with a Blender-based dataset generator providing exact ground truth and controlled camera configurations and observation densities. Our experiments reveal a previously overlooked optimization--reconstruction gap: projective solutions with similarly low OSE values can lead to substantially different Euclidean reconstructions after metric upgrade. We identify initialization priors, landmark observation density, and metric-upgrade stability as key factors governing reconstruction success. Overall, our results suggest that the main challenge of InitFree BA is not merely minimizing OSE objectives, but obtaining projective reconstructions that admit reliable metric upgrade. We believe that the proposed benchmark, implementation, and analysis establish stronger experimental foundations for future research on initialization-free bundle adjustment, a problem largely unexplored within the computer vision community. Project page is available at https://github.com/simonwebertum/InitFreeBA.git.

Reasoning in LLMs is overwhelmingly studied in domains that provide a model with rules: mathematics and code. Linguistic puzzles invert this: the solver must first discover the system before reasoning within it. We present the IOL-AI Challenge, an open-science competition run on the unseen problems of the International Linguistics Olympiad (IOL) 2026 Individual Contest, evaluated both automatically and, for the first time, by members of the official IOL Jury under the same rubrics applied to human contestants. The challenge drew 731 submissions from 46 teams under a strict compute budget (one T4, 30 mins). We additionally benchmark 15 unconstrained frontier and open models, with Claude Opus 4.8 earning a jury score equivalent to a gold medal, while both resource-constrained systems we submitted for jury grading scored in the range of the bottom 5% of contestants. Capability was not determined by scale: 14B submissions outperform models twice their size, and gains come from decoding and output-handling rather than model capacity. We also found that automatic metrics rank systems exactly as the jury does, but compress the scale, upscoring weak systems by ~13 points and understating strong ones. Our analysis shows that while frontier models might have prior knowledge about some of the problem languages, it does not significantly help them solve the linguistic reasoning tasks, leaving linguistic reasoning as a strong benchmarking proxy for generalizable reasoning skills.

Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual search among thousands of video frames for each individual user query. In this work, we propose a memory tree guided key frame selection paradigm for efficient 3D question answering in embodied scenarios. Our method leverages a compact and reusable 3D scene representation, termed MemTree3D, which supports real-time online construction leveraging camera 6-DoF poses. MemTree3D captures multi-level 3D scene information, enabling a Large Language Model to efficiently query and retrieve question-relevant key frames through our scoring-based frame selection without reprocessing the entire video stream. On OpenEQA, our method improves the LLM-Match of GPT-4o by 17.4%, LLaVA-OneVision-7B by 5.8%, outperforms existing visual search methods. Our code is available at https://github.com/hsiangwei0903/MemTree3D

Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing helpfulness or alignment, where no single reference answer exists. However, objective tasks introduce a distinct reliability challenge for reference-free LLM judging. In the absence of a reference answer, the judge evaluates factual correctness either through its parametric knowledge or through tool augmentation. Although the former enables efficient evaluation, the judge may hallucinate or lack sufficient evidence for its verdict. Conversely, tool augmentation can provide additional evidence but introduces extra computational cost and requires an appropriate mechanism to determine when and how that evidence should be used reliably. More importantly, neither approach alone provides formal control over the risk of accepted verdicts or guarantees their reliability at a specified level. We propose a risk-controlled framework that calibrates uncertainty thresholds on a held-out set so that the false discovery rate among accepted verdicts remains below a user-specified level~$α$ with high probability, using finite-sample Clopper--Pearson intervals. When the parametric mode is not sufficiently confident, the instance is routed to a retrieval-augmented mode, where the judge gathers web evidence and re-evaluates the instance under a second calibrated threshold. The finite-sample guarantee carries over to this two-threshold routing without additional assumptions. Across open-domain QA benchmarks and judges of varying scales, the framework maintains the target error rate while achieving substantially higher coverage than single-mode baselines.

Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to distinguish it from that of other writers. In practice, however, this assumption is challenged by distribution shifts caused by changes in genre, time, and AI-assisted writing. Existing AV benchmarks typically study these factors in isolation and focus predominantly on English, limiting our understanding of model robustness under realistic conditions. We introduce AVShift, the first German benchmark for systematically evaluating AV under multiple distribution shifts. AVShift comprises over 150,000 text pairs spanning three genres and 21 years, enabling controlled evaluation of cross-genre, temporal, and AI-era shifts within a unified framework. We benchmark representative feature-based, embedding-based, and LLM-based approaches. Our experiments show that fine-tuned LLMs generalize best across genres and benefit substantially from stylistically diverse training data. We further demonstrate that temporal drift is one of the strongest factors affecting AV, with performance degrading significantly as the time gap between documents increases. In contrast, we find no evidence of a measurable AI-era distribution shift within AVShift. Finally, our feature analysis reveals stylistic features that remain stable across genres, while their relative importance varies depending on the specific genre transition. We release AVShift and our code for future research.

Recent progress in robotic learning has been fueled by large-scale datasets collected in everyday environments. However, most existing datasets emphasize short-horizon, low-contact tasks such as pick-and-place, and therefore do not capture the precision control, force/torque or tactile regulation, and multimodal feedback required for industrial assembly. To address this gap, we introduce PRISM, a large-scale multimodal dataset for contact-rich industrial operations. The dataset spans more than 25 manipulation tasks (e.g., electronic components plug/unplug, conveyor-based sorting) and covers diverse mechanical constraints. PRISM includes more than 5,000 trajectories totaling 45 hours of teleoperated demonstrations, recorded using synchronized multi-view RGB-D, force/torque, tactile, and robot-state measurements. In contrast to datasets collected in household or laboratory settings, PRISM provides a realistic benchmark for multimodal perception and control under high-precision industrial constraints, and serves as a foundation for contact-rich, generalizable manipulation in real-world manufacturing environments. The dataset is open-sourced at: https://tengbo-yu.github.io/PRISM/

In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled transitions. We ask what that acceptance certifies in continuous control. We define the pipeline's danger as an expected risk and isolate its exact factor: the probability that N i.i.d. gate rollouts all miss a critical event of probability r is exactly (1-r)^N; an independent acceptance sample adds its budget to the exponent. On three hybrid instruments the accepted mode-blind model is exploited: the planner is pinned at the mode boundary at a regret of nearly the whole attainable return. We prove a localization budget, valid at boundary points: models with Lipschitz constant at most L differing by eta at a point disagree above tolerance eps on a region of volume at least kappa((eta-eps)/L)^(d+m); the discontinuous reset modes studied pay no such budget. With real LLM synthesis, GPT-5.x repairs an omitted 1D clamp in 105 of 111 mode-containing draws -- every attempt exact on 50 of 56 instrument-stream blocks (95% CI [0.781, 0.960]). On 2D regions no artifact recovers the rule (0/156); eight targeted interventions leave the failure in place, and positive controls locate it: a located rule is not induced, while given form and location the constants follow exactly. A version-space certificate proves identification is class-relative: at the widest dose the declared fit succeeds in 20/20 blocks and every sample-consistent circle is within tolerance in 18/20. We prove a class of entry rules exactly consistent with every sample yet harmless at play, so identifiability is a measurable property of the instrument. Re-scoring all 1034 artifacts on independent samples confirms acceptance certifies sample consistency and no more: where the gate is provably informative it covers about two percent of the exploited planner's queries.

Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these distant cognitive leaps remain poorly understood. Traditional attention-based interpretability often fails to capture true semantic proximity due to routing artifacts like attention sinks. In this paper, we bypass attention weights to directly analyze the dynamic geometry of the hidden state manifold, proving that deep LLM latent spaces natively organize into Small-World networks. By sparsifying the continuous similarity matrices of long-context representations into unweighted graphs, we trace the connectivity between highly disjoint semantic anchors across two distinct architectures. Our findings reveal a sharp topological phase transition: while early syntactic layers remain entirely fractured, deep reasoning layers abruptly compress massive conceptual distances into highly navigable pathways strictly bounded by the "Six Degrees of Separation" limit (=< 6 semantic hops). Furthermore, we demonstrate the practical efficacy of this framework by applying it to zero-shot hallucination detection within Retrieval-Augmented Generation (RAG) using the RAGognize dataset. We show that factually grounded generations maintain structural integrity with their source context (approximately 3 hops), whereas hallucinations induce severe topological collapse. Ultimately, this work mathematically formalizes how transformers execute abstract reasoning and provides a novel, strictly geometric signature for evaluating factual reliability.

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but relies on costly rollout exploration. Assigning the same exploration budget to samples with different difficulty levels is inefficient: easy samples may receive redundant rollouts, whereas difficult but learnable samples may receive too little exploration. Existing adaptive schedulers address this mismatch through curriculum-based sample selection or non-uniform rollout allocation based on estimated sample difficulty. However, obtaining reliable online difficulty estimates remains challenging: dedicated probing adds substantial generation overhead, whereas history-based estimators face a cold start with no initial observations and stale feedback, and typically ignore relations among samples. To address these limitations, we propose a plug-and-play graph-based online difficulty estimator that shares rollout feedback across related samples and continuously updates their difficulty estimates, mitigating cold start and staleness without dedicated probing. Specifically, we first construct a difficulty-aware sample graph based on semantic and reasoning similarities. Based on this graph, we introduce latent difficulty states and use a Potts prior to encourage neighboring samples to share the same state. We then employ a state-level Beta-Binomial model to aggregate the rollout outcomes associated with each state. Finally, we use an online mean-field variational algorithm to continuously update the latent-state assignments and state-level difficulty as new feedback arrives. Our framework can be integrated into sample-selection and rollout-allocation schedulers, enabling difficulty-adaptive exploration without dedicated probing. Experiments across multiple base models, RL schedulers, and benchmarks demonstrate that our framework achieves better performance.

Groups routinely complete projects that no single member can plan, execute, or verify alone. We propose a formal model of this phenomenon, Collective Counterfactual Planning (CCP), in which the binding limitation on each agent is neither capability, knowledge, nor observability, but representational geometry: each agent perceives the state, conceives moves, consents to actions, and certifies goal requirements only through a projection onto an agent-specific subspace of a common task space. Four gates jointly determine whether a team can reach a conjunctive goal and legitimately recognize that it has done so: the exogenous implementation coalitions required to perform each action, together with three representational gates -- conception, consent, and task-relative verification qualification. We define the Collective Counterfactual Solvability (CCS) problem, separating geometric feasibility, executable attainment, and validated completion. The results expose a positive-negative duality. Iterated cross-agent relay can unlock a solution that no one-shot pooling of individual plans contains, but any goal requirement depending essentially on the subspace dark to the entire team is unverifiable and therefore not validly completable, even when the trajectory accidentally attains it. Memoryless and audited consent further constrain different objects -- action directions versus cumulative trajectory states -- and neither dominates the other. A four-step exhaustive horizon-bounded solvability scheme is sound and complete under exact representation of the relay closure; restricted implementations remain sound on returned plans but need not be complete. The model gives one geometry for sequential mutual enabling, competent execution of steps whose purpose is invisible to the executor, forced sub-teaming at expertise boundaries, and completion that cannot be validly declared.

Recent advances in AI have revolutionized speech processing, yet effective speech understanding requires discerning not just what is said, but how it is said. Speech Sentiment Analysis plays a critical role in decoding these paralinguistic cues for diverse real-world applications such as recruitment and customer service. However, existing Speech Sentiment Analysis research faces two primary limitations. First, dominant approaches rely on text-centric pipelines that cascade Automatic Speech Recognition with text analysis. This process inevitably discards essential acoustic features like prosody and tone, failing to capture attitudinal meanings in acoustically ambiguous utterances. Second, current benchmarks suffer from a mismatch in label granularity, prioritizing basic emotions (e.g., happy, sad) over the nuanced interpersonal stances (e.g., confident, impatient) necessary for social sensitivity. To address these limitations, we propose a novel dataset, SpeechSense, for fine-grained speech sentiment analysis. Specifically, we define a specialized 8-class taxonomy of interpersonal stances detectable primarily through prosodic cues beyond lexical content alone. We then construct a curated dataset based on this taxonomy, built from high-fidelity speech synthesis and rigorous human validation. Comprehensive experiments across multi-modal LLMs, text-only LLMs, and speech encoders demonstrate that models with acoustic access consistently outperform text-only baselines. These results empirically validate the primacy of acoustic cues in detecting subtle speaker attitudes, highlighting the necessity of SpeechSense. Dataset and supplementary materials are available at https://github.com/Sher13cked/SpeechSense.

In the Lifelong Multi-Agent Path Finding (L-MAPF) problem, agents must repeatedly move from one destination to another while avoiding obstacles and inter-agent collisions. Widely regarded as one of the highest-performing solutions to this problem is the Rolling-Horizon Collision Resolution (RHCR) framework. However, commensurate with its quality solutions, it incurs a computational cost that limits its applicability to even modest agent counts. In this paper, leveraging theoretical methods from the Locally Interdependent Multi-Agent MDP literature, we first theoretically prove the near-optimality of RHCR in a discounted MDP formulation of the L-MAPF problem. Then, we leverage these results to naturally motivate an extended framework called Group Decentralized RHCR (GD-RHCR) which incorporates a group decentralized structure that partitions agents based on a transitive communication scheme and plans for each partition of agents in parallel. We show that both RHCR and GD-RHCR achieve similar exponentially close to optimal guarantees, establishing a theoretical duality between the time based restrictions performed by vanilla RHCR and the additional space based partitioning performed by GD-RHCR. Lastly, we show that across varying maps, GD-RHCR is able to attain high throughput that scales into higher agent counts while maintaining a significantly lower per plan cost.

As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a bounded memory interface. We study this evidence-reachability problem in long-term conversational memory, where retrieval still relies heavily on semantic similarity. This works well for topical recall, but it often misses earlier experiences, plans, or motivations that are semantically distant from the later events they help explain. Existing memory graphs provide cross-memory structure, yet links driven mainly by semantic overlap can duplicate what the host retriever already recovers. We argue that link construction should instead prioritize a sparse set of retriever-complementary associations. We present CABLE (Complementary Antecedent-Based Linking and Expansion), a plug-in augmentation that constructs links designed to extend the host retriever's direct semantic reach. For each new memory, CABLE generates antecedent-oriented queries, retrieves prior memories, subtracts candidates in the direct semantic neighborhood, and verifies the remainder before adding the accepted complementary associations into a sparse directed graph. At retrieval time, CABLE expands the host system's retrieved seeds along these links to surface implicit supporting evidence. We evaluate CABLE with A-MEM on LoCoMo and MA-LongMemEval, and further integrate it into SimpleMem and Mem0g on LoCoMo, using Qwen3.5-27B, DeepSeek-chat, and GPT-4o-mini. CABLE yields higher mean LLM-judge scores in every evaluated system-level setting, with the largest gains in categories where useful evidence is distributed across memories or sessions, including open-domain, multi-session, and preference-oriented questions. These results support prioritizing sparse, reasoning-relevant associations that complement rather than duplicate the host retriever.

Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. In Idea Generation, AutoResearch continuously integrates emerging research signals with accumulated domain knowledge, identifies transferable mechanistic insights, and uses multi-model generation and cross-review to produce grounded, testable research plans. In Idea Execution, coordinated agents decompose these plans into experiments, iteratively implement and diagnose them, and employ independent evidence-based review before accepting research conclusions. Across representative settings in cross-modal retrieval, systems optimization, and benchmark-driven machine learning, AutoResearch turns generated ideas into measurable progress, detects and corrects unreliable experimental results, and makes evidence-conditioned decisions to continue, revise, or terminate research directions. For example, on RSICD benchmark, an AutoResearch-generated idea improves mean Recall from 32.84 to 34.69, while recording only 5 audit-confirmed issue events compared with 11-27 for other autonomous research systems. These results demonstrate a research process in which meaningful insight is grounded before experimentation and conclusions are grounded before acceptance: Insight In, Hallucination Out.

While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, professional documents remains incompletely evaluated. Existing benchmarks emphasize information extraction, require external domain knowledge, or cover professional documents only as one of many settings. They are also largely English- or Chinese-centric, leaving other languages and Russian, in particular, substantially underrepresented. To address these limitations, we introduce BEAR-Bench (Bilingual Enterprise and Academic Reasoning), a self-contained, complex English-and-Russian benchmark comprising 1000 human-annotated questions based on text-rich business and scientific documents. We evaluate 16 proprietary and open-weight MLLMs, including Gemini 3.1 Pro and Qwen3.5-397B, on BEAR-Bench and observe clear headroom even for the strongest systems. Finally, we use the resulting model outputs to compare existing hallucination detection methods, evaluating not only how often models fail on BEAR-Bench but also how reliably those failures can be identified.

Trajectory prediction is central to safety in autonomous driving, yet learning-based predictors tend to degrade sharply when encountering scenarios poorly represented by their training data. Many methods attempt to mitigate distribution shift degradation through data-centric or test-time adaptation approaches; however, they are typically validated along fragmented axes of generalization, leaving the field without a standardized way to compare robustness across shifts a model may encounter. To address this, we introduce ControlledShifts, a framework and benchmark suite that systematically re-splits existing trajectory datasets into in-distribution (seen) and out-of-distribution (unseen) partitions, via a shared characterization-and-splitting formulation, in which a characterization function fixes the axis of variation a benchmark probes and a splitting function fixes how the tail of that axis is withheld. The suite comprises three benchmarks targeting key topological and behavioral distribution shifts. Furthermore, to aggregate multi-dimensional performance metrics across these benchmarks, we propose a unified robustness score that evaluates models along two complementary dimensions: prediction quality (relative performance gain) and prediction stability (performance preservation under shift). We showcase ControlledShifts by benchmarking prominent transformer-based architectures, exposing critical differences in how models of varying capacities handle latent relevance and environmental structure.

Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Existing benchmarks, however, are of limited use as they primarily reflect English-language and US-centric settings, and often only evaluate task performance. In this paper, we present first results of MÖVE, a holistic evaluation framework for the German public sector, examining three rarely considered governance dimensions: energy consumption, provider transparency, and knowledge of German-party positions. Our results reveal significant trade-offs, with no single model excelling across all dimensions: estimated energy consumption varies more than 60-fold and is not explained by model size alone, information disclosure varies systematically across providers, and European models do not exhibit stronger knowledge of German party positions. Model selection for public institutions thus cannot rely on performance rankings alone. Instead, evaluations should also reflect the governance requirements of the deployment context.

Aerial manipulation extends robotic operations to previously inaccessible aerial environments. Unlike arm-equipped aerial systems, tiltable-multirotors can directly generate six-degree-of-freedom wrenches through their flight bases, enabling both efficient movement and omnidirectional operation by tilting the thrust direction. This work presents a design analysis and a wrench-based control framework for tiltable-multirotors in aerial manipulation. We show that a four-rotor tiltable configuration provides a balance between interference-free propeller sizing and hovering efficiency across different attitudes, and its null-space redundancy is crucial for traversing singular configurations under physical constraints. We further show that an upward end-effector placement yields a favorable trade-off between geometric clearance and available wrench. To address disturbances, we propose a dual strategy consisting of a modified integral term for model error and an acceleration-based estimator for external wrenches. Building on these insights, we develop an effector-centric nonlinear model predictive control (NMPC) framework that integrates design choices, singularity handling, and disturbance compensation into a unified formulation. The proposed framework runs fully onboard at 100 Hz on a custom-built tiltable-quadrotor. Real-world experiments, including a 90-deg step cartwheel rotation, whiteboard pushing, and continuous 360-deg valve turning, demonstrate the feasibility of wrench-based omnidirectional manipulation with singularity traversal on a one-DoF-per-arm tiltable-quadrotor.

Reliable transfer of orbital angular momentum (OAM) to microscopic objects typically relies on high-fidelity vortex beams generated by programmable spatial light modulators or precision-fabricated phase optics. Here, we demonstrate that robust OAM transfer in optical tweezers can be achieved using static binary holograms printed on acetate substrates. The printed diffractive optics generate Laguerre-Gaussian vortex beams with sufficient spatial fidelity to induce controlled optical torque and stable rotational manipulation of polystyrene microspheres in a high-numerical-aperture optical tweezers system. Despite a diffraction efficiency of only approximately 2%, the generated beams enable reproducible particle rotation using less than 1 mW of optical power in the first diffraction order. The rotational dynamics were systematically characterized as a function of incident optical power and topological charge, revealing the expected increase in angular velocity with both parameters, consistent with OAM-driven torque in the overdamped regime. These results demonstrate that efficient optical angular momentum transfer is remarkably tolerant to the reduced efficiency of passive printed diffractive optics, establishing a robust, scalable, and high-damage-threshold platform for structured-light optical manipulation with applications in microfluidics, biophysics, optomechanics, and optical trapping.

Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a third behavior underspecified: when a target-adjacent prompt admits a broader answer without target-specific leakage, the model should answer at that level rather than leak, evade, or refuse. We study this specification problem in a controlled LoRA-GRPO RWKU setting, comparing four reward designs that span lexical suppression, anti-refusal shaping, rubric-based broad answering, and an explicit refusal contrast, with and without SFT warm-up. The experiments show that optimization success is not equivalent to behavioral unlearning: RWKU forget scores, held-out completion audits, terminal training-rollout audits, and training dynamics can point to different conclusions. We trace these disagreements to reward-hacking endpoints, policy-support limits in GRPO, benchmark probes that miss endpoint changes, and rewards that can select broad-topic answering with low semantic leakage during optimization.

ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure rather than input-local interactions. We test this in retrieval-augmented generation (RAG), where evidence utility can be measured under controlled interventions. Holding query, evidence, task, scoring, and intervention fixed, nine readers disagree on effect sign in 33\% of jointly affected cells; reader$\times$query interaction explains 29.8\% of utility variance versus an 8.4\% permutation null; and self-selected evidence improves F1 by $+0.031$ ($t=3.39$). We then ask the sharper question: \emph{which components of this heterogeneity are stable reader properties across queries?} Separating three measurable objects---evidence \emph{activity}, \emph{ordinal preference}, and \emph{conditional signed direction}---we find ordinal reader geometry stable across four independent settings (split-half $ρ=0.60$--$0.83$): leave-one-out interventions, PRISM preferences, RAMDocs, and RAGuard. Signed geometry is task-bounded: weak in open-ended QA (0.14, 0.35), especially for misleading and irrelevant evidence, but strong in binary fact-checking (0.75) with no significant ordinal gap, though still below its sparsity-matched ceiling. Sparsity, decoding noise, and metric artifacts do not explain the main ordinal--signed gap. Finally, stable ordinal similarity fails to predict cross-reader intervention transfer (oracle-distance $ρ=-0.27$; regret reliability $-0.28$). Reader-specific utility exists, but preference is not intervention: stable ranking similarity does not license transfer of help/harm decisions.

Embodied intelligence is shifting artificial intelligence from passive digital perception toward active physical interaction. However, foundation-model-enabled embodied agents face a fundamental tension between open-world cognition and resource-constrained deployment. On-device models are limited by computation, memory, and energy budgets, whereas cloud-centric solutions introduce latency and reliability risks over dynamic wireless links. Edge general intelligence provides a promising cognitive backbone, but existing frameworks still lack physical grounding, action awareness, and mechanisms for actively acquiring useful physical experience. To address these limitations, this article introduces edge-native embodied intelligence (ENEI), an action-aware wireless edge framework that integrates embodied agents, the 6G communication and networking fabric, and edge cognitive services into a 6G-mediated bidirectional edge-embodiment loop. Along the edge-to-embodiment axis, confidence-aware assistance and edge-driven generative adaptation enhance local autonomy under out-of-distribution (OOD) conditions. Along the embodiment-to-edge axis, value-of-experience guided active embodied federated learning enables physical actions to generate informative experience for continuous edge model evolution. The 6G fabric supports both directions through goal-oriented transmission and programmable radio-resource allocation. Two case studies on OOD drone navigation and mobility-driven federated learning illustrate the feasibility and communication efficiency of the proposed mechanisms. ENEI provides a unified perspective in which edge cognition strengthens embodied action, while embodied agency actively enriches edge cognition, laying the foundation for scalable, adaptive, and self-evolving embodied wireless systems.

Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On accuracy benchmarks almost nothing happens, and the benchmark itself is noise at this scale: changing only the random seed moves the score by 7.7 points, more than every data and recipe effect we measured. That null is our first result. The real changes live where accuracy cannot see. Base models never think in Greek: 0 of 1,000 reasoning traces, even when the question is Greek, so the model answers correctly while reasoning in a form its user cannot read, audit, or correct. After supervised fine-tuning (SFT), every released checkpoint reasons in the language of the question on ~98% of items, one family at 3x fewer tokens, with judged grammaticality improving on all four models and general ability within a few points of each base: nothing was forgotten, and fluency was gained. We propose six behavioural dimensions that make such changes measurable, each gated to reject any metric that correlates with output length, and we report how our own instruments lied: six failures, each caught by a control. What SFT cannot do is fix its own defects: a quarter of answers skip the requested format, answers leak into the reasoning channel, and an explicit "think in English" is obeyed under half the time. Reinforcement learning with verifiable rewards, pre-registered before training, fixes the first two outright (fallback 24% to 2.5%, leak 3.5% to 0.0%, both against a flat random-reward control) and moves the third (+9.1pp), while the Greek reasoning habit survives an accuracy-only gradient untouched. We release five checkpoints. The instruments, the controls and the pre-registration travel to any low-resource language; Greek is the case that let us measure them.

This study investigates cooperative control of connected and automated vehicles (CAVs) at partially observable highway bottlenecks in mixed traffic, aiming to mitigate congestion without relying on complete global traffic states or online trial-and-error. We propose a physics-informed world model-based offline multi-agent reinforcement learning framework that reconstructs a physically interpretable global traffic state from local CAV observation-action histories, with coupled macroscopic-microscopic traffic dynamics providing physics-based supervision. A probabilistic ensemble world model learns traffic-state transitions and system rewards, while model disagreement quantifies epistemic uncertainty. Multi-step imagined rollouts with pessimistic rewards and uncertainty-driven truncation are then used for offline policy learning. Experiments in a SUMO-based on-ramp bottleneck using approximately $1\times10^6$ offline transitions show that physics supervision improves state reconstruction and world-model prediction accuracy.

In bus routing, the task is to plan a bus route in a network with several agents, each of whom wants to travel from a starting point to a destination. A bus route should account for several factors, including agents' cost for reaching the bus stops, their travel time, or the energy consumption of the buses. We study the complexity of several variants of this problem, focusing on how the objective function and the models for agents' walking costs influence the problem complexity. After observing that even the simplest agent cost model leads to hardness on general networks, we consider networks with tree structure. Our main findings are as follows. First, allowing agent-specific cost models leads to hardness even on extremely limited trees such as stars. Second, consistent agent models (where agents differ only in their starting points and destinations) make the problem easier in some cases. Finally, allowing agents to choose between using the bus and walking directly can make the problem considerably harder. Most of our hardness results show not only classical NP-hardness but also parameterized intractability for the natural parameter $k$, the number of bus stops.

Context: Software systems that depend on commercial large language model APIs must migrate to successor versions when vendors deprecate older models. Migration decisions typically rely on aggregate benchmark scores, which compress heterogeneous item-level behaviour into a single net figure. Objective: We measure what that compression conceals. Method: On three pairwise upgrades in the GPT-5.4 to GPT-5.6 Sol product sequence, we query 900 public benchmark items (graduate-level knowledge, olympiad mathematics, instruction following) 50 times per item per model, classify each item as reliably improved, reliably regressed, practically equivalent, or inconclusive under false-discovery-rate control and a practical-significance threshold, and calibrate the results against a label-permutation null. Results: Across all nine migration-benchmark cells, reliable improvements and reliable regressions coexist. Edges with aggregate gains of up to 7.3 percentage points contain up to 8.3% reliably regressed items; edges with aggregate losses contain up to 10.7% reliably improved items. On the instruction-following benchmark, the gap between strict and loose scoring widens by 3.9 percentage points on the latest migration: a 3.9-point regression under strict scoring shrinks to 0.04 points under loose scoring. Conclusion: Migration decisions based on aggregate scores alone miss substantial bidirectional item-level change. The complete response-level archive and per-item scoring outputs are released.

A robot asked to "place the cup near the red plate or the blue plate" may reach the centroid between them and appear geometrically successful, while satisfying neither disjunct of the instruction. This silent semantic failure exposes a structural limitation of language-conditioned robot policies: representations that collapse a disjunctive instruction into a single connected set cannot preserve all feasible modes, and planners that commit to one action degrade under run-time mode uncertainty. We address this limitation with CompCPZ, a sound algebraic layer that language-conditioned learning systems wrap to recover multi-modal disjunctive representation, recursively composing per-primitive constrained polynomial zonotope enclosures along the language parse tree with distribution-free conformal coverage and sub-millisecond runtime. On a closed-loop ManiSkill3 tabletop-manipulation benchmark, CompCPZ outperforms convex set baselines, multi-peak decoders, and a zero-shot vision-language-action model (1,900/1,918 paired wins, p << 10^(-30)); the same compiler also transfers without retuning to planar real-robot trials on a Unitree Go2 quadruped under motion capture. These results suggest that compositional language grounding should be evaluated not only by reaching a decoded target, but by whether the represented feasibility set preserves the connected-component structure of the user's intent.

Mobile robots that operate in side by side with humans and critical facilities must reach their goals at low cost, despite often unknown true traversal costs of the map apriori and imperfect actuation. Planners that solve the underlying stochastic shortest path problem exactly, such as value iteration, require computation that grows with the diameter of the map, whereas Dijkstra's algorithm is fast but is usually considered inexact once transitions are stochastic. This study shows that Dijkstra's algorithm can remain an exact planning engine under a condition that is much weaker than the causality condition often invoked in the literature, namely nonnegativity of a reduced cost defined on the determinized map. Building on this characterization, an online learner DORA (Dijkstra Oracle Reduced-cost Algorithm) is proposed for robot navigation that calls a shortest path oracle a fixed number of times per episode, never estimates a transition kernel, and adds a logarithmic survival weight when the probability of contact with a dynamic obstacle must stay within a budget. In the numerical experiments involving three other benchmarks that cover grid world navigation, directional drilling, and drone surveillance, the learner matches optimistic value iteration that is given the true transition kernel while performing 4.5 to 19.3 times less planner work, reduces contacts during learning by a factor of seventeen relative to determinize and replan, and keeps the contact rate within budgets that span two orders of magnitude. These results indicate that shortest path search supports safe and efficient online navigation and path planning tasks.

Autoencoders are commonly used for unsupervised data-driven fault detection in nonlinear dynamical systems. Despite their widespread success and often favorable performance compared with traditional approaches, most applications rely on heuristic reconstruction of measured data using features learned from nominal training data, without explicit insight into the underlying nonlinear dynamics. This lack of interpretability limits the extension of autoencoder-based fault detection methods to higher levels of fault diagnosis, e.g., fault localization and quantification, and confines their use largely to application-oriented studies. To address this limitation, we propose a strategy for detecting parametric faults in nonlinear stochastic mechanical systems. A mathematical representation of the output data is developed using Koopman operator theory, which motivates their embedding on a manifold and its subsequent approximation with a two-stage autoencoder. Fault detection is formulated within a hypothesis-testing framework, in which new data are tested for consistency with a neighborhood of the manifold identified from nominal observations. The proposed method is validated through Monte Carlo simulations of a toy mechanical system with two types of nonlinearity and applied to two well-known real benchmarks, where it provides favorable fault-detection performance compared with standard autoencoders.

Key-keyway assembly tasks impose strict geometric constraints and are highly sensitive to grasp pose deviations in uncertain environments. This work presents a force-based offset estimation method for keyed peg-in-hole assembly, embedded within a perception-validation-insertion pipeline. Residual misalignment is estimated directly from wrist force/torque measurements using a local KNN-Gaussian Process hybrid regressor. The framework distinguishes between two contact regimes, hard collision and guided chamfer insertion, and routes inference to a dedicated model for each. Regime classification is achieved via a contact-window duration threshold. KNN combined with a deterministic search using the results of a post-grasp monocular visual validation contributes to an increased accuracy of the regressor model. This approach achieves accurate radial offset estimation in chamfered peg insertion, during a keypoint detection-based pick and place application. Experiments using the integrated force/torque sensor of a collaborative robot arm showed an increase in insertion success rate from 67% to 87% after the pipeline was applied.

Multi-robot patrolling requires a team to visit all areas of an environment at regular intervals, typically minimising idleness. A practical extension, motivated by security and environmental monitoring, is to additionally form a collective ranking of all patrol locations by some measured signal, a generalisation of the best-of-n problem to the many-option, continuous-valued regime. We observe that the patrol graph admits a natural dual interpretation: it is simultaneously the topology that dictates agent movement and a factor graph over which spatial beliefs can be propagated. Exploiting this equivalence, we apply Gaussian Belief Propagation (GBP), a graph-based algorithm, to collective ranking using unary measurement factors at visited nodes and pairwise smoothness factors along patrol edges. We compare GBP against simple and visit-count-weighted averaging across a range of sensor-noise conditions in simulation, and validate the approach on four Leo Rovers tracking a propagating radio signal in an office lobby. GBP outperforms both baselines on ranking accuracy, mean squared error, and time to consensus. We find that as noise increases and the task becomes harder, GBP degrades gracefully in simulation while both averaging methods degrade substantially. Hardware trials reproduce the same performance ordering on a real propagating radio signal, supporting the practical relevance of the simulated results.

Integrating open-vocabulary perception into object-level 3D scene graphs is a double-edged sword. While vision-language detectors recover long-tail categories and small, fine-grained objects overlooked by closed-set models, they also tend to fragment large surfaces and merge small objects into larger neighboring objects, compromising instance-level consistency and undermining mapping fidelity. Moreover, existing methods struggle to retrieve previously unmapped targets or determine whether a queried object is absent, hindering robust embodied open-world navigation and exploration. We present OVIP-SG, a unified framework for instance-preserving semantic mapping, functional scene partitioning, and language-guided small, fine-grained object retrieval. OVIP-SG uses a vision-language model (VLM) to enumerate scene-specific categories for robust open-world detection. Symmetric 3D Intersection over Union (IoU) association and area-weighted feature fusion preserve small independent instances, while VLM-inferred object functions partition scenes into compact functional search regions. A four-stage cascaded retrieval pipeline further incorporates voxel voting and determines target absence from exploration coverage. Under a unified evaluation protocol on Replica, OVIP-SG outperforms ConceptGraphs by 6.31 points in class-mean accuracy (mAcc) and 5.15 points in frequency-weighted mIoU (F-mIoU) while achieving a class-agnostic native-instance Panoptic Quality (PQ) of 0.398. It reduces the search area to 21.8% of the indoor floor space and reaches 0.773 balanced accuracy for object-presence classification. Real-world robotic experiments further demonstrate its practical effectiveness.

Developing robots capable of understanding and manipulating objects requires compact, interpretable, and generalizable representations. This work proposes a reinforcement learning-based framework for robotic grasp refinement, integrating keypoint-based object representations with a Deep Q-Network (DQN). Using 2D overhead images captured in a simulated environment, a geometric-based algorithm generates initial grasp candidates, which are iteratively refined by the proposed framework, transforming failed grasps into successful ones. Experiments conducted on 300 objects from the Dex-Net dataset using a UR5 manipulator demonstrate the framework's effectiveness, achieving a 100% success rate on objects previously deemed ungraspable by geometrical methods. The framework's sim-to-real transferability is further validated through physical experiments on a Delta parallel robot, where a refined grasp successfully manipulates an object that was previously ungraspable. The findings underscore the effectiveness of reinforcement learning in addressing challenges in robotic grasping, offering a scalable and adaptable solution for contact-rich manipulation tasks.

We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in fixed-size segments via test-time learning of fast-weight neural memory networks with layer-localized gradient updates; at inference, the memory generates keys and values from the query tokens alone, with no context tokens re-read. This two-phase design decouples inference cost from context length, achieving $O(N)$ preprocessing and $O(1)$ query cost with peak GPU memory that does not grow with $N$. At 128K tokens, MoNe reduces both compute and peak GPU memory by approximately 80% compared to ICL with only 6.4% parameter overhead. MoNe generalizes to context lengths far beyond the backbone's native window, achieving strong performance on needle-in-a-haystack and word extraction benchmarks from RULER, where ICL degrades sharply.

We consider the dynamic principal-agent problem under asymmetric information, wherein a principal sequentially designs contracts to incentivize an agent with unknown preferences and hidden actions. A fundamental bottleneck in the existing literature is the assumption of deterministic agent utility, which renders the principal's expected utility discontinuous and forces computationally intractable discretizations of the contract space. In this paper, we address this limitation by introducing a stochastic counterpart into the agent's utility model, capturing the inherent physical and behavioral variations in realistic subsystems. We formally prove that this stochastic formulation restores the continuity of the principal's expected utility. Leveraging this continuous geometric structure, we formulate the interaction as a structured multi-armed bandit problem subject to heteroscedastic noise. We propose a \texttt{Heteroscedastic GP-UCB} algorithm that utilizes a Neural Network (Arcsin) kernel, chosen to capture the non-stationary, sigmoidal geometry of the utility landscape. For an $m$-dimensional compact contract space, we establish a high-probability cumulative regret bound of $O\left(\sqrt{T}(\log T)^{m+1}\right)$. Finally, we demonstrate the practical efficacy of our theoretical framework by formulating the Vehicle-to-Grid (V2G) incentive design problem, proving its equivalence to a dynamic principal-agent problem, and showing superior economic performance for grid aggregators.

Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews multi-turn conversational AI across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around datasets and benchmarks, modeling paradigms, training strategies, evaluation setups, and cross-cutting challenges. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a session. Despite stronger capabilities to perceive, speak, and act across modalities, current systems still struggle with persistent memory, cross-turn grounding, full-duplex interaction, robust evaluation, and cultural alignment. We conclude with a research agenda for systems that can remember, revise, ground, speak, listen, act, and adapt across turns, modalities, and cultures. (https://github.com/faiza-sfa/multiturn-conversational-ai-survey)

This paper studies tactile-only 6-DoF pose refinement and belief maintenance for grasped objects in static and short quasi-static in-hand configurations where vision is unavailable or heavily occluded. The key difficulty is tactile partial observability: whole-hand taxel contacts are sparse, intermittent, and ambiguous under limited excitation and object symmetries. We propose a physics-informed particle filter on $\mathrm{SE}(3)$ that updates pose beliefs from dense whole-hand tactile measurements. The likelihood combines active-contact signed-distance consistency, force-normal alignment, friction-cone feasibility, zero-force negative evidence, and optional feasibility guards. A sliding-window log-likelihood fuses recent tactile frames to reduce single-frame ambiguity, while a potential-field-guided proposal steers particles away from hand--object penetration. Symmetry-aware resampling preserves multiple plausible modes. Experiments on an Allegro Hand V5 with five objects show lower normalized ADD-S than tactile-only geometric, particle-filter, and learning baselines, and ablations confirm the benefits of temporal fusion, potential guidance, and mode preservation.

Visual cues are increasingly adopted to guide robot learning, but whether Vision-Language-Action (VLA) models can reliably follow authorized cues while disregarding unauthorized ones remains unclear. Existing work covers only a narrow range of cue forms and focuses on final task success, providing only a coarse assessment of cue-following capability. Treating all visual cues as authorized also leaves safety risks of unauthorized following unexplored. To address these gaps, we introduce LIBERO-VIFO, a benchmark to evaluate both the capability and safety of visual cue following in VLA models. LIBERO-VIFO defines eight visual cue families spanning diverse forms. A total of four protocols in two parts are defined: Part I tests cue understanding and authorized following, while Part II evaluates unauthorized visual cue following under language-cue conflict and empty language conditions. Evaluating seven VLA models reveals that although visual cue understanding does not reliably translate into execution, current VLAs are able to execute cue-indicated tasks without language instruction, exposing an emerging risk of unauthorized visual cue following. Extended experiments on scene-instantiated cues, safety-critical settings, and real-robot deployment corroborate these findings. LIBERO-VIFO brings both the capability and safety of visual cue following into systematic evaluation, establishing visual-centric safety as a new perspective for the VLA community.

In this study, we investigate developmental mechanisms that enable small, resource-constrained systems such as cm-sized millirobots to autonomously explore, learn, and adapt their capabilities throughout their lifespan. Reinforcement learning algorithms guide the agent's skill acquisition and adaptation through the interplay of our proposed tinyDSM, which integrates intrinsic motivation and fitness-based assessment. We strive for minimal, hard-wired skills while encouraging the open-ended development of new skills. A key emphasis in our approach is to encode minimal a-priori general knowledge, which serves as a foundational starting point for the system as it further learns system-specific dependencies from the initial knowledge provided. Thus, by design, our approach attempts to cover very generic application domains. The methodology is based on (a) developmental mechanism with intrinsic motivation, and (b) a cognitive architecture (knowledge, reasoning, learning), while (c) utilizing minimal resources. It uses a hierarchical knowledge graph and kinematic reasoners to model and evaluate simple and advanced motion related skills. In our experiments, we use a resource-constrained millirobot with a volume of 36 cm^3 with a Raspberry Pi Pico 32-bit microcontroller (RP2040) that integrates all described features and capabilities except the camera system in 9 kB. Starting with learning the most elementary motor skills the millirobot autonomously progresses from simple linear and angular movements to complex geometric patterns within 15 minutes. To complement the physical experiments, we perform a simulation-based analysis that enables systematic comparisons across learning algorithms and intrinsic motivation parameters.

The communication demands of distributed model prediction control (DMPC) can overwhelm even advanced wireless communication technologies as agents must exchange a significant amount of information at least once per time step. To semantically reduce communication demands, this work employs encoder-decoder networks built around long-short term memory (LSTM) cells in a distributed optimization algorithm. Agents publish a reduced representation of a message and receivers reconstruct the original message upon reception. In tests with reduced communication using formations of mobile robots, trained networks retain satisfactory performance and work reliably under conditions overwhelming full communication. As the results show, the usage of LSTMs either allows unprecedented reconstruction accuracy or the usage of different prediction-horizon lengths without the necessity to retrain.

Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that following procedural guidance and improving it from execution evidence are distinct capabilities. Inference time loops can repair skills but do not improve the model that writes the next one. We study how to organize execution experience from intermediate skills into training states for an optimizer. We introduce WER (Write, Execute, and Refine), a multi-phase framework that trains a Skill Optimizer outside a frozen executor. The optimizer proposes skills, a frozen agent executes each repeatedly, and a programmatic verifier scores the outcomes. The scores provide relative credit and select mixed-outcome records. Matched successful and failed trajectories from these records form the next phase's refinement states, so the optimizer learns from the consequences of its earlier outputs. On BFCL v4 multi-turn and tau2-bench, WER improves average Pass@1 over the no-skill baseline by 7.80 and 3.85 points, respectively. Under an identical refinement workflow, it outperforms the same backbone without optimizer training by 9.35 and 10.29 points. The trained 4B optimizer reaches 76.63 percent on BFCL v4, outperforming all evaluated off-the-shelf general-purpose models used as skill optimizers on average.

We propose HODAgent, a System-2 embodied agent for humanoid robots in service settings, addressing situated intent, responsive execution, task revision, and outcome verification. Its semi-duplex architecture integrates an Env-Interactor, Planner, Executor, and hierarchical Memory to maintain coherent interaction, planning, and task state during service episodes. This allows handling new requests during motion, retaining progress, revising actions, and grounding closure in execution outcomes. A shared interface connects simulation and physical robots (Unitree G1), isolating platform-specific control. In an interactive simulation with 164 cases, HODAgent achieves 84.8% and 91.5% Joint Success under two VLM backbones, outperforming baselines by 9.8 and 18.9 points. On physical robots, pass rates are 92% (atomic), 72% (composite), and 63.3% (complete tasks). On multiple embodied benchmarks, it improves over baselines by 0.7-9.0 points. Results show a unified System-2 agent enables adaptive humanoid service across simulation and reality.

How cautious should an agent be while it is still learning its environment? We propose RATTL (Risk-Adversarial Total-Reward Learning), which ties caution to epistemic uncertainty: the agent holds a Bayesian posterior over unknown dynamics and plans against a Wasserstein ambiguity set whose radius is a monotone function of that posterior. The radius contracts with evidence, so behaviour interpolates continuously between worst-case robustness and risk-neutral total-reward maximization. The design follows the duality underlying the Entropic Value-at-Risk, which converts the choice of a risk level into the choice of an ambiguity radius. We show the resulting planning problem is well posed under transience and compactness conditions, and prove a Safety Sandwich: the RATTL value lies between the uninformed robust value and the full- knowledge optimum, with a gap that vanishes as the posterior concentrates. In a canonical binary-hazard instance, the induced criterion reduces to Conditional Value-at-Risk at a level set by the posterior entropy. A worked example shows the agent deferring the efficient action until a sharp identification threshold. RATTL targets runtime safety for agents, including LLM-based systems, acting under uncertainty.

Pretrained molecular language models are increasingly used as molecular encoders for learning structure-property relationships. However, their practical suitability for molecular discovery within and beyond their pretraining domain remains unclear. Herein, we systematically benchmark four molecular language models across six virtual molecular libraries spanning drug discovery, organic materials, and catalysis. Native molecular language model embeddings show substantial variation in discovery performance across libraries, whereas molecular fingerprints provide a consistently strong and robust baseline. Consistent with a potential domain-representation mismatch, we show that explicit domain adaptation substantially improves representation performance. Fine-tuning molecular language model encoders on structures from the target virtual library consistently improves sample efficiency, with several adapted encoders emerging as the top-performing representations across the benchmark tasks. These results show that molecular representation quality depends strongly on the target domain and that explicit adaptation can improve the practical utility of molecular foundation models. More broadly, our findings establish domain-adapted molecular representations as a promising strategy for sample-efficient adaptive decision making in virtual screening and self-driving laboratories.

Cameras are ubiquitous sensors in robotics due to their compact form factor and the perceptual richness captured through visual information. Monocular SLAM enables robots to understand the environment with a minimum setup, however, it inherently suffers from scale ambiguity. A common solution is to provide multi-modal sensor configurations, such as visual-inertial systems, where scale is observable unless the robot navigates under a constant-velocity motion, a common scenario in mobile robotics. With the advent of deep-learning, geometric foundation models have been used to address this problem, but the depths maps are often noisy and scale-inconsistent across frames. In this paper, we propose Scalix, a real-time monocular SLAM framework that achieves metric-scale state estimation by integrating learned depth cues into a probabilistic factor-graph formulation. By augmenting existing monocular depth models with both per-pixel depth uncertainty and per-frame scale uncertainty, Scalix treats scale predictions as independent measurements within its optimization, leading to improved scale consistency through multi-view data associations. Experiments in large-scale outdoor and indoor environments demonstrate state-of-the-art performance on both metric and up-to-scale benchmarks while maintaining real-time operation and generalization.

Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine use. For Multimodal Large Language Models (MLLMs), the core challenge is not only perception, but representation: scientific pages interleave text with Structured Academic Elements (SAEs) such as tables, formulas, charts, and pseudocode, whose structure, data, and logic are poorly preserved by common surrogates like Markdown. We therefore propose Compilable Academic Document Parsing (CADP), a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page. To support this setting, we introduce CADP-Bench, an expert-verified benchmark of full academic pages containing tightly coupled text and multiple SAE types, evaluated through a re-injection compilation protocol. We further study current capabilities using SOTA MLLMs and an exploratory multi-agent baseline that incorporates common agentic techniques. Results show that even frontier models still struggle to produce high-fidelity executable reconstructions, highlighting substantial room for improvement in structure-aware scientific document parsing. CADP-Bench is released for future research.

Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor interpretability for complex ones, making it difficult to meet the requirements for both answer quality and efficiency in high-risk scenarios. To address this issue, this paper proposes CoAL-RAG, a complexity-aware legal retrieval-augmented generation method, which constructs a multi-dimensional evaluation mechanism based on ``question essence'' and ``retrieval consistency'' to enable adaptive routing of retrieval strategies. First, the reasoning demand is quantified according to the logical structure of the question. Then, the discrepancy between semantic retrieval and keyword retrieval is utilized to indirectly reflect problem complexity, thereby selecting the most appropriate retrieval strategy and dynamically filtering contextual information. Experimental results demonstrate that the proposed method significantly outperforms baseline models not only on Chinese legal benchmarks (SocialLawQA, LawBench) but also demonstrates strong cross-jurisdictional generalization on English datasets (LexGLUE, CaseHold). Specifically, on Chinese datasets, the BLEU score improves by 42.5\% and ROUGE-L reaches 3.6 times that of knowledge graph-based methods. On English benchmarks, CoAL-RAG maintains highly competitive accuracy, achieving an optimal balance between generation quality, deep logical reasoning, and system efficiency across different legal systems.

Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localizes the relevant state, restores its branch-local context, and augments it with reusable evidence retrieved across branches, preserving interaction continuity without conflating semantically related but structurally distinct trajectories. Existing long-term memory benchmarks cover diverse memory and reasoning capabilities but do not explicitly isolate branch-structured challenges. We therefore introduce BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. Experiments on LongMemEval, LoCoMo, BEAM 100K, and BranchMemEval show that ArborMem outperforms the strongest baselines by 3.36 to 10.31 percentage points on the three established benchmarks and by 5.0 points on BranchMemEval. Its advantage grows under constrained read budgets, while complete memory queries remain below half a second.

Gender bias or other social biases in large language models (LLMs) are frequently evaluated with question answering or survey benchmarks where the LLM needs to give a response in a predefined answer format. It is well known in survey science that the answer format has a substantial impact on answers, just as LLMs are sensitive to the prompt wording. However, to our knowledge it has not been studied yet how changes in answer format impact the measurement of gender bias in LLMs and their alignment with human response distributions. We evaluate three instruction-tuned models on the BBQ benchmark and OpinionQA survey data across closed-ended, Likert-scaled and open-ended formats, comparing bias measurement and distributional alignment under otherwise identical conditions. We find that answer format does substantially alter measured outcomes, including reversals in order rankings. These differences arise because each format elicits distinct response behaviours, such as forced-choice selection, scale-based distributions and refusal in free-text generation. Our findings highlight the importance of treating answer format as a substantive component of LLM evaluation and motivate multi-format designs for more robust model assessment.

Although Large Vision-Language Models (VLMs) have significantly advanced embodied navigation, their direct deployment remains challenging, as existing methods often force VLMs into unnatural action spaces that misalign with their 2D pre-training priors, compounded by rigid reasoning schedules and inefficient memory management. To overcome these limitations, we propose TAMP-Nav, a unified framework for efficient embodied navigation. First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual prompting. Specifically, the VLM merely selects 2D pixels, which are then projected into 3D coordinates for a low-level SLAM controller. This design naturally aligns embodied execution with the VLM's inherent 2D visual capabilities. Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize), which dynamically triggers Chain-of-Thought and retains high-fidelity memory only at critical nodes, compressing redundant trajectories into lightweight Space-Time Indicators, thereby preserving critical historical information and enhancing spatio-temporal perception. Finally, we design an efficient Two-Level Alignment Paradigm (Align) via Group Relative Policy Optimization (GRPO). By superimposing global outcome rewards with fine-grained process rewards, this dense supervision tightly aligns the agent's cognitive planning with physical environmental feedback, endowing the model with adaptive reasoning capabilities. Experiments demonstrate that TAMP-Nav achieves state-of-the-art performance (e.g., 66.2% SR on R2R-CE) with high runtime and sample efficiency (requiring only 90k training trajectories).

Spin defects in silicon carbide (SiC) are promising candidates for integrated quantum photonics, offering long-lived spin states and near-infrared emission suitable for low-loss photonic integration and fibre-based quantum communication. However, light extraction from these defects remains challenging due the relatively high refractive index of SiC. Metalenses offer a compact approach to enhance light collection by engineering the wavefront directly at the material interface. Here, we design and fabricate monolithic metalenses from SiC bulk material that simultaneously operate at 860 and 1240 nm, matching with emission from the nitrogen vacancy and silicon vacancy colour centers. By independently engineering the phase response at both wavelengths, the metalens enables collection and polarization manipulation of the emitted light. We further employ the metalenses to demonstrate optically detected magnetic resonance of both defects simultaneously. These multifunctional metalenses provide a compact optical interface for scalable integrated SiC photonic devices.

Vision-language-action policies generalize broadly but provide no execution-time guarantees; classical model-based planners respect kinematic and geometric constraints but generalize poorly. We study whether an action-conditioned Joint-Embedding Predictive Architecture (JEPA) world model can predict, before execution, both task progress and physical risk for candidate action chunks, and whether coupling these predictions to an embodiment-specific model-based safety shield yields a deployable pipeline for heterogeneous robots. We propose a receding-horizon decision pipeline: (1) a proposer produces K candidate action chunks; (2) an action-conditioned JEPA rolls each candidate forward in a frozen-encoder latent space conditioned on an embodiment embedding; (3) calibrated risk and progress heads score each rollout and report uncertainty; (4) a deterministic per-embodiment safety shield filters inadmissible candidates; (5) a fallback ladder handles empty-admissible-set cases. The learned ranking only reorders admissible candidates; enforcement guarantees come from the deterministic shield and fallback ladder. We evaluate with a pre-registered protocol in simulation (LIBERO-Long). In 600-episode configurations the full framework improved success over a shield-only baseline and reduced collision false negatives at matched recall. Deployment-efficiency measurements on target on-robot and edge accelerators are included. Real-robot experiments and an offline reranking significance test remain future work; see the paper for disclosures.

Frozen vision-language-action (VLA) policies are increasingly improved at test time by sampling additional policy behaviors or introducing external demonstrations. Yet there is little guidance for deciding which intervention a deployed policy actually needs. Additional sampling is useful only when better behavior already exists within the policy's stochastic rollouts and can be identified, whereas retrieval is most useful when the relevant action prior is not reliably represented by the policy. We study this decision through two measurable factors, recoverable headroom and retrieval complementarity, which characterize how much useful behavior is already available to recover and whether an external action prior fills a measurable gap. We evaluate an episode-level retry selector under retryable or parallel execution, together with retrieval across multiple frozen VLA policies and environments. The selector consistently recovers substantial latent capability across all tested VLA backbones on LIBERO, with gains of up to 21.0 success-rate points that closely track recoverable headroom. It also transfers to a different robot and simulator and remains effective under degraded observations, while experiments with autoregressive OpenVLA illustrate the distinction between available headroom and the ability to rank candidate rollouts. Retrieval behaves differently, improving the policy with the largest measured action-prior gap and providing further gains when combined with selection. Together, these results provide an empirical basis for characterizing test-time augmentation opportunities by separating capability that can be recovered from the frozen policy from behavioral priors that may need to be introduced externally.

Long-horizon humanoid vision--language--action (VLA) control with head-mounted stereo cameras requires visual interfaces that can exploit complementary views while maintaining compatibility with pretrained representations. Existing interfaces often discard complementary stereo evidence or fuse additional observations without preserving the native primary-view pathway and adapting auxiliary information to robot embodiment. We present EATR-Stereo, an embodiment-aware token-routing framework that retains primary-view tokens and constructs primary-aligned Cross-View Auxiliary Tokens (CVATs) by querying the synchronized auxiliary-view token sequence. A body-segmented proprioceptive encoder further conditions token-wise auxiliary usage on robot configuration history, enabling selective incorporation of stereo evidence during action generation. The routed auxiliary stream augments the language and primary-visual context of a pretrained VLA while keeping its vision--language model frozen. On a 33-DoF physical humanoid with a 37-D proprioceptive state, we evaluate nine configurations in over-100-s search--approach--grasp--place--return tasks. EATR-Stereo achieves 60.0% full-task success, 100.0% grasp success, and 80.0% stage success. Under severe asymmetric occlusion, it improves recovery to 80% compared with 30% for CVAT alone. Ablation studies further show the importance of preserving primary tokens and combining cross-view auxiliary features with structured proprioceptive routing. These results demonstrate that selectively routed paired stereo evidence improves spatial grounding for reliable long-horizon humanoid VLA control.

LLM agents have been widely adopted to operate mission-critical infrastructure (MCI). These agents normally rely on a harness that determines what information they can access, which tools they can use, and what actions they can take. Existing systems often expose the same comprehensive harness to every task, which may not be necessary and cause resource wastes. In this paper, we focus on the identification of optimal harness configurations, and view it as a resource-matching problem between what each task requires and what the harness provides. To measure this match, we classify MCI tasks based on the mathematical representation of the underlying system and rank harness configurations by the amount and type of information they provide. We then construct task-to-harness mappings from two sources: mining research literature and measuring controlled agent execution. Leveraging the measured mapping, we propose a new harness provisioning algorithm: map-guided escalation. It begins with a task-specific harness and expands to full provision only after a failed self-check. We evaluate our method in two representative MCI tasks: in liquid cooling, it improves the agent accuracy from 0.652 under full provision to 0.715 and achieves accuracy comparable to Reflexion with 48% fewer tokens; In power grids, full provision remains accuracy-optimal, while map-based provisioning offers lower-cost alternatives. These findings show that harness provisioning follows a domain-dependent accuracy-cost Pareto frontier rather than a universal optimum.

Generative imitation learning policies excel at trajectory planning but lack closed-loop force regulation, while directly incorporating force modalities often requires redesigning or retraining the network. We present UniReflex, a universal plug-and-play framework that equips frozen generative policies with variable impedance control (VIC) for contact regulation, guided by force-direction intent collected during demonstration, without further slow-backbone fine-tuning. By non-invasively intercepting deep latent representations from the action head, UniReflex drives a fast reflex network that decouples active force exertion from external interaction response. This scheme predicts normalized anisotropic stiffness directions for directional compliance allocation. Furthermore, UniReflex integrates an adaptive gating mechanism that enables seamless transitions between position-dominant planning and force-dominant execution. Real-world bimanual experiments demonstrate that UniReflex significantly improves contact stability and success rates while preserving original position accuracy. Our approach achieves 25-66x lower per-step backward latency relative to joint training strategies on the evaluated backbones.

GRPO is increasingly used for reinforcement learning of vision-language-action (VLA) policies because, unlike PPO, it does not require training a critic. This simplification comes with a sampling cost: group-relative advantages require multiple rollouts from each scene. Under binary success rewards, groups whose rollouts all succeed or all fail have zero advantage and are discarded by dynamic sampling. These groups are especially common early in training, when most rollouts fail, wasting much of the expensive robotic rollout budget. We introduce Prism-GRPO, which augments binary outcome reward with a weighted trajectory-level execution-quality score. By splitting same-outcome groups into a quality spectrum, Prism-GRPO recovers training signal while ensuring that every success still outranks every failure. Quality scores can be derived from simulator contacts, executed actions, or visual observations, avoiding task-specific progress rewards. We prove that Prism-GRPO never increases the probability that a sampled group is discarded for having zero advantages, and derive a gradient-alignment condition under which its combined update remains a local ascent direction for task success. Across four RoboTwin tasks spanning different horizons and coordination patterns, Prism-GRPO improves success and quality at matched rollout budgets and reaches target success rates with up to 56% fewer rollouts. It also suppresses a reward-hacking shortcut, with the cleaner behavior transferring under direct deployment to a real robot. Through ablations, we show consistent gains across contact-, smoothness-, and VLM-derived quality signals.

Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce ManiGuard, a specification-grounded framework for evaluating and improving the safety of foundation-model manipulation, comprising the ManiGuard-Bench task suite and a paired safety-annotated trajectory-generation pipeline. ManiGuard-Bench organizes six contact-rich household task families into 200 locked base tasks along a skill $\times$ constraint taxonomy, with safety specified independently of task success. Each task is evaluated under one in-distribution and four single-axis out-of-distribution perturbations that hold the safety specification fixed, giving 1,000 locked scenarios. Every rollout is runtime-checked by LTL$_f$-grounded automaton monitors over physics-grounded predicates rather than learned classifiers or LLM judges, in simulation and on a physical Franka platform. The pipeline pairs an automated motion-planning generator with human teleoperation, annotated by the same per-step monitor, and directly supports safety-aware fine-tuning; we release 8,000 safety-annotated demonstrations, 40 per base task. Benchmarking zero-shot and fine-tuned VLAs across more than 23,000 rollouts, we find: (i) safety must be evaluated independently of task success, as 6-21% of successful rollouts violate the specification; (ii) fine-tuning on our suite raises safe task completion from near zero to 7.5-29.8% and engaged-and-safe behavior from 16-40% to 51-72%; but (iii) a gap remains that scaling demonstrations does not close, with 21-42% of engaged rollouts still violating, two of six families below 2% safe success for every policy, and these failures persisting under distribution shift and on hardware.

In this work, we demonstrate a data-driven machine learning (ML) framework for the efficient design and optimization of Kretschmann-configuration-based surface plasmon resonance (SPR) sensors. A physics-based dataset was generated using a MATLAB-based transfer matrix method (TMM), covering diverse material properties, layer thicknesses, and multilayer configurations. Optical properties and layer thicknesses were used as input features, while figure of merit (FOM) and minimum reflectance (Rmin) were the target performance parameters. Four ML models, namely CatBoost, XGBoost, LightGBM, and multilayer perceptron (MLP), were benchmarked using R2, mean absolute error (MAE), and root mean squared error (RMSE). The framework integrates ML benchmarking, SHAP explainability, robustness analysis, and optimization-driven inverse design. SHAP-weighted perturbation experiments assessed the model's robustness to input variations. Four optimization algorithms were employed for inverse sensor design, followed by an analysis of parameter recovery and performance. The optimizers were also evaluated using an independent forward-design task, in which repeated runs converged on a common configuration. The optimized designs agreed closely with direct TMM calculations, with FOM errors of 0.6-0.9 percent and Rmin errors below 0.7 percent. The ML models achieved R2 values greater than 0.99 while reducing computational cost from seconds to milliseconds, corresponding to an acceleration of approximately 10^3 to 10^4 times compared with direct TMM simulations. Overall, the results demonstrate that physics-based surrogate ML models combined with explainability and optimization provide a computationally efficient and interpretable framework for rapid SPR sensor analysis, inverse design, and optimization.

Repetition is a fundamental mechanism in human learning, where revisiting successful experiences strengthens memory, consolidates skills, and improves future performance. Motivated by this biological principle, we introduce Instant Episode Repetition (IER), a simple and novel mechanism that improves sample efficiency by immediately repeating action sequences from successful episodes during environment interaction. Unlike conventional approaches such as Experience Replay and Self-Imitation Learning (SIL), which passively reuse past experience during training updates, IER directly influences the data collection process. Upon identifying a high-reward episode, the agent repeats its action sequence for a fixed number of subsequent episodes, reinforcing valuable behaviors through renewed interaction with the environment. We integrate IER into state-of-the-art SAC and TD3 algorithms and evaluate its effectiveness on continuous-control benchmarks, including MuJoCo, the DeepMind Control Suite, and a real-world dynamic object translation task with a robotic manipulator. Experimental results demonstrate that this simple mechanism improves learning performance over standard and self-imitation-based baselines.

Neural network surrogates are an emerging alternative to traditional electromagnetic wave simulators like finite-difference time-domain (FDTD); their goal is to replace rigorous physical simulations with pre-trained neural networks that solve wave-scattering forward and inverse problems orders of magnitude faster. However, nonrecurrent, single-step surrogates have scaled only to a few tens of simulation variables. Here, we show that this barrier can be overcome by dynamically generating salient training examples during training, rather than randomly sampling the large space of possible examples. We introduce an algorithm that runs in parallel with surrogate training, using gradient ascent to search refractive-index and source configurations for cases where the surrogate disagrees with a full-wave ground-truth simulator. We also use source and ground-truth normalization with an evolving replay dataset to stabilize and accelerate learning. Using this approach, we train a fast, single-step surrogate for two-dimensional wave scattering with up to 41,772 controllable variables, including dense, freely configurable grids of refractive indices and complex-valued sources. The resulting neural surrogate is robustly accurate across diverse structured and unstructured examples and generalizes inductively to larger domains, reaching over 3 million controllable variables without retraining, a $73.8\times$ increase. We demonstrate the surrogate on large-scale forward simulations and inverse design of freeform beam splitters and gradient-index (GRIN) lenses up to 98 wavelengths wide, showing comparable or better performance than FDTD-based designs, with speedups from $1.29\times$ to $26.5\times$. These results demonstrate a practical path toward fast, robustly accurate, inductively scalable neural simulators for photonic inverse design and other wave-scattering inverse problems.

Robotic manipulation policies trained via imitation learning, such as Action Chunking with Transformers (ACT), can achieve strong performance under ideal conditions but often remain sensitive to small execution errors and distribution shifts. Correcting these failures typically requires dataset aggregation and full-policy retraining, which is computationally expensive and unsuitable for real-time deployment. In this work, we propose Online Residual Policy Adaptation (ORPA), a framework that enables immediate, feedback-driven correction of robot actions without modifying the underlying policy parameters. ORPA augments a pretrained control policy with a lightweight, feedback-conditioned module that predicts residual adjustments directly in joint space, allowing the system to adapt its behavior at runtime. We evaluate ORPA on a set of precision-sensitive manipulation tasks using the ALOHA platform, demonstrating improvements in success rate and recovery from small perturbations compared to baseline control policies and rule-based inverse kinematics corrections.

Brachiation is a form of locomotion in which primates move primarily using their arms, enabling traversal in environments without footholds. However, this motion requires highly coordinated whole-body movement and precise timing control for bar grasping and release. As a result, achieving robust behavior on life-sized robotic platforms remains challenging. In this study, we present a reinforcement learning-based method to realize brachiation on a life-sized dual-arm robot. The core of the proposed approach is Waypoint-Guided Reinforcement Learning (WGRL), a learning framework for inducing non-linear and complex motions. For high-difficulty tasks where imitation learning data are unavailable, WGRL guides behavior acquisition by sparsely specifying waypoints for the end-effector trajectory, while whole-body motion is generated through reinforcement learning. In addition, by integrating the waypoint-following guidance with rewards based on task success and mechanical energy, and training in an environment designed for Sim-to-Real transfer, the proposed method achieves both forward progression and motion stability. The acquired behavior is evaluated through Sim-to-Sim experiments under monkey-bar environments with geometric variations and hardware experiments, confirming robust brachiation including failure recovery behavior. This study provides effective learning design guidelines for realizing arm-based locomotion on life-sized robotic hardware and expanding the traversable workspace of robots.

Vision-language navigation agents are often evaluated on their ability to follow route-like instructions toward a fixed goal. Yet, real navigation instructions often depend on observed states of the environment: if a condition holds, then follow one path, otherwise take another. Such instructions require an agent to evaluate scene evidence, select the correct logical branch, and execute the corresponding navigation behavior. Existing evaluations provide limited control over conditional branch execution, making it difficult to determine whether agents fail because of perception, grounding, navigation, or logical decision-making. We introduce CondVLN, a scene-graph-grounded benchmark for diagnosing conditional branching in vision-language navigation. CondVLN programmatically generates instructions whose branch conditions are grounded in verifiable 3D scene-graph predicates, with controlled variation in branch depth, dependency chain length, spatial composition, evidence observability, and instruction horizon. CondVLN contains over 11,500 generated conditional instructions across AI2-THOR, Matterport3D, Gibson, and ReplicaCAD, and evaluates agents using standard VLN metrics and branch-specific diagnostics: Branch Selection Accuracy and Conditional Success Rate. Evaluating four state-of-the-art VLN agents (VLN-Zero, NaVid, NaVILA, and Open-Nav) shows that conditional branching exposes failures that are not captured by standard success rate or path length alone: agents can navigate plausibly while committing to a branch inconsistent with the observed scene condition. We also present a lightweight neurosymbolic branch-selection model that separates condition grounding from navigation execution, improving performance by 2x. CondVLN provides a reusable testbed for measuring whether embodied agents can not only follow instructions, but follow the right instruction under the right condition.

This paper considers robust nonadaptive regulation for general nonlinear systems in an output-feedback setting with arbitrarily high relative degree. We develop a nonadaptive design that combines an input-driven filter and a generic internal model with a recursive backstepping law, thereby recasting the regulation problem as the robust input-to-state stabilization of an augmented error system. Unlike adaptive schemes, the proposed method does not rely on linearly parameterized regressors and does not require the construction of Lyapunov functions having merely nonpositive derivatives. Under standard assumptions on the exosystem, including purely imaginary and simple eigenvalues, together with a minimum-phase input-to-state stability condition on the internal dynamics, we establish global asymptotic regulation and derive explicit, verifiable inequalities for selecting the design gains. The resulting nonadaptive framework guarantees convergence of the estimation and tracking errors even when the controlled-system dynamics are complex or only partially known. The effectiveness of the theoretical results is demonstrated using a benchmark controlled Duffing system.

HVAC systems represent a major share of building energy consumption. Traditional control strategies are limited in coordinating energy-comfort tradeoffs across multiple zones simultaneously. Reinforcement learning (RL) offers adaptive, data-driven control that optimizes performance over time. However, deploying learned neural network controllers in safety-critical building systems remains challenging due to lack of formal safety guarantees. We propose a safety-certified deep RL framework for multi-zone residential HVAC control. Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents are trained in an EnergyPlus/Sinergym simulation to minimize energy consumption while maintaining thermal comfort. Post-training safety certification is performed on the PPO policy using Lipschitz-based forward invariance analysis, building on existing tools for the computation of Lipschitz constants for neural networks, to guarantee constraint satisfaction. Both agents are evaluated over an annual simulation cycle in an eight-zone variable refrigerant flow (VRF) testbed. The PPO agent achieves 67\% comfort violation reduction compared to rule-based control, while the SAC agent achieves 27.6\% energy savings. The PPO policy satisfies formal safety certification with a margin of $2.003^\circ$C. These results demonstrate the feasibility of combining reinforcement learning with post-training safety verification for multi-zone building control.

Continual learning has traditionally treated forgetting as a failure, emphasizing preservation of previously acquired knowledge as environments evolve. We argue that this objective is incomplete for enterprise AI agents operating in non-stationary environments, where customers, policies, tools, workflows, regulations, and market conditions change over time. Indiscriminate retention can allow obsolete knowledge to influence decisions, creating negative transfer and operational risk. We therefore propose reversible forgetting: a conceptual framework with three operational memory states: active, dormant, and retired, and a reactivation transition that can restore dormant knowledge when its relevance returns. We instantiate the framework as a Hysteretic Reversible Memory Controller that accumulates relevance evidence, uses asymmetric thresholds to prevent state oscillation, tests reactivation in shadow mode, and gates retirement through policy. The framework reduces the influence of obsolete information without conflating temporary suppression with permanent erasure. Finance illustrates the idea: knowledge useful under one market regime may become harmful under another yet regain relevance when similar conditions recur.

End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded by validated physical coverage. When an unfamiliar object, sensor, embodiment, or contact falls outside that coverage and no validated fallback exists, correcting the failure requires new robot data, a policy update, and regression testing. This recurring burden is the retraining tax. Unlike text, embodied data must often be created by operating machines. We present Teach-and-Grow Learning (TGL), an agent-centered architecture for general robot learning. In its general form, a multimodal agent turns a few successful demonstrations into reusable Skill Blocks: closed-loop behaviors for meaningful subgoals. In a new scene, the agent grounds and composes these blocks, selects learned or geometric tools, observes the physical outcome, and revises the route when execution departs from intent. A Skill Library stores executable behavior, while structured Experience Memory carries forward success, failure, and repair. New tasks are acquired without task-specific policy retraining. Our LIBERO evaluation attains state-of-the-art performance; controlled studies expose skill induction, persistent reuse, and agent-directed adaptation. Finally, we propose the Teach-and-Grow scaling-law hypothesis: if X denotes effective reusable experience, future-task error and teaching demand should approach irreducible floors as power laws in X. The architecture therefore treats deployment as a period of continued learning, in which one task can make the next easier.

Active inference selects actions by minimising an expected free energy functional over predicted futures. However, adding an expectation over yet-unobserved outcomes means the free energy functional no longer has a Kullback-Leibler structure, which hinders message passing treatments of inference procedures. We propose an alternative formulation based on a Bethe free energy functional, fully supporting inference by message passing. The epistemic drive is maintained by imposing an information constraint, next to normalisation, marginalisation and form constraints, insisting that the mutual information between future observations, states and parameters given actions must be at least as large as the entropy of the goal prior. For a specific value of the corresponding Karush-Kuhn-Tucker multiplier, the stationary point of this constrained Bethe Lagrangian recovers the expected free energy solution. We show that, as the information demand is varied, the solved multiplier moves through its inactive, interior, and saturated regimes. In the inactive regime the agent's epistemic drive switches off entirely, while in the saturated regime it is maximal. We compare the performance of the constrained Bethe agent on three tasks against EFE and Q-MDP.

Symbolic planning with PDDL offers a principled framework for long-horizon robot manipulation, but constructing accurate PDDL domain and problem descriptions remains a significant bottleneck, typically requiring substantial domain expertise. We present a Vision-Language Model (VLM)-based approach called PDDL-ART, a framework that autonomously generates task-specific PDDL domain and problem descriptions from a single expert demonstration, a natural language task description, and a library of available high-level action names. PDDL-ART does not require any domain templates, action signatures, or fine-tuning. To ensure the generated descriptions are not only syntactically valid but semantically aligned with the demonstrated task, PDDL-ART introduces a multi-stage correction pipeline operating at syntactic, semantic, and execution levels. A key component of execution-guided correction is symbolic predicate grounding. Instead of relying solely on visual observations, PDDL-ART leverages the tool-use capabilities of modern VLMs to incorporate geometric and temporal reasoning for evaluating relational predicates that are not directly discernible from images alone. Critically, the model autonomously determines when to invoke these tools and how to interpret their outputs. We evaluate PDDL-ART on challenging manipulation tasks in engine maintenance and household domains, including tasks that require memory, abstract predicate inference, and goal states that are visually indistinguishable from the initial state. PDDL-ART achieves an average success rate of 93.3%, compared to 78.3% for a baseline VLM-based planner.

Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home robot "Is my medication still in the cabinet?" The answer may be physically hidden behind a row of containers that must first be moved aside. Answering such questions in real-world cluttered environments requires reasoning in dynamic scenes: distractors must be manipulated to reveal occluded objects, and each action changes the scene the model must reason over. We formalize this setting as Manipulation-Grounded Visual Question Answering (MG-VQA) and introduce PROBE, a framework for benchmarking and finetuning VLM agents on such tasks. We first develop PROBE-Sim, a high-fidelity tabletop simulator with everyday objects and a robot manipulator equipped with grasping and pushing tools. PROBE-Sim is used to create PROBE-Bench: an evaluation suite of 150 tasks across 6 question types on cluttered tabletop scenes, where a VLM perceives, picks up or pushes objects before answering. We observe consistent trend across all frontier VLMs: agentic tool-based methods outperform their perception-only baselines (8.0% on average) across all task types. We further design PROBE-Agent, a finetuning recipe to distill successful trajectories from a powerful teacher foundation model to a smaller open-weight model using a mixed data recipe that encourages manipulation-efficient question answering. PROBE Agent finetuned models outperform their off-the-shelf agent baseline (11.5% on average) and demonstrate positive transfer to unseen objects and a held-out task. We validate sim-to-real transfer by deploying PROBE-Agent finetuned policies in real-world tabletop environments.

We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in parallel and coordinate through conclusions-only shared memory, a deterministic benchmark guard, and read-only cross-agent state with plateau-triggered drafting. We evaluate \kernelarc{} on NVIDIA H100 and B200 GPUs using category-representative SOL-ExecBench workloads. The resulting implementations span custom BF16 GEMM, static cuBLASLt Expert-API configuration tables, fused mixture-of-experts backward, shape-gated decoder-layer fusion, native NVFP4 grouped-query attention, and paged prefill attention. At the public SOL-ExecBench leaderboard snapshot recorded on July~30, 2026, these submissions ranked first on representative L1, L2, Quantization, and FlashInfer tasks. The trajectories support the paper's central motivation: shared multi-agent search can broaden exploration and reach stronger incumbents within a fixed candidate budget, while the value of individual coordination features depends on the kernel and optimization stage.

A bounded agent may obtain information for a decision from its own past, from peers, or from both sources. Retaining task-relevant history can reduce later communication, while a peer message can supply what memory lacks. Under limits on both resources, how should an agent allocate its information budget? Given a fixed task and decision rule, the memory and message rate pairs attaining a performance threshold form an achievable region under specified rules for using history and peer observations. We call its efficient boundary the remembering--signaling frontier. Across conditions where history permits the same maximum reduction in task loss, we hypothesize that a bounded agent will need less peer communication when it obtains a larger loss reduction from history. In preliminary referential games, target repetition coincided with shorter successful messages, while predictability from a hidden cyclic rule did not shorten them. Experiments varying memory and message rates can estimate the frontier and test this prediction across cooperative tasks.

Visual loco-manipulation policies that can generalize to novel scenes and objects have long been a goal of robotics research. However, today's data-hungry algorithms make collecting sufficient demonstrations a struggle for tabletop manipulation, and even more so for humanoids that must also walk and balance. Learning from simulated data and transferring that behavior to the real world, as is commonly done in locomotion, sidesteps this struggle, so we replicate that recipe for loco-manipulation. In doing so, we find that cloning synthetic demonstrations results in a low performance ceiling no matter the amount of training data. Reinforcement learning breaks through it, and refining the cloned policy with Flow-GRPO on a single sparse reward yields performance that synthetic behavior cloning cannot match. Together, these stages form our end-to-end sim-to-real pipeline spanning more than 150,000 scenes, which we use to train FetchMan. We evaluate it on FetchMan-Bench, a simulation benchmark we release, and deploy it zero-shot on a real Unitree G1, where our single-object reach-and-pick policy walks to and grasps a target across unseen scenes at 73.3% success. Finally, we extend this recipe to multi-object training, a first step toward loco-manipulation generalist policies at this data scale.

Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) models increasingly master the individual skills, yet the chain still fails: errors compound beyond the policy's ability to correct, and one subtask silently constrains the next. A promising recipe freezes the VLA and puts an LLM agent in charge: it plans in language, moves in free space with analytic primitives, invokes the VLA only for contact-rich segments, and writes adaptation into language memory. Applied to long horizons, it breaks twice. (1) Competence comes from whole-task exploration at test time, whose cost is multiplicative in stages: if one stage needs T episodes, a K-stage task needs about T^K, and a failure does not reveal which stage caused it. (2) It has no representation of transitions: the VLA primitive carries an exit but no entry condition, so a subtask can succeed in a form its successor cannot use. We present BATON. Against (1), BATON makes the subtask the unit of exploration: each is explored in the cheap short-horizon regime and its solution stored in memory; a long-horizon trajectory is then composed from these solutions rather than discovered whole. Cost becomes additive (T*K) and every failure is attributed to a single stage. Against (2), BATON equips exploration with a transition-aware memory. Within a subtask, a verifier agent governs the invocation transition: the VLA is called only after the wrist view confirms the scene is ready. Across subtasks, a handoff transition restores an entry state disturbed by the predecessor's residue, and a lookahead transition selects the strategy whose outcome the successor can inherit. No parameters are updated. On the long-horizon benchmark RoboMemArena, BATON improves task success by 11.6% and cumulative success by 14.9% over the SoTA.

Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce $τ_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a trust-boundary-centric survey of foundation-model-powered embodied-agent security. Using a first-compromised-trust-boundary principle, we separate attack surface from attack mechanism and organize the system into five layers and twelve attack surfaces spanning the model supply chain, user instructions, context and memory, physical semantic environments, multimodal perception, world state, internal reasoning, task planning, action interfaces, middleware, multi-agent communication, and execution control. Based on 58 attack records and 61 defense records collected through August 15, 2026, we analyze representative attacks, cross-layer propagation, defense placement, and evaluation practices. Our quantitative analysis shows that attack research is concentrated on multimodal perception and action interfaces, while defenses are especially concentrated on action-level and runtime protection. Context and long-term memory, middleware and networking, world-state integrity, and multi-agent trust remain comparatively underexplored. We conclude with open challenges in state provenance, compositional defenses, long-horizon attack propagation, physical realizability, Byzantine multi-robot behavior, and unified closed-loop evaluation.

Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining, which throws away much of the reasoning that made the model worth reaching for. We go the other way and keep the VLM frozen. It writes the policy as a short Python control function, with no demonstrations and no fine-tuning. Writing that code once is open-loop, though. Existing closed-loop methods react at the wrong level: they retry a fixed policy or pick a different subtask, but never rewrite the code that failed. VLCP closes the loop where the failure actually lives, on the control code, within a single episode. Every $K$ steps the VLM re-observes the scene from multi-view RGB, proprioceptive state, and a state delta, then rewrites the control function from what it just saw, so a failure is caught before it compounds. We evaluate on a 57-task MuJoCo/RoboVerse sweep. This training-free policy reaches $35.1\%$ pooled success, against $3.5\%$ for the identical system queried once per episode. That tenfold gap holds with non-overlapping confidence intervals in every scene family. The gain traces to a $27.3\%$ within-episode recovery rate on failed grasps: a miss an open-loop controller would carry to the end of the episode gets re-observed and fixed at the next replan. And the loop stays cheap. A median $84\%$ of input tokens hit cache, an episode needs only about $10$ compact queries, and control blocks written during any replan persist to a cross-episode skill library reused in later prompts.

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively. Moreover, policies trained through offline behavior cloning can remain suboptimal during real-world deployment. Although online reinforcement learning can refine policies through real-world interaction, directly tuning large VLA backbones demands excessive computation and may introduce safety risks during real-robot exploration. To address these bottlenecks, we introduce HAF (Humanoid Adaptation Framework), a two-part framework consisting of HAF-VLA and HAF-Steer that transfers off-the-shelf generalist VLA foundation models to humanoid whole-body loco-manipulation. HAF-VLA is a hierarchical action-flow generator built on a pretrained flow-matching VLA. It splits full-body action denoising into three sequential stages with stage embeddings and cross-stage KV caches that retain kinematic dependencies, avoiding incoherent whole-body actions from one-shot generation. On top of the frozen HAF-VLA, HAF-Steer is a latent offline-to-online RL pipeline that leverages flow-matching invertibility and DCT-based dimensionality reduction to restrict RL optimization to a compact noise subspace and train a regularized SAC policy. This avoids updating the large VLA backbone and enables efficient real-world policy refinement. Evaluated on seven real-world humanoid loco-manipulation tasks, HAF surpasses vanilla single-stage VLA baselines and improves whole-body coordination and task performance. Project website: https://grange007.github.io/HAF .

The Central Place Foraging Algorithm (CPFA) combines site fidelity, pheromone-guided navigation, and uninformed random search to enable decentralized resource collection in robot swarms. However, CPFA often revisits previously explored regions while leaving other areas insufficiently searched, reducing efficiency as resources become scarce. In this paper, we propose Adaptive Repulsive Pheromone Clustering (ARPC), a bio-inspired method in which robots deposit repulsive pheromone waypoints to mark previously explored locations. These waypoints are clustered around the nest to estimate low-value search regions, allowing robots to be redirected toward likely unvisited areas. By integrating the exploitation of known resources with systematic avoidance of redundant exploration, ARPC improves search diversity and resource discovery efficiency. Extensive simulations in ARGoS across varying arena sizes, resource densities, and clustered, random, and power-law spatial distributions demonstrate that ARPC consistently outperforms CPFA and the Grid-Based CPFA (GPFA). In particular, ARPC yields significant gains during both early discovery (10\%) and late-stage (up to 60\%) collection, where conventional methods typically degrade. These results indicate that ARPC provides a scalable and robust strategy for large-scale heterogeneous swarm foraging environments.

Optoelectronic resistive random-access memory elements (ORRAM) are critical emerging devices that leverage photonic technologies to bring the advantages of optical programming to traditionally electronic memristive platforms for neuromorphic computing and artificial intelligence. In this work, a free-space optic micro-LED ($μ$LED) array is combined with a 2-terminal oxide semiconductor ORRAM (based on IGZO\textsubscript{Rich}/IGZO active layers), to realise parallel spatial programming of form-free memristive arrays. We report the optical and electrical programming of resistive states with potentiation/depression analysis of various stimuli parameters (pulse frequency, pulse width, pulse amplitude). Further, we demonstrate the simultaneous photonic-electronic programming of the ORRAM with optical SET (blue 450\,nm) and electrical RESET functionality. Persistent photocurrent is also observed and exploited as a pathway to fading memory or synaptic plasticity for temporal bit encoding. Finally, parallel optical $μ$LED to ORRAM channels are demonstrated to achieve the simultaneous photonic programming of multiple devices and the writing of spatial patterns across a chip of memristive IGZO devices. This work highlights the light-enabled scalability of the optoelectronic platform and the feasibility of ORRAM to interface with spatially-multiplexed optical sources to bring neuromorphic technologies directly into applications that process and sense in the optical domain.

Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making planner-visible state representations a critical security boundary. Existing attacks primarily manipulate user instructions, prompt contexts, model behavior, or perceptual inputs, while paying limited attention to whether environment-state text itself can serve as deceptive task evidence and propagate beyond planning to affect execution outcomes. Because embodied tasks are constrained by entity grounding, action preconditions, spatial relations, and environmental constraints, planning deviation alone does not guarantee adversarial execution. To address this gap, we investigate environment-state text as an independent attack surface and present the first closed-loop Environment State-Text Injection (ESTI) attack for LLM-driven embodied agents. Without modifying the original user instruction, model parameters, or executor, ESTI reformulates an adversarial objective as false state evidence compatible with the current environment and influences planning and execution through object properties, spatial relations, affordances, task-stage rules, and execution feedback. We further develop ESTI-Bench to evaluate attack propagation across the planning-to-execution closed loop and compare ESTI with Vanilla IPI, EIRAD, and BADROBOT across ProgPrompt/VirtualHome, VoxPoser/RLBench, and AI2-THOR/iTHOR. ESTI consistently outperforms existing baselines, improving planning-level and execution-level attack success rates by up to 89.32\% and 43.69\%, respectively. Further analysis shows that grounding, consistency, and executability jointly determine whether manipulated state evidence can propagate through the embodied closed loop and produce verifiable environmental changes.

Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that factors long-horizon household tasks into task-directed visual exploration and constrained symbolic planning. In the first phase, a vision-language model and exploration harness acquire goal-relevant predicates and instance bindings from egocentric observations and grounded interactions, producing a symbolic initial state. In the second, a PDDL transition model restricts decoding to tokens that extend applicable actions. Monte Carlo tree search then evaluates executable continuations using a domain-independent planning heuristic. The resulting plans are executable by construction under the transition model, with transfer to the environment conditioned on correct visual grounding. On VirtualHome and ALFWorld, open 4B-27B models exceed 90% success in both environments, and our smallest agent substantially outperforms a 27B direct visual policy in each. Constraints and search prove complementary rather than interchangeable: in ALFWorld either alone solves under a third of tasks, whereas their combination solves over 95%. The method also uses several times fewer generated tokens than extended thinking and far fewer model-visible images than direct interaction, and residual failures localize to state acquisition rather than plan generation without any specialized training.

Long-term manipulation planning requires robots to reason not only about immediate task success but also about how current decisions affect future interactions with the environment. In this context, household service robots may need to organize groceries in partially occupied shelves while using limited storage space efficiently and preserving access for subsequent placements. In this paper, we consider an online multi-object shelf-placement setting in which future objects arrivals are unknown. Existing approaches do not jointly address semantic organization, dense space utilization, and manipulator accessibility during sequential shelf filling. To address this gap, we propose Semantic-Dense Placement Planning (SDPP), an accessibility-preserving approach that ranks candidate poses using a semantic-density score combining inter-object semantic similarity with spatial proximity. An Accessibility Map (AM) further filters candidates unlikely to be reachable before motion planning and penalizes placements that reduce the remaining accessible workspace. Simulation experiments show that SDPP significantly improves semantic placement quality over state-of-the-art baselines and achieves the highest average shelf density, while the AM substantially reduces the time required to identify feasible placement poses. A qualitative real-world experiment demonstrates the applicability of our pipeline in a domestic shelf-storage scenario.

Designing large soft robots capable of generating high forces for physical human-robot interaction remains a significant challenge in soft robotics. Prior work in large soft robots has focused on proof-of-concept prototypes, and no systematic framework exists for determining the suitability of a design paradigm for a desired task. This manuscript introduces a method for optimizing the geometry of a soft robot limb, maximizing its blocking force subject to an anti-bucking constraint under its own gravitational loading. We demonstrate that an explicit solution exists to the proposed optimization problem under certain assumptions. Experiments with three geometries of a large, soft, pneumatically-actuated manipulator demonstrate that the method correctly predicts which designs meet constraints and which produces the largest end-effector forces. This method, with its closed-form solution, can allow designers to determine a-priori if an intended class of soft manipulators is an appropriate choice for physical interaction at large size scales.

In-context imitation learning enables few-shot policy generalization but struggles to maintain performance on unseen objects and novel scenarios. To address this, we introduce MatchingPolicy, a correspondence-driven framework that explicitly decouples demonstration-to-scene matching from policy learning. Central to our method is a correspondence-aware diffusion policy that conditions robotic actions directly on dense semantic correspondences. This architectural separation resolves the inherent conflict between correspondence identification and action adaptation, enabling robust out-of-distribution transfer. Our framework integrates vision foundation models with a novel two-stage matching algorithm to dynamically establish reliable correspondences. Extensive evaluations on RLBench and real-world manipulation tasks confirm that MatchingPolicy achieves superior few-shot performance, generalizing reliably across unseen object instances and semantic categories.

Underactuated tendon-driven hands offer compact actuation and passive compliance, but tendon elongation under restoring-spring loading introduces configuration-dependent joint deviations. This paper presents H-PAC, a modular 6-actuator, 15-DoF robotic hand with a control-oriented modeling and implementation framework. A sparse analytical actuator-joint model is derived from the tendon-routing geometry, and a mechanics-based compensation model is developed to account for tendon-elasticity-induced joint errors. The proposed method is implemented in a hierarchical architecture: a host computer performs workspace-constrained posture mapping and compensation, while an ESP32 generates synchronized commands for six position-controlled servos. The same control parameters and execution strategy are used across all tasks without task-specific retuning. Monotonic servo-sweep experiments show that the compensation substantially improves joint-angle prediction. The MAE of the index DIP joint decreases from 1.15 degrees to 0.18 degrees, and all nine evaluated joints achieve an MAE below 0.23 degrees. Representative postures and grasping configurations are further executed using the same control pipeline without external joint or force sensing in the control loop. The results demonstrate a practical approach to improving posture reproducibility in compact underactuated robotic end-effectors.

Empathetic social robots should respond not only to what users say, but also to how their emotions dynamically evolve during interaction. However, existing empathetic dialogue systems are often text-centered and primarily model empathy as a one-way mapping from the user's emotion to the system response, limiting their ability to capture embodied speaker--listener affective exchange. We present AffectLoop, a multimodal speaker-listener emotion-dynamics-aware spoken dialogue system implemented on the Misty II robot. The system tracks the speaker's verbal and facial affective dynamics, estimates the robot listener's own verbal and behavioral affective state, and conditions LLM-based response generation on both affective streams. The robot then generates a short spoken empathetic response together with emotionally congruent embodied behavior, forming a closed speaker--listener affective loop. We evaluate the system in a pilot within-subject study with five participants, comparing it with an otherwise identical utterance-conditioned baseline that omits the speaker- and listener-affective-state inputs. The proposed system received higher overall impression ratings, especially for empathetic response and user satisfaction. Post-hoc log analysis further showed higher speaker-listener affective alignment and stronger valence-based distress recovery. These preliminary results suggest that explicitly modeling both speaker emotional dynamics and listener affective state can improve embodied empathetic interaction.

Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length inputs and post-hoc refinement, hindering online-oriented localization under partial or dynamic observations. In this work, we formulate Progressive Cross-view Video Geo-localization (PCVG) as a deployment-oriented extension and evaluation protocol of CVG, enabling localization under varying temporal budgets, prefix-based inference, random-start evaluation, and long-range localization with interruptions. To explore PCVG, we introduce X$^2$Localizer, a cross-grained alignment framework that jointly supervises global prefix-to-aerial retrieval and token-aggregated frame--aerial-tile matching with a budget-dependent asymmetric objective. Furthermore, we introduce a Sliding-Window Re-Localization (SWRL) strategy that dynamically refreshes candidate regions for failure recovery and long-range deployment without full-sequence reprocessing. Extensive experiments show that X$^2$Localizer preserves conventional full-video performance, with marginal gains of +0.1 Recall@1 and +0.3 Recall@10, while substantially improving early localization. In the challenging single-frame setting, X$^2$Localizer improves coarse retrieval by +4.7 Recall@1 and +11.5 Recall@10 over the previous state-of-the-art method. With SWRL, our approach further enables robust progressive localization under random-start and long-distance scenarios, narrowing the gap between benchmark evaluation and real-world deployment.

Satellite agents for on-orbit navigation tasks need to predict collision risks using limited onboard observations. However, conventional planners often rely on predefined maps and fixed environmental assumptions, limiting their adaptability in dynamic on-orbit scenarios. In this paper, we propose Orbit-Planner, a two-stage latent world model for on-orbit obstacle avoidance. Orbit-Planner learns action-conditioned spacecraft dynamics to perform future-state rollouts in latent space, and introduces a Physics Probe to decode physical state changes from imagined latent trajectories. Experiments demonstrate that Orbit-Planner can perform long-horizon latent rollouts and recover physical states from imagined trajectories. In closed-loop obstacle-avoidance navigation in Isaac Sim, it attains a success rate of 91.7%. Code is available at https://github.com/ZhijianLi2003/Orbit_Planner.

Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind idea-recovery benchmark that withholds the seed paper and all contemporaneous or future literature, and asks models to propose hypotheses that an independent large language model judge matches against the held-out ground-truth idea. A strict anti-leakage protocol-temporal citation cutoff, anonymous reference IDs, and frozen per-paper bibliographies, which prevents prompt-time leakage of the seed idea. Across six scientific domains and 643 evaluated papers, seven frontier models achieve only modest Match rates (approx. 3-15%). We then evaluate a reference-only multi-agent (top 4) pipeline that combines cross-model review with a Swiss tournament over aligned hypothesis slots, without external web search. Cross-model review plus tournament selection raises Match rates to approx. 23-42% across all six domains, which is an observed approx. 2.4x lift over the best single-model baseline. This draft reports the protocol, anti-leakage design, and current results as an arXiv timestamp.

Accurate throwing of the American football requires precise regulation of release conditions, where coupled linear and angular momentum determine flight stability and targeting accuracy. While prior work on robotic object throwing has largely focused on generating dynamically feasible release velocities using open-gripper paradigms, explicit control of spin injection at detachment remains underexplored, particularly for aerodynamically anisotropic objects like the American football. In this paper, we present the spin-stabilized controlled tight spiral throw of an American football by a humanoid robot. Achieving this requires (i) accurately reaching the desired coupled momentum, which often involves high degrees-of-freedom (DoF) movements completed within approximately half a second, and (ii) managing the complex transient contact dynamics that arise during the sub-100-millisecond release phase, when the football is effectively underactuated as it moves partially across the fingers. To this end, we develop a coupled whole-body control strategy where the lower body is performing informed stabilization while the upper body is further divided into two phases with (i) a throw phase accelerating the football to a target state through trajectory optimization and tracking, and (ii) a follow-through phase utilizing model predictive control to actively control the wrist and remaining in-contact fingers. The proposed framework is empirically validated on a 29-DoF Unitree G1 humanoid equipped with a 7-DoF Dex3-1 three-fingered gripper. The thrown American football reaches up to 93.6% spin efficiency and a 0.286 radians linear-velocity-to-nose-alignment (nose-angle) error (where an ``ideal'' tight spiral corresponds to 100 % spin efficiency and 0 radians nose-angle error) at up to a 5.35 m/s linear velocity and an angular velocity of 14.5 rad/s.

Vision-based Unmanned Aerial Vehicles (UAVs) often suffer from navigation failures in dead ends due to limited sensing accuracy and range. To address this challenge, this paper proposes a systematic solution for efficient dead-end prediction and avoidance. The proposed method introduces a lightweight neural network to predict the relative distance and bearing of potential dead ends within the current field of view using RGB-D inputs. These predictions prune a predefined, compact trajectory library, enabling the planner to proactively avoid dead ends while maintaining navigational smoothness. Notably, our approach transfers across real-world scenarios without manual annotation or fine-tuning on real-world data. The system achieves high-frequency replanning at 50 Hz onboard. Extensive simulation benchmarks demonstrate superior performance in success rate, flight time, and trajectory length, and real-world experiments further validate its effectiveness in complex scenarios.

High-resolution three-dimensional (3D) nanostructures for visible-light photon manipulation provide unique and bespoke capabilities in optics and photonics. However subwavelength nanofabrication and reliable ensemble manipulation of the 3D prints onto arbitrary substrates remain challenging. Here, we introduce sublime transfer strategy tailored for transfer printing ensembles of delicate 3D printed nanostructures. This strategy enables conformal, damage-free integration of arrays of 3D structures on diverse substrates. Naphthalene acts as a transient stamp to encapsulate the structures during transfer and placement. We rely on the low sublimation temperature of naphthalene to release the structures reliably with nearly zero stress, preventing mechanical damage and positional misalignment. This approach is broadly applicable to integrate diverse nanostructures and photonic devices onto various substrates, and enabling inorganic architectures through ensemble uniform post-processing, including 2.5D photonic crystals on flexible PDMS, diffractive optical elements on curved lenses, spiral phase plates on CMOS chips, multilayer achromatic metalens on optical fiber facet, as well as 3D glass photonic crystals and optical topological resonators on anti-stiction quartz.

Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the agentic path has not realized closed-loop learning in physical execution: existing harnesses remain largely open-loop, following fixed skills during rollout and reflecting only after an episode completes. Such post-hoc reflection cannot govern execution as it unfolds, because physical interaction requires decisions to track rapidly changing robot-environment states at a frequency beyond today's large agentic models. We present Zetta, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Through three timescale-separated loops, Zetta provides action-frequency governance, rollout-level critic-recovery proposal, and validation-gated skill updates. Together with Z-Infra, a rollout infrastructure decoupling agent logic from heterogeneous execution resources, Zetta achieves state-of-the-art success on LIBERO-Pro and RoboCasa under our current rollout budget, reaching 90.8% and 93.6%, with an 11.1x inference speedup; success continues to scale with self-exploration experience; learned skills transfer zero-shot, and clear robotic "Aha Moments" emerge. These results show that closed-loop harness self-evolution opens a scaling path for reliable physical intelligence.

AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.

Learning from demonstration is a promising approach for dexterous manipulation, but collecting high-quality contact-critical demonstrations remains difficult with low-cost teleoperation hardware. We present ViHaTeleop, a lightweight (0.7 kg), low-cost (\$550) visual-haptic teleoperation system with SLAM-based wrist tracking, camera-based hand tracking, and finger-wise vibrotactile feedback through Linear Resonant Actuators (LRA). The system includes several design choices (LED illumination, fisheye hand camera, and tactile-aware retargeting constraints) and is deployed on Franka + LEAP Hand + 9DTact in both real and simulated environments. Under matched with/without-haptic conditions with nine participants across six contact-critical tasks, haptics improved success rates across all tasks (+2.2 to +15.6 percentage points), while completion-time effects were task-dependent. Subjective ratings showed significant gains in contact clarity and grasp confidence in both simulation and real-world settings (Wilcoxon signed-rank, $p<0.05$). We also integrate a lightweight depth-camera-based tactile proxy in Isaac Sim, enabling a full pipeline from multi-modal demonstration collection to visual-tactile policy training. Preliminary downstream validation by training visual-tactile policies from collected demonstrations shows tactile cues benefit contact-critical subtasks (peg-in-hole: +17 percentage points over vision-only).

Recent advances in AI technologies have enabled the advanced design of complex control policies. In contrast, focusing on the body, many robots still employ simple bodies that can limit adaptability to environments. Studies in embodied robotics have shown that well-designed bodies can partially replace the role of control and computation with physical body-environment interactions, yet such designs still depend heavily on expert intuition. There is a need for a systematic theoretical framework for body design, as well as a method for joint optimization of the body and controller. To address this, we introduce the Embodied Perceptron, a theoretical framework that unifies neural networks and physical body systems. In this view, the body itself acts as a perceptron: mechanical parameters correspond to weights, and physical nonlinearities play the role of activation functions. By representing physical constraints as weights and nonlinear properties as activation functions, a physical body can be modeled in neural-network form. The system representation enables us to explicitly and theoretically explain that the body can substitute for part of the neural control. As an application, we co-optimize control policy and muscle configuration in a musculoskeletal robot and show that the resulting embodied intelligence can provide inherent stability, improve learning efficiency, and drastically reduce model size-even with a single-neuron controller. The results bridge the informational and physical worlds and provide a pathway toward understanding and systematic design of embodied AI systems.

Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-evolution methods primarily revise skills using execution trajectories collected from current tasks, leaving the evolution knowledge accumulated in public skill version histories largely untapped. Our pilot study reveals a clear complementarity between the two sources: public skill changes provide reusable evolution priors, whereas trajectories provide evidence grounded in the current task. Motivated by this, we propose VCE-Skill, which distills noisy and implementation-specific public skill changes into reusable, structured version-change experience and adaptively fuses it with trajectory-derived proposals from the base evolver, thereby exploiting external experience while retaining task-specific evidence. Extensive experiments demonstrate that VCE-Skill improves skill self-evolution, increasing mean scores by 3.20--4.98 points; transfer experiments further show that the resulting skills achieve stronger cross-model transfer performance. Our work highlights public skill version changes as a previously underexplored yet effective source of prior knowledge and advances trajectory-driven skill self-evolution.

Real-world deployment of Vision-Language-Action (VLA) models is often bottlenecked by efficiency-performance trade-offs, cross-embodiment generalization, and execution smoothness. We present NebulaVLA, an asynchronous dual-frequency architecture that decouples high-level semantic reasoning from low-level action control, optimizing computational resources and modularity. To bridge semantic gaps across heterogeneous robots, we introduce GESTURE-7, a unified language-grounded action representation. Furthermore, our Guide Action algorithm enforces kinematic continuity via mask-based smoothness constraints. Comprehensive evaluations demonstrate that NebulaVLA significantly outperforms synchronous baselines, achieving an 85.5\% average success rate on LIBERO-Plus and accelerating action generation by \textasciitilde 2.7$\times$. This asynchronous design enables highly efficient and responsive control for practical robotics.

Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tight frame budgets, such geometry-driven strategies may prioritize global scene coverage while leaving partially observed objects incompletely reconstructed. To address this limitation, we propose OccamView, an object-conditioned view-selection framework for frame-budgeted active 3D Gaussian reconstruction. Rather than predicting unseen object geometry or performing shape completion, OccamView maintains an online object memory from open-vocabulary detections grounded in measured RGB-D observations and represents unresolved local occupancy around detected objects as conservative hidden-region proxies. Candidate viewpoints are then evaluated using an occlusion-aware proxy-coverage score. Furthermore, we introduce a Geo-Floor mechanism that restricts object-conditioned re-ranking to geometrically competitive candidates, allowing object-conditioned cues to guide complementary observations while preserving the geometry-driven exploration behavior of the underlying planner. Experiments on Replica and Matterport3D under a unified frame-budgeted protocol show that OccamView consistently reduces Completion and improves Completion Ratio across five frame budgets, with particularly pronounced gains under limited frame budgets. These results demonstrate that lightweight object-conditioned cues effectively complement geometry-driven active view planning.

Modern power systems face growing operational complexity driven by the integration of renewable energy sources, decentralization, and the need for real-time decision-making across a wide range of timescales. Addressing these challenges traditionally relies on model-based methods that, while accurate, can be too slow for operational demands. Machine learning (ML) has therefore emerged as a faster, data-driven alternative. As grid topology plays a central role in power system operation, graph machine learning (GML) methods offer a natural framework for incorporating topological dependencies as an inductive bias. We survey nearly 800 papers at the intersection of GML and power systems, covering forecasting, state estimation, optimization, control, fault diagnosis, and cybersecurity. Power systems constitute an unusually rich benchmark setting for GML, as they combine hard physical constraints, multi-scale dynamics, safety-critical requirements, and scarce labeled data within a single, well-defined domain. Conversely, power systems can benefit from utilizing GML to complement classical solvers, as GML provide scalable, topology-aware approximations with promising generalization and computational efficiency. We identify open challenges, including limited real-world deployment and the need for interpretable models in safety-critical settings. Despite the rapidly growing number of publications, standardized benchmarks and open datasets remain scarce, leaving many results difficult to reproduce and undermining the long-term scientific credibility of the field. We further derive a structured requirements catalog for ML-ready power grid benchmarks, intended to guide future dataset development and improve reproducibility across studies. We call on the community to prioritize dedicated benchmark studies and the release of open datasets and models.

Autonomous agents share a transport and can call each other's tools, but they cannot share what they know: no protocol lets two agents' memories reconcile a fact phrased two ways, link related facts held apart, or reconcile contradictory knowledge without silently discarding either claim. We present MELD, a self-managing coherence mechanism for a federation of agent memories whose run-time model is the knowledge graph itself. Each brain admits every incoming claim through a five-outcome procedure (insert, merge, relate, conflict, or reject), decided from three signals (scoped claim-key identity, embedding similarity, and a natural-language-inference verdict) under context and freshness gates, and acting through exactly one auditable, authenticated Patch, the only object that mutates state. A binding onto standard publish/subscribe transport with a per-claim status CRDT keeps sovereign brains coherent in claim status without a coordinator: self-healing after partitions and under lossy routing, and self-protecting against silent rewrite by a peer, under a benign-fault model. MELD does not adjudicate truth; a detected contradiction is preserved for later adjudication, never silently resolved. On HotpotQA distractor, distributed merge is recall-non-inferior to a centralized store under a pre-specified equivalence test and recall-superior to naive union at about 11% less live storage; the merge classifier separates at AUC 0.968 with a 0.013 false-merge rate on adjudicated candidate pairs; the status CRDT reconverges in 30/30 real partition-heal trials where last-writer-wins manages 11/30; and semantic routing delivers about 3x fewer messages at matched recall. We evaluate on a real computing continuum spanning an operator-grade 5G edge, national HPC, and a local tier, with empirically calibrated thresholds.

Shared autonomy requires principled mechanisms for allocating and transferring control between a human and an autonomous agent. Existing approaches often rely on blending control inputs or heuristic switching rules, which lack theoretical guarantees and fail to account for the dynamics of authority transfer. This paper develops a cooperative game-theoretic framework for authority switching in shared autonomy. We formulate the control switching problem as an identical-interest dynamic game in which authority transitions are embedded into the system dynamics, yielding optimal switching policies rather than ad hoc rules. We establish the existence and characterization of team-optimal policies in pure strategies under stochastic human override, accounting for asymmetric authority where humans retain override capability. For linear-quadratic systems, we derive closed-form recursions for the optimal switching policies and value functions, enabling efficient computation independent of the continuous state. We validate the framework on scalar and multi-dimensional linear systems, demonstrating how optimal switching adapts to varying system dynamics, cost structures, and override probabilities. The results reveal fundamental trade-offs between human adaptability and autonomous efficiency, illustrating the practical benefits of grounding shared autonomy in cooperative game theory.

Shared autonomy requires principled mechanisms for allocating and transferring control between a human and an autonomous agent. Existing approaches often rely on blending control inputs or heuristic switching rules, which lack theoretical guarantees and fail to account for the dynamics of authority transfer. This paper develops a cooperative game-theoretic framework for authority switching in shared autonomy. We formulate the control switching problem as an identical-interest dynamic game in which authority transitions are embedded into the system dynamics, yielding optimal switching policies rather than ad hoc rules. We establish the existence and characterization of team-optimal policies in pure strategies under stochastic human override, accounting for asymmetric authority where humans retain override capability. For linear-quadratic systems, we derive closed-form recursions for the optimal switching policies and value functions, enabling efficient computation independent of the continuous state. We validate the framework on scalar and multi-dimensional linear systems, demonstrating how optimal switching adapts to varying system dynamics, cost structures, and override probabilities. The results reveal fundamental trade-offs between human adaptability and autonomous efficiency, illustrating the practical benefits of grounding shared autonomy in cooperative game theory.

Differentiable nonlinear model predictive control (NMPC) provides a principled way to embed optimal control structure into end-to-end learning paradigms, but its practical use is often limited by the computational and memory costs of both forward optimization and backward sensitivity propagation. This brief proposes PANDA, a matrix-free solver for differentiable NMPC. In the forward pass, PANDA combines proximal-gradient iterations with quasi-Newton acceleration and introduces an adaptive stepsize enlargement mechanism to mitigate the conservativeness of monotone stepsize reduction. The resulting stepsize behavior and its effect on local convergence are theoretically analyzed. In the backward pass, PANDA performs implicit differentiation from the residual equation and computes adjoint sensitivities using Krylov-subspace iterative methods together with automatic-differentiation-based Matrix-Vector product operators, thereby avoiding explicit Hessian and Jacobian construction. The method is evaluated on a nonconvex trailer NMPC problem embedded in an imitation learning task. The results show that PANDA achieves much faster forward and backward computation and lower memory overhead than representative differentiable optimization solvers, while maintaining effective imitation learning performance.

Surface acoustic wave (SAW) micromanipulation enables the precise, non-contact handling of microscale particles and has attracted considerable interest in microfluidics and biomedicine. However, conventional SAW platforms generally rely on simple interference fields which are susceptible to fabrication imperfections and environmental perturbations, resulting in limited trapping stability. Here, we develop a SAW-based acoustofluidic platform that generates an acoustic skyrmion lattice through the coherent interference of three SAWs. The topologically structured field provides robust phase singularities and a stable gradient-force landscape, enabling microparticles to be localized at predefined lattice sites and supporting controllable rotational manipulation. Independent modulation of the amplitude and phase of the electrical inputs allows the field strength to be tuned for particles of different sizes. Numerical simulations and proof-of-concept experiments confirm particle trapping and ordered lattice assembly in the acoustic skyrmion field, demonstrating the feasibility of translating topological acoustic textures into practical on-chip manipulation functions. This reconfigurable strategy offers a route to robust SAW manipulation and may support applications in single-cell analysis, three-dimensional cell assembly, high-throughput screening, and microscale and nanoscale device assembly.

Valley photonic crystals enable valley-dependent transport and chirality-selective emission, but incorporating wavelength-scale localization remains challenging. Existing valley-photonic-crystal cavities rely on finite defects or local lattice modifications that require structure-specific optimization and offer limited continuous control. Here, we theoretically and experimentally demonstrate two-dimensional nanocavity confinement using two orthogonal domain walls in a glide-symmetric valley photonic crystal. A valley domain wall confines the guided interface mode transversely, while an SSH-like domain wall localizes it longitudinally. Starting from a glide-symmetry-protected Dirac point in a bearded-interface waveguide, controlled displacements of adjacent triangular holes open a topological gap in the continuous guided-mode dispersion. The displacement amplitude $ΔR$ tunes the gap, mode volume, and intrinsic radiative $Q$ factor. Implemented in a silicon photonic-crystal slab, the structure exhibits localized resonances within the topological mode gap and systematic spectral tuning with $ΔR$. The maximum measured loaded $Q$ factor is $1.2\times10^{4}$. This approach enables continuously tunable, high-$Q$ nanocavities integrated into topological waveguide networks for compact resonant devices and enhanced light--matter interactions.

Electric vehicles (EVs) represent a critical intelligent terminal within the Internet of Things (IoT). Despite the year-on-year growth in EV penetration, the highway driving experience still requires improvement. Accurate prediction of EV highway charging behavior is crucial to addressing this issue. This paper introduces a novel bounded rationality framework to analyze highway charging decisions. Specifically, we utilize prospect theory to capture the tendency of drivers to reserve more electricity than theoretically necessary. We then propose a Bayesian game in which EV drivers, unaware of others' decisions, aim to minimize costs, including range anxiety, charging fees, and queuing time. To gain insights into the game, we prove the existence and uniqueness of the Bayesian Nash Equilibrium in two practical scenarios. Our numerical experiments, based on real-life data, demonstrate that drivers' risk aversion tendency significantly influence EV charging decisions, charging demand, queuing lengths at charging stations, and the departure rate on the highway network. Furthermore, our strategy reduces cumulative EV cost and CSs' charging costs compared to other benchmarks.

Semiconductor quantum-device design still lacks an integrated Technology Computer-Aided Design (TCAD)-like environment that connects material geometry, quantum many-body simulation, and automated design. Here we introduce zenDot, a large-language model (LLM)-integrated quantum TCAD platform that links a material-labelled device state to a unified condensed-matter physics toolbox. The device and calculation components are integrated into a desktop workbench, Python API, and an embedded LLM agent, allowing electrostatics, charge and transport characterization, correlated-state calculations, and qubit modelling to be executed within one reproducible environment. We demonstrate zenDot on a Si/SiO2 double quantum dot, where a single device state reproduces the characterization workflow and supports hybrid, tunnel-charge, and singlet-triplet qubit analyses. A platform-level universal-control scan revises the singlet-triplet operating point and reduces the predicted worst-gate infidelity by nearly 30-fold. Beyond analysis, the LLM agent directly operates the same physics environment as human users, proposing design changes, executing registered simulations, and iterating on solver-returned metrics under physics-aware validation. Across three demonstration tasks it completes 18 validated design iterations, including geometry modification followed by a full re-solve from the material stack. zenDot establishes a machine-operable quantum TCAD workflow that connects device physics with LLM-driven design exploration.

There has been a flurry of activity in the development of robotic systems to localize and track underwater man-made or natural targets based on sparse acoustic data. Compelling examples include the development of surface tracking systems to aid in the navigation of groups of underwater vehicles performing environmental monitoring missions or to study the motion patterns of large underwater fauna. With current technology, the latter case can only be tackled using Time-Difference-of-Arrival (TDoA) techniques. Recent progress in nonlinear state estimation indicates that optimization-based methods may overcome the limitations of classical recursive filtering. However, achieving reliable estimator performance in the case of nonlinear target dynamics and sparse measurements remains a key challenge. In this paper, we study a Moving Horizon Estimation (MHE) approach to TDoA-based underwater target tracking. Through a 2D simulation environment capturing typical marine conditions, we show that the MHE-based estimator maintains reliable tracking in the considered scenarios even when the classical EKF becomes unreliable. The results highlight that multi-step trajectory coupling and physically consistent constraints, which are key advantages of the MHE approach, significantly enhance estimator robustness. It is shown that the MHE approach offers promise as a practical and scalable building block for future multi-agent tracking systems based on TDoA measurements operating in real underwater missions.

Modern power systems and smart grids are often composed of fragmented and heterogeneous data silos, which lack the cohesion needed for effective cross-domain analysis. For this, this paper introduces a universal ontology framework for the operational representation of intelligent cyber-physical power systems via a unified knowledge graph and an ontology capable of cross-domain reasoning. This work focuses on bridging cyber-physical simulators as a stepping stone towards that vision. By establishing a unified semantic middleware grounded in IEC 61970 (CIM) and IEC 62351/61850 standards, this framework integrates disparate cyber and physical simulation environments, illustrated via OMNeT++ and PowerWorld, into a single knowledge graph. Evaluation across three standard power system benchmarks demonstrates sub-linear scaling in both knowledge graph size and construction time. We further validate the framework's efficacy for real-time decision support, achieving millisecond-level query performance across both domains, maintained across six cumulative structural mutations to the knowledge graph. The resulting unified knowledge graph provides a robust, scalable information corpus for autonomous smart grid operations, enabling complex analysis of real-world power systems.

Functional electro-optic (EO) tunable photonic integrated circuits are crucial to next-generation information processing and advanced computing, where ferroelectric materials such as lithium niobate (LiNbO3) provide outstanding optical properties and versatile tuning mechanisms. However, beyond achieving high-performance devices, practical deployment of LiNbO3 photonic integrated circuits requires rapid and cost-effective scale-up, which remains challenging because of the fabrication complexity and high costs of ion-sliced thin-film lithium niobate and wafer bonding processes. To address this gap, we demonstrate a fully monolithic photonic platform, amorphous silicon carbide (a-SiC) on bulk LiNbO3 crystal substrate, enabling scalable, CMOS-compatible, low-cost, and high-density photonic integrated circuits without relying on thin-film LiNbO3. This integration approach breaks the long-standing cost-performance-scalability tradeoff, and intrinsically eliminates the need for sophisticated fabrication processes, including ion slicing, wafer bonding, and LiNbO3 etching. It realizes high-density, low-loss, and record high EO tuning efficiency of VpiL = 2.87 Vcm on bulk LiNbO3 crystal substrate. Furthermore, leveraging slow-light effect near photonic crystal bandgap, an 8.5-fold EO tuning efficiency enhancement is achieved, highlighting the platform's capability in confinement control and dispersion engineering.

Post-disaster damage to terrestrial infrastructure can disrupt wireless coverage,while Uncrewed Aerial Vehicle (UAV) swarms provide a promising solution for rapid restoration.However, due to the limitations in local geometry observations hidden radio impact,and inter-UAV communication,there exists a significant gap between locally visible movement choices and swarm-level coverage outcomes.To combat this gap,we propose a raido World-model-based Optimized Negotiation framework for Distributed UAV covERage (WONDER).Particularly, to tackle the unavailability of the future radio field from onboard observations, WONDER uses a Joint-Embedding Predictive Architecture (JEPA)-based radio world model to learn and predict the incremental radio effect of each candidate trajectory from deployment-available information.Multi-round negotiation in WONDER then coordinates ranked proposals by committing one trajectory at a time and re-evaluating the remaining proposals under the updated context. Our theoretical analyses further validate the effectiveness of such a world model-based framework. WONDER also adopts a Proximal Policy Optimization (PPO)-style Actor and alternates between updating the world model and the actor. Furthermore,we build RadioDynamics,a comprehensive simulation environment that integrates UAV mobility,radio propagation, inter-UAV communication modeling,and digital-twin geometry with ray-traced fields in $62$ metropolitan scenes.Experiments on $11$ testing scenes in RadioDynamics show that WONDER achieves the highest balanced score among seven evaluated methods,reaching $0.870$ with a $0.162$ coverage advantage over STACCA, while maintaining $100\%$ connectivity between UAVs.

What happens when you teach an LLM-based agent the scientific method? Motivation: Scientific discovery emerges from cycles of hypothesis, implementation, empirical testing, and feedback. Can this process be automated? We approach automated algorithm design through the lens of the scientific method, where an LLM-based agent goes through each step of the process in an ordered, iterative fashion. Results: We present The Little Scientist, a framework in which a "Scientist agent" works inside an evaluation environment that benchmarks its code and returns structured per-instance diagnostics. When the Scientist plateaus at a local optimum, a "Kuhn agent" injects a paradigm-shifting conjecture paired with a cross-disciplinary inspiration, forcing exploration of a different region of the LLM's latent space. We demonstrate the framework on two problems that require fundamentally different modes of discovery. For protein fitness prediction, the Scientist discovered Delta V, an ensemble calibration strategy that ranks first on the ProteinGym DMS Substitutions Zero-Shot leaderboard across all five official evaluation metrics, exceeding the #2 model (VenusREM) by +0.033 mean Spearman correlation across 217 DMS assays. For DNA motif discovery, the Scientist wrote an algorithm from scratch--DALE (Dual-seed Algorithm for Latent Enumeration)--that outperforms STREME (the default in the MEME Suite) across 132 ENCODE transcription factors (mean AUROC 0.842 vs. 0.803, Wilcoxon p < 10^{-6}) while running 11x faster. This demonstrates that the framework can produce genuinely novel algorithms, not just optimize existing components. Together, these results show that an LLM agent stepping through the scientific method can discover both new algorithms and new ensemble strategies that outperform prior solutions. The entire research program consumed 704M tokens on a single virtual machine with no GPUs

The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and supporting increasingly complex clinical decision-making. However, the deployment of these systems in real-world healthcare settings raises critical ethical concerns related to safety, fairness, accountability, transparency, and patient trust. While numerous organizations, including the World Health Organization, the National Academy of Medicine, and the FUTURE-AI consortium, have proposed ethical frameworks and governance principles for healthcare AI, these efforts remain largely conceptual. To address this challenge, we present ETHOS (Ethics and Trust through Hierarchical Oversight System), a modular ethics framework designed as a governance meta-agent that can be integrated with any existing multi-agent system without requiring changes to its underlying architecture. ETHOS translates stakeholder-informed ethical requirements into executable runtime oversight through a layered governance approach consisting of deterministic checks, contextual reviews, and a final ethics critic. These components continuously evaluate intermediate reasoning steps and final outputs, enabling the system to identify ethical risks, request revisions, or suppress responses that fail predefined safety and trustworthiness criteria. We demonstrate ETHOS within a hepatology clinical decision-support MAS. Results show that ETHOS improves decision reliability by detecting incomplete, inconsistent, or out-of-scope evidence and appropriately increasing abstention when safe recommendations cannot be supported. By embedding ethical governance directly into system operation, ETHOS provides a practical and auditable mechanism for transforming high-level AI ethics principles into deployable safeguards.