Physical AI Brief

We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data sources and video backbones is challenging: datasets differ in temporal scale, camera geometry, visual quality, motion, and captioning styles, while video generators use distinct representations and architectures. Naive data mixing and model-specific implementations therefore produce inconsistent supervision and make results difficult to reproduce and compare. SolarWM addresses this coupling with a reconfigurable multi-source data engine and a backbone-native adaptation framework. The engine converts 1.43 million canonical clips from 10 datasets into a unified, frame-aligned contract covering visual observations, metric camera geometry, captions, quality metadata, selection decisions, and provenance, while decoupling source processing from mixture construction. Under shared camera-conditioning, training, and inference interfaces, we instantiate four 5B--33B models based on Wan2.2, LTX-2.5, and MiniMax-H3 while preserving their native representations and objectives. A unified three-stage recipe combines bidirectional adaptation, teacher-forced autoregressive initialization, and distribution matching distillation. The resulting causal models enable real-time interaction over rollouts ranging from minutes to hours after being trained on only 5s sequences. By releasing the resulting data, pipeline, recipes, weights, and framework, SolarWM provides a reproducible and extensible foundation for interactive world-model research.

Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM). These world models are typically trained via supervised next-state prediction to generate fixed representations like HTML or AXTree snapshots. However, this objective is misaligned with the downstream ranker, which relies on predicted states being discriminative across candidates to accurately score them. To address this, we introduce predicted-state matching, a training objective where the predicted representation must distinguish the true resulting state from those reached by alternative actions. We train these models using a branching web-agent dataset derived from WebArena Go-Browse trajectories, where every decision point contains multiple alternative actions and their resulting states. Experiments on our held-out predicted-state matching benchmark show that our approach outperforms world models trained with supervised next-state prediction. We further show that our approach improves PRM-style action ranking on WebPRMBench compared with action-only PRMs and PRMs augmented with supervised-next-state world models. Finally, on WebArena-Lite, using our world model for test-time action selection improves end-to-end task success. Our project page is available at: https://dhruvpendharkar.github.io/dwm/.

Recent advancements in unified generative models (UGMs) and world simulators have achieved unprecedented results in visual perception and synthesis. However, these models primarily rely on surface-level event alignment, leaving the capacity for high-level visual reasoning underexplored. True visual generative intelligence demands "Reasoning-to-Generation", an ability to infer latent rules from visual inputs and manifest solutions through precise, logically constrained visual outcomes. We introduce RIG-BENCH, a novel comprehensive benchmark that systematically evaluates Reasoning-driven Image Generation (RIG) across four cognitively demanding domains: Concept-based, Transformation-based, Pattern & Structure, and Scenario-based. Featuring 2000 curated samples, RIG-BENCH serves as a rigorous stress test for RIG. Our extensive evaluations of state-of-the-art UGMs and image/video generation models reveal a significant reasoning-generation gap, wherein models frequently produce locally plausible but globally illogical outputs. RIG-BENCH provides a vital diagnostic framework to guide the development of next-generation, logically grounded UGMs and world simulators.

Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We present an end-to-end specialization pipeline combining large-scale problem curation, synthetic reasoning traces, supervised fine-tuning (SFT), and reinforcement learning (RL). Using 22,000 curated problems, we train Nemotron-3-Nano-CC (30B-A3B) with SFT and RL and Nemotron-3-Ultra-CC (550B-A55B) with SFT alone. We further introduce GenCorrect, a feedback-driven test-time compute strategy that iteratively generates, evaluates, and refines diverse solutions. On IOI 2025, Nano-CC improves from 130 points to 291 after post-training and to 468 with GenCorrect, exceeding the gold threshold of 438.3 while Ultra-CC reaches 502. Guided by these results, we develop a competition-specific Ultra-CC system and evaluate it prospectively during IOI 2026. Under the same time, internet-access, and submission constraints as human contestants, it scores 535.4 out of 600, exceeding both the gold threshold of 361.12 and the top human score of 498.27. To our knowledge, this is the first AI system to outscore the highest-scoring human contestant on an IOI problem set.

Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restoration around a fixed ISP: (A) pre-ISP restoration in the RAW domain and (B) post-ISP restoration in the sRGB domain. The benchmark covers four smartphone device groups, two learned ISPs, three degradation regimes--noise, blur, and joint noise and blur--, and several representative RAW and RGB restoration models. Our results show that placement alone does not determine performance. The RAW restoration strategy outperforms the best generic RGB restoration models. However, RGB restoration models trained considering the ISP transformations, achieve the best overall performance. Our novel benchmark demonstrates that the image reconstruction performance strongly depends on the alignment between the restoration model and the target imaging pipeline. We consequently recommend reporting restoration placement and ISP-aware supervision as key experimental factors. Our code is available at https://github.com/mv-lab/AISP

LiDAR-based semantic segmentation is a core perception module for autonomous vehicles and mobile robots. Despite the strong performance of recent state-of-the-art methods on standard benchmarks, existing evaluation protocols remain focused on clean, single-domain settings and fine-grained label taxonomies, leaving deployment readiness largely unassessed. Real-world systems must handle safety-critical label semantics, degraded sensing conditions, and cross-domain variability, yet no unified protocol currently addresses all three aspects together. In this paper, we propose a structured evaluation protocol that assesses the deployment readiness of LiDAR semantic segmentation models along three complementary dimensions: (i) coarse-label evaluation aligned with autonomous driving safety priorities, revealing how label granularity affects different methods; (ii) robustness under eight types of LiDAR corruptions designed to emulate real-world atmospheric, geometric, and sensor degradations; and (iii) domain generalization across datasets without adaptation. The evaluation includes inference speed measured on an embedded Jetson AGX Orin platform, directly reflecting deployment constraints. Our results show that fine-grained benchmark rankings do not always reflect safety-relevant performance, that all methods experience substantial degradation under corruptions with architecture-dependent robustness characteristics, and that current domain generalization remains insufficient for reliable deployment. These findings expose concrete gaps between benchmark performance and deployment readiness, and provide a reference protocol for more practically grounded evaluation of LiDAR semantic segmentation.

Researchers increasingly use artificial intelligence to construct measures of social, organizational, and occupational characteristics that are absent from conventional surveys. We propose AICOME, AI COntextual MEasurement, a framework for evaluating whether AI-derived respondent-level measures can recover individual and group-level effects in contextual models. The key idea is that an AI measure constructed at the respondent level can be used to derive its group-level aggregate and its individual deviation, allowing researchers to estimate both between-group and within-group associations rather than treating AI measurement as response prediction alone. We validate the framework using the 2022 China Family Panel Studies (CFPS), where occupations provide the empirical grouping structure and several job-related survey variables provide validation benchmarks. For computer use, foreign-language use, weekly hours, and management responsibilities, we compare survey measures with AI-derived measures in response-level, model-level, contextual, and boundary-condition validations. The results show that AI contextual measurement can recover much of the contextual-model information contained in observed survey variables when rich respondent and job characteristics are available. Weekly hours provides the strongest validation case, with AI-derived measures reproducing the large negative between- and within-occupation associations with satisfaction observed in CFPS. The framework also identifies clear boundary conditions: performance deteriorates when information is restricted to occupation and basic demographics, and recovery is weaker when several related concepts are treated as simultaneously unobserved. The findings suggest that AICOME is most useful for recovering a limited number of theoretically important constructs from rich existing datasets.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards leads to limited guidance on intermediate reasoning processes. Existing approaches such as process reward modeling and on-policy distillation introduce additional constraints, such as reliance on a specialized reward model or assuming identical reasoning patterns between teacher and student. Nevertheless, we observe that once a reasoning process first goes wrong, evaluating the subsequent reasoning provides limited additional information, as it is already conditioned on an invalid prefix. Therefore, we propose Cliff, a reward shaping strategy that utilizes an off-the-shelf LLM as a teacher to identify the first mistake in each rollout. As a result, the rollout is naturally decomposed into two parts: a correct prefix and an incorrect suffix. Cliff then converts this signal into token-level advantages, assigning positive advantages for the correct prefix and negative feedback afterward. Experiments across 12 different scenarios demonstrate that Cliff consistently improves reasoning performance, outperforming on-policy distillation by 15% and standard GRPO by 7%, even with teachers of modest capability. Furthermore, we analyse the role of ``ground truth'' in Cliff and investigate its training dynamics. These results establish Cliff as a simple, general and effective approach for improving RLVR with richer, fine-grained supervision.

Text-to-image models excel at natural image synthesis but struggle with graphic design, where success depends on satisfying precise constraints on typography, layout, color, and visual communication. While prompt optimization offers an attractive alternative to expensive diffusion model fine-tuning, learning prompts for frozen image generators requires informative reward functions despite the entirely non-differentiable generation process. Reinforcement learning does not require differentiable objectives; it requires only scalar rewards capable of ranking candidate outputs. This raises a simple question: can design evaluation metrics themselves become reinforcement learning rewards? Our central contribution is GDB-Reward, a framework that systematically transforms heterogeneous graphic design evaluation metrics into a unified reinforcement learning reward. Experiments demonstrate that GDB-Reward provides an effective optimization objective, substantially improving adherence to the design specification in perceptual quality, rendering fidelity, and spatial accuracy while keeping the image generator entirely frozen. More broadly, our results demonstrate that heterogeneous, non-differentiable evaluation metrics can move beyond passive benchmarking to become effective optimization objectives for reinforcement learning in domains where differentiable supervision is unavailable.

Predictive models are increasingly used in robotics for state estimation, planning, control, and policy evaluation, yet they are often judged by open-loop prediction accuracy over a fixed horizon. In closed-loop operation, a robot repeatedly acts, receives new measurements, updates its state estimate, and recomputes control. We study this difference in a differential-drive path-tracking task with biased odometry and intermittent landmark sensing. Six state estimators are evaluated across 24 sensing conditions using trajectory replay, a 20-step measurement-free rollout, and closed-loop tracking. Replay position RMSE correlates more strongly with closed-loop cross-track RMSE than rollout error (Spearman rho = 0.923 vs. 0.774) and selects a different estimator from the closed-loop optimum in 5/24 conditions, compared with 18/24 for the rollout metric. We then vary rollout horizon and measurement-update interval. With H=20, rank agreement decreases from rho = 0.916 with measurements at every step to rho = 0.774 with no measurements. A horizon-update grid shows that long prediction horizons remain informative when regular corrections are retained, whereas long rollouts without correction can produce rankings that differ substantially from closed-loop behavior. We also test recurrent estimators trained on longer sensing outages. This improves the EKF-anchored models under combined sensing degradation, reducing GRU-EKF cross-track RMSE from 1.72 m to 1.06 m, but the gain is not consistent across isolated outages or estimator architectures. These results show that predictive-model evaluation in robotics should specify both prediction horizon and measurement-update schedule. For models used in feedback, offline rollouts are most informative when their sensing and correction pattern reflects closed-loop operation. Code is available at https://github.com/rdharini2001/Robot_World_Model

Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G networks remains challenging due to complex cross-layer dependencies. While large language models (LLMs) offer promising capabilities for reasoning and knowledge integration, directly applying vanilla LLMs to telecom RCA often leads to hallucination, unstable reasoning, and poor alignment with structured network evidence. This work first reviews the evolution of telecom RCA from rule-based and machine learning (ML) approaches to emerging LLM-enabled techniques, and provides an overview of recent paradigms, including structured reasoning, retrieval-augmented knowledge grounding, agentic orchestration, and verifiable reasoning. Building upon these insights, we propose a structured reasoning framework for LLM-enabled telecom RCA that aligns diagnostic reasoning with telecom-specific evidence and domain knowledge. The proposed approach first organizes heterogeneous network telemetry into canonical contexts, and then enforces decision-path reasoning during diagnosis, and finally generates evidence-grounded explanations for reliable fault identification. Experimental results on two 5G RCA datasets, TeleLogs and TelecomTS, demonstrate that the proposed framework consistently improves diagnostic accuracy and decision consistency compared with baseline techniques. These cross-dataset results highlight the importance of structured reasoning design for practical LLM-based RCA systems in next-generation telecom networks.

For more than 20 years, the Model-RB benchmark frb100-40 remained an open challenge; since 2014, its public record had stood at 99 of 100 variables. We give a directly checkable 100-vertex independent set for its 4,000-vertex graph. Together with a verified partition into 100 cliques of size 40, the witness proves that the maximum independent-set size is 100 and the minimum vertex-cover size is 3,900. The stochastic run that found the witness is kept separate from this proof. We evaluated its added pair and triple repair operators in a preregistered campaign comprising 8,668 valid runs. The primary comparison found no detectable acceleration over base ULSA (hazard ratio 0.967, 95% confidence interval 0.915-1.023; p=0.248), and the factorial ablation reached the same conclusion. On a smaller FRB suite, the group-aware CSP pipeline solved 2,500/2,500 runs, compared with 2,391/2,500 for LibMVC-NuMVC. On frb100-40, full ULSA, base ULSA, and NuMVC each produced 0/56 new certificates. With no events, the planned cross-solver hazard ratios remain unidentified. NuMVC ended with cover size 3,902 in 40 runs and 3,903 in 16. Exhaustive enumeration showed that none of the 108 unique recorded conflict-two states had a strictly improving group-aware CSP neighbor within Hamming radius three. The certificate settles the instance. The experiments characterize the search barrier, and the preregistered comparisons show no heuristic advantage.

Neural map matchers estimate an image's 3-DoF pose relative to a 2D map. These models are trained on large-scale datasets of geo-referenced images, whose position and heading labels often contain noise that affects the trained models. To address this, we present AutoCompass, a supervision approach for training neural map matchers from inaccurate absolute pose labels. First, we show that heading labels are unnecessary: trained from raw GPS labels, models learn to predict accurate headings, automatically. Second, defining a tolerance region around raw GPS improves positional accuracy. Third, if available, our supervision uses relative poses between training images, obtained via SLAM or SfM, which provide a more accurate training signal. Across driving and egocentric benchmarks, AutoCompass consistently outperforms counterparts trained with the usual strong reliance on absolute pose labels.

People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life event, a natural disaster, or an economic outcome? Users of language models may implicitly trust that these forecasts fall out of a coherent world model. In this paper, we evaluate the coherence of language model probabilistic forecasts through a procedure that builds on a theorem due to de Finetti. We elicit forecasts from language models across events generated from stock returns data. We then use linear programs to compute the largest Dutch-book profit - the profit an arbitrageur could guarantee by betting against model-generated probabilities - which we use as a measure of incoherence. Our procedure does not require outcome labels, so we can evaluate coherence even in settings where outcomes are not observed or have not yet resolved. We find substantial evidence of incoherence in language model forecasts. Such incoherence increases when there are richer logical relationships between events, and irrelevant contextual details can increase incoherence by an order of magnitude. We conclude by discussing how alternative training strategies may improve probabilistic coherence.

The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmful final responses and multi-step execution trajectories. Existing safety alignment mechanisms often rely on either external harness updates or policy optimization, yet applying either paradigm in isolation fails to bridge runtime control with intrinsic safety. We propose SafeEvolve, an experience-driven self-evolving framework for agent safety alignment. SafeEvolve leverages safety experience from completed on-policy trajectories to drive a continual loop of harness-policy co-evolution. On the harness side, SafeEvolve converts trajectory-level safety evidence into bounded, component-level updates across safety prompt and hierarchical skills, yielding auditable and reversible harness artifacts. On the policy side, SafeEvolve follows a two-stage SFT-RL paradigm, where harness-use SFT bootstraps the policy to actively leverage evolved harness artifacts, and harness-augmented RL further shapes autonomous safety behaviors during multi-step exploration via verifier-decomposed rewards. Through harness-policy co-evolution, SafeEvolve converts safety experience into an evolved runtime harness and improved policy behavior. Experiments on agentic safety benchmarks show that SafeEvolve achieves a stronger safety-utility tradeoff than existing baselines. For Qwen3.5-4B, SafeEvolve achieves a $3\times$ ASR reduction on AgentDojo while improving benign utility from 59.79% to 61.86%.

Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single pass of a frontier model over an agentic benchmark can cost hundreds to thousands of dollars, a price paid repeatedly across iterative development cycles. Prior efforts, centered on benchmark distillation, reduce the number of evaluation tasks but leave the cost of executing each retained task untouched. In this work, we introduce early outcome prediction, a complementary axis of efficiency that instead cuts cost within each task. Our key insight is that an agent's final outcome is often evident from its intermediate behavior well before execution completes. We instantiate this idea in EarlyEval, a lightweight framework that trains a pair of LightGBM success and failure classifiers over behavioral, textual, and reference-solution features, and halts an agent run the moment either classifier crosses a calibrated confidence threshold, adding negligible per-step overhead. Across three benchmarks, SWE-bench Verified, TerminalBench, and Toolathlon, EarlyEval can eliminate 13%-26% of agent steps and up to 44.1% input tokens and 29.4% output tokens at 89%-97% prediction accuracy, while perturbing per-agent resolve rates by only one to two percentage points on average.

Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and early warning, and wearable assistants. However, processing continuous video streams with multimodal large language models (MLLMs) is computationally expensive. Existing efforts have explored reducing streaming overhead through visual token pruning, token merging, quantization, on-demand frame retrieval, and context offloading. However, most existing methods overlook the dimension of model depth. Repeatedly executing full-depth MLLM prefill over incoming frames is prohibitively expensive, incurring substantial computational overhead and causing the KV cache to grow at a rate directly proportional to the prefill depth. To address these challenges, we propose ShallowStream, a novel framework that leverages the shallow layers of an MLLM to simultaneously perform frame encoding and retrieval index building. During stream processing, ShallowStream maintains an always-on lightweight index using the KV cache of shallow layers. During query-time answering, we leverage the attention scores generated by the shallow layers to score context frames and employ a diversity-aware selection strategy to retrieve precise and comprehensive evidence. ShallowStream achieves performance on par with the strongest existing streaming methods, while reducing per-frame prefill latency and 10-second end-to-end latency by up to 52.1x and 11.9x, respectively. Our code is available at https://github.com/CURRENTF/ShallowStream.

Palm-vein biometrics are increasingly used for secure, contactless authentication. Yet real-world deployment exposes them to surface noise (sweat, dirt), illumination and motion variation, and temperature-driven changes in vascular visibility, which remain underexplored for lack of data captured under such conditions. To study these effects, we introduce the Columbia University Palm-vein (CUP) dataset, to our knowledge the first public video-based palm-vein dataset. CUP records every palm under four surface conditions (a clean baseline, warm, wet, and dirty) and pairs each subject with physiological and demographic metadata. On it we benchmark twenty-one recognizers spanning static, video, and multi-frame aggregation architectures. Models that verify reliably on clean palms lose most of their accuracy on dirty ones, and the mean equal error rate (EER) roughly quadruples. We recover much of that robustness along both axes of the capture. Temporally, a consensus over the few frames the sensor already returns cancels transient corruption; spatially, a test-time matcher that adds no learned parameters fuses the global cosine with a saliency-steered region-level optimal transport that routes the comparison around corrupted regions. The full design leads on every surface of CUP in EER, TAR@FAR=0.01, and Rank-1, at 4.3M parameters and 3.1 GFLOPs, a fraction of the video models' cost. Attached to four frozen state-of-the-art backbones it cuts their mean EER by 29-37% without retraining, and on four public single-image datasets the regional matching alone still helps. A preliminary audit across ten demographic and physiological traits finds two warm-condition gaps, along body water and gender, that survive multiple-comparison correction. CUP will be released for non-commercial research use at https://github.com/MobileX-CU/CUP_v1 upon publication.

Retrieval-Augmented Code Generation (RACG) improves LLM-based software development by retrieving external code artifacts, documentation, and patches, and incorporating them into the generation context. This reliance on external knowledge introduces a critical trust boundary: poisoned artifacts can influence generated code without modifying the underlying LLM. Prior work shows that selecting existing vulnerable examples can increase the general vulnerability rate of RACG outputs, but leaves open whether a black-box attacker can construct a single task-matched artifact that propagates an attacker-selected weakness. We introduce CodePoisonRAG, a targeted upstream knowledge-poisoning framework that transforms benign fixed-code entries into poisoned artifacts. Its attack chain combines CWE-specific Vulnerability Injection, which embeds a selected source-to-sink flow while retaining task alignment, with Semantic Mislabeling, which adds false safety claims without repairing the vulnerable behavior. The attacker has no access to the victim's deployed knowledge base, retriever, re-ranker, generator, prompt, or defense mechanism and injects at most one artifact per anticipated programming task. We construct 85 poisoned artifacts covering ten CWE classes across Java and C, yielding an aggregate corpus-poisoning ratio of 0.7%. Across three generators, all 85 artifacts appear among the Top-3 results for their corresponding queries, and CodePoisonRAG achieves attack success rates between 0.80 and 0.93. Against CodeGuarder, which injects vulnerability-specific security knowledge into the generation context, the attack retains success rates between 0.40 and 0.71. These results show that RACG poisoning extends beyond the incidental propagation of existing vulnerabilities to the targeted construction and propagation of attacker-selected weaknesses.

On-premise assistants can give factory workers conversational access to machine documentation, but models capable of the task rarely fit shop-floor hardware. We show that after structural compression and retrieval-grounded adaptation, model size is no longer a reliable predictor of adapted answer quality: general capability falls almost linearly with parameter count, while judged retrieval-augmented answer quality does not. We therefore treat deployment as a post-adaptation selection problem, committing one sub-network per device on judged answer quality and measured on-device throughput under a configurable general-capability floor and memory budget; rules that optimize size, speed, or quality alone each give up capability or throughput. A weight-shared supernetwork trained with sandwich-style in-place distillation keeps this selection inexpensive. In a manufacturing-manual case study, extraction costs 13.7 percent of the unpruned model's judged quality and retrieval-grounded distillation returns it to within 4.6 percent, recovering two thirds of the loss, and the same assistant runs across three heterogeneous edge tiers at 1.3 to 5 watts standby.

Large language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and misleading context can corrupt a model's medical judgment. To understand how misleading context corrupts this judgment, we examine the model's susceptibility to the context, disclosure of it, mechanism of corrupted reasoning, and monitorability of the decision. On the medical reasoning subset of MedMisBench, a clinician-reviewed question-answering benchmark of 8,627 questions, we inject two types of misleading context cues, fabricated evidence and a bare assertion. We test three reasoning models, two that expose their full reasoning trace and one frontier model that exposes only its response. All three are more susceptible to the assertion than to the fabricated evidence, adopting the asserted answer 10 to 27 points more often. The misleading cues are disclosed in 81 to 98% of traces but only 7 to 90% of responses, and the assertion is disclosed less often than evidence based cues. Resampling from reasoning traces without disclosure shows the two cues corrupt reasoning differently, evidence entering early and accumulating while the assertion redirects the conclusion near its end. An LLM monitor catches 78% of corrupted decisions at 5% false positives when reading an open model's trace with guidance, against at most 32% from any response. The misleading context that models are most susceptible to is disclosed least, and was caught reliably only from an open reasoning trace, which frontier providers withhold.

As generative AI tools become increasingly powerful and easy to use, people can easily edit portrait images with a prompt, necessitating the task of image editing attribution, which predicts the involved editing tools from the given image. Existing attribution methods hold the single-tool assumption and can only attribute a specific editing tool, but struggle to handle the more complex and increasingly common multi-tool editing scenarios, where artifacts left by different editing tools are composite and overlapped. To address this gap, we explore Multi-Tool Image Editing Attribution (MIEA), which aims to identify multiple editing tools involved in a multi-tool edited facial image. To simulate the real-life editing operations on facial images, we then construct a new dataset, MultiEdit, which contains 500k+ edited facial images and covers six types of editing tools that support face swapping (Deepfake) and various facial enhancements. Inspired by the findings from data analysis, we design DPEC, a multi-tool attribution method that can capture distinguishable, locality-aware editing tool traces from both spatial and frequency domains with the support of an error-based curriculum learning strategy. Experiments show \Method\ outperforms nine methods for facial images edited in at most five steps.

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orchestrator-worker interaction as a bilevel coordination game: under bounded coupling, the workers' local-update game is an approximate potential game whose equilibrium slack is controlled by decomposition quality. We then analyse reflection as stochastic movement over semantic memory states. For free-form reflection, we derive a finite-time upper bound, prove worst-case tightness, and give a positive lower bound under a falsifiable persistent-harm condition. We further prove an information-theoretic impossibility result: no gate that observes only the generated transcript can improve uniformly over text-indistinguishable environments, whereas an environment-grounded gate can. Motivated by this separation, we introduce Stochastic Reflective Memory Ascent (SRMA), which accepts a candidate memory only after a grounded evaluation risk strictly decreases. Under calibration and non-degenerate corrective mass, SRMA converges exactly, geometrically or polynomially; matching constructions show that both rate regimes are order-tight. We also provide confidence gating for stochastic evaluation and re-anchoring guarantees for piecewise-stationary environments. Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws. On 500 SWE-bench instances, the complete Kimi-based system resolves 72.2% versus a 70.8% public mini-SWE-agent reference. Code: https://github.com/YihangChen9/Bilevel-Coordinated-Reflection

Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and verification, but this architecture still leaves domain-specific know-how outside the agent. We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work. That knowledge is not absent from the field. It appears in repositories and papers, but in forms written for human readers and too large to load during a task. Once distilled into compact, verified skills, this knowledge can be reused across tasks rather than rediscovered during each run. We present DisCo, a skill-powered research agent that creates skills and uses them during research. Its distillation runs in two complementary forms: task-agnostic, condensing the field's widely used repositories into reusable skills, and task-oriented, producing the skills a concrete task calls for. The former, applied across the open ecosystem, yields the AREX-Skill Library, with 5,000+ verified skills distilled from 1,000 widely used ML repositories and organized into 20 areas and 178 capability families. With the GPT-5.5 backbone, research harness, and downstream execution budget held fixed, the skill-equipped research agent scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS, and 14.0% higher on PassNet than the same agent without skills. These gains come from adding distilled operating context under that fixed setup.

Selecting a retrieval model for a production RAG system requires reliable comparative evaluation, but obtaining relevance judgments at scale is expensive and difficult to repeat as new candidate systems arrive. We study pooled LLM evaluation, in which an LLM judges the union of documents retrieved by the current set of candidate systems, and the pool is then expanded incrementally as new systems are introduced by judging only the new documents they contribute. These judgments are reused to evaluate all systems on a common basis. We validate this approach on four retrieval benchmarks with 11 systems spanning dense, sparse, and hybrid configurations, and deploy it to compare 62 retrieval configurations for a financial news QA system. Pooled LLM rankings correlate strongly with gold-standard evaluation across datasets, and 97% of pairwise system orderings are preserved once bootstrap uncertainty in the qrels is taken into account. In production, document overlap yields 65-80% judgment reuse and up to 4.9x lower evaluation cost, allowing teams to benchmark new retrieval candidates without re-judging previously assessed documents. These results suggest pooled LLM evaluation is a practical and cost-effective workflow for incremental retrieval model selection in deployed systems.

Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If the user asks about a previous detail in a 1M-token conversation, global attention layers must scan the full context to generate each token of the reply. A prominent approach mitigates this cost by pre-selecting relevant tokens via lightweight proxy scores, but this extrinsic scoring still incurs O(N) per step. We take an intrinsic approach motivated by the simple question: wouldn't the model already know which parts of the context are relevant? To this end, we introduce Declarative Attention (DA), a protocol that elicits the model to declare where it needs to attend within its chain-of-thought, partitioning generation into three modes: <global> (full context), <focus> (a specific region), and <local> (recent output only). The inference engine parses these declarations like tool calls and skips most of the KV cache read. Under zero-shot evaluation across 15 long-context tasks, DA on off-the-shelf models (Gemma-4-31B, Qwen-3.6-27B) significantly reduces total attended tokens during decoding (52.0%, 31.1%) with modest accuracy drops (1.27pp, 2.75pp) that shrink with model scale. DA unlocks a new axis of sparse attention, with further potential under training-based methods that future work can explore.

Per-patient adapters are the preferred production architecture for dysarthric automatic speech recognition (ASR), yet parameter-efficient fine-tuning (PEFT) variants have not been compared in the speaker-dependent, per-patient regime. We present a single-speaker case study comparing seven LoRA-family methods (LoRA, QLoRA, AdaLoRA, DoRA, LoHA, VeRA, VB-LoRA) on two production bases (Whisper-large-v3 with Hungarian fine-tuning, and a multilingual Qwen3-ASR-1.7B checkpoint) for one post-stroke Hungarian male speaker (S1, 409 utterances; severe dysarthria on auditory-perceptual clinical assessment). Attention-projection adapters substantially improve CER on both bases. Across three seeds, a paired bootstrap detects no significant LoRA-DoRA difference (p>0.5; 13.86/13.90 % CER on Whisper, 28.10/28.33 % on Qwen3-ASR), so we adopt the simpler, cheaper LoRA. Real 4-bit (NF4) QLoRA is worse on every seed and both bases (14.56/30.09 % CER) with no memory saving at this scale, and LoHA, VeRA, VB-LoRA and AdaLoRA do not reach the LoRA family, though LoHA still gives an 18.6 % relative CER reduction on Whisper. On the same base, full fine-tuning is more accurate (11.43 % CER), but a 115 MB LoRA that also adapts the feed-forward blocks reaches within 0.66 pp of it at approximately 3.7 % of the per-patient storage. A 6-point enrollment grid shows about 5 min of patient audio captures 45.6 % of the zero-shot-to-30-min CER reduction, with further gains at 10 and 30 min (caveat: one speaker, one language, severe post-stroke dysarthria). Training scripts and recipes will be released, source-available under a research-use licence, on publication.

Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that treats every LoRA step as a tangent vector of the fixed-rank matrix manifold and takes the spectral-norm steepest-descent step of Muon inside that tangent space, mapping the result back to the factors through a retraction native to the LoRA parametrization. The step avoids expensive operations on full weight matrices, and its retraction is up to $2.8\times$ cheaper than the truncated-SVD retraction used by prior manifold methods. We prove that the Frobenius-norm version of our surrogate recovers LoRA-Pro, and we identify the tangent-projected gradient, the Riemannian gradient of the manifold, as the stationarity measure natural to LoRA training and computable from the factor gradients alone. Under this measure we give the first global convergence guarantees for both LoRA-Pro and LoRA-TSD, with rates that drive the factor-gradient norms to zero. Across six commonsense and natural-language-inference benchmarks with Llama-3.2-1B, Llama-3.1-8B and Qwen3-32B, LoRA-TSD outperforms every competing LoRA optimizer and stays robust to the adapter rank. Code is available at https://github.com/brain-lab-research/LoRA-TSD.

Large vision-language models have achieved remarkable success in vision-language tasks. However, they remain prone to Visual Hallucinations (VHs), undermining their reliability in real-world applications. Existing solutions typically require curated datasets, additional training, or multi-round decoding, resulting in considerable computational overhead. In this paper, we propose \textbf{RVSD} (\underline{R}etrieval \underline{V}ision \underline{S}parse \underline{D}ecoding), a training-free and plug-and-play decoding framework that, for the first time, unifies token sparsification and \textbf{Semantic-Space Visual Retrieval} (SSVR) within a single decoding pass. Within RVSD, we introduce a \textbf{semantics-directed token selection} strategy that selectively sparsifies redundant tokens while preserving critical visual information. We further propose the SSVR mechanism, which reformulates visual compensation as an on-demand cross-modal retrieval process within a shared semantic space. Extensive experiments demonstrate that RVSD achieves state-of-the-art performance in mitigating VHs while maintaining robust suppression capabilities under long-context generation settings. Our code is available here.\footnote{https://github.com/canjie-liu/RVSD}

Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models shift, the choices governing retrieval, ranking, and serving must be revisited. Traditionally, human engineers test such changes through online experiments--a slow, reactive process limited by engineering effort, leaving parts of the system unrevised as conditions change. Although large language models have been applied to ranking, user modeling, and offline model development, few systems place an agent in a continual closed loop that acts on a live recommender and learns from the measured effects of its decisions. We present CORAL (Constraint-Optimized Recommender via an Agentic Loop), an LLM-native harness that closes this loop: each cycle, the agent observes operating signals, reasons over a memory of past decisions and outcomes, and invokes tools--including a numerical optimizer that keeps changes within a fixed operating budget--to reconfigure the recommender, with measured outcomes informing the next cycle. We formulate this as a partially observed, non-stationary, constrained optimization problem in which the policy improves in context, without parameter updates, from its prior actions. Across two large-scale social platforms, evaluated with A/B experiments, the same harness improves engagement at no additional serving cost on one and reduces serving cost without degrading engagement on the other, spanning the engagement-efficiency frontier. Performance improves as the loop iterates, suggesting that a single agentic loop can automate continual optimization work traditionally performed by human algorithm engineers under explicit guardrails.

Large-scale training and refined optimization techniques have greatly improved sparse multi-view 3D reconstruction. Despite their relevance to surgery, such methods have never before been rigorously evaluated on real endoscopic images. Current clinical telerobots deploy a single stereo camera inside the patient, making multi-viewpoint data extremely rare. This paper presents MV-dVRK, the first ex-vivo surgical dataset to combine multiple exposure-synchronized stereo viewpoints with accurate surface geometry and camera poses. The static subset of the benchmark provides dense SfM reference geometry, validated against an industrial 3D scanner, together with ground-truth camera poses and sparse-view test sets. We use MV-dVRK to systematically compare zero-shot monocular, stereo, multi-stereo, and multi-view 3D reconstruction methods as the number of viewpoints increases. With two endoscopes, multi-stereo reconstruction achieves the highest coverage. With a third viewpoint, optimization-based multi-view methods perform best, covering 67% of ground-truth surface points within a 1 mm tolerance and recovering highly accurate relative camera poses. By contrast, feed-forward foundation models cover only 43% of the ground-truth surface in the same setting. MV-dVRK also includes ten dynamic sequences spanning multiple surgical tasks, with increasing kinematic complexity and tissue deformation, providing a basis for future research in multi-viewpoint surgical perception. The project is available at: https://mv-dvrk.is.mpg.de.

Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to be granted. We test this on nine production models from three providers: each model refuses a large request, then receives a smaller version of the same request, and we compare its compliance with asking directly. The answer depends on the model. On Anthropic's frontier models the technique works: Opus 5 answers the smaller request 65.8% of the time after refusing the larger one, against 29.3% when asked directly. On the frontier models of OpenAI and Google, and on Haiku 4.5, it backfires, lowering compliance by 15.5 to 23.0 points. A control locates the effect: a refused large request on an unrelated topic does less than the related one on all nine models, so the concession itself matters everywhere, while the reaction to having just refused something differs by model family. The technique does not transfer to refusals drawn from public benchmarks. What decides whether a retreat can work is what the request asks for: rewriting 265 refused requests for usable instructions into requests for explanations of the same topic removed the refusal in 263 cases. Human influence techniques port to language models one model family at a time.

Transformers process information causally, but long-context reasoning may depend on task state discovered only later. We formalize this mismatch through conditional state update tasks. For causal state update processors, providing the condition first can require exponentially less memory in the worst case than providing it last. Motivated by this principle, we introduce Trace as State. We use collected reasoning traces as a textual proxy for task state and place it before the long-context block on a fresh pass, allowing information derived previously to guide rereading. We conduct extensive experiments on Trace as State and Trace Append, a matched control that uses the same task state proxy but put it after the context. Across three models and three long-context datasets, Trace as State outperforms Trace Append in 26 of 27 reported combinations of model, task, and metric. On GraphWalks Parents, exact match lifts DeepSeek V4 Pro Preview from 29.2% on the initial pass and 43.0% with Trace Appendto 81.8% with Trace as State, and from 66.4% and 83.2% to 100.0% for GLM-5.2. These results show that placing traces before the context can improve long-context reasoning while retaining the causal transformer structure.

Future-aware representations and world models are increasingly used in proposal-based autonomous-driving planners to improve trajectory selection. However, improvements in proxy objectives or restricted subsets are often interpreted as planning gains without verifying proposal ordering, selected trajectories, full-scale utility, and critical driving components. We propose the Proxy-to-Decision Transfer (PDT) Framework, an analysis framework that evaluates when learned future information supports a reliable driving-performance improvement claim. Its Decision-Transfer Decomposition Module localizes value loss through score margins, switch-conditioned utility, and support-versus-selection regret. Its Reliability-Constrained Validation Module requires exact pairing, a minimum meaningful effect, scale-expanded confirmation, safety non-compensation, sequential comparability, and family-level robustness. On a representative future-aware planner evaluated with NAVSIM-v1, component BCE decreases from 0.705 to 0.530 while held selected PDM decreases from 0.963 to 0.961. A separate candidate improves a 512-record prefix by 0.00909, with a scene-bootstrap 95% interval of [0.000744, 0.0177], but its 2048-record and complete-support intervals include zero. A proposal-level replay further confirms the switch-utility decomposition, yet none of 432 screened configurations passes the two-half, two-seed robustness gate. PDT therefore identifies where decision transfer fails or remains indeterminate across proxy, subset, aggregate, and selection evidence.

RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual grounding, it fails when retrieval is incorrect or incomplete, leading to hallucinations. Finetuning methods such as RAFT and PA-RAG enhance RAG by injecting new knowledge into the model's parameters, but require generating a massive amount of synthetic QA that covers the entire corpus. Extended Pre-Training (EPT) on the text corpus avoids the need for comprehensive synthetic data generation but compromises an Instruct LLM's instruction-following capabilities, necessitating instruction fine-tuning (IFT) after pre-training. However, IFT is costly and may be infeasible due to the unavailability of an instruction-tuning corpus. In this work, we propose DKL-Decoupled Knowledge Learning for Instruction-Tuned Language Models. Instead of doing EPT on the Instruct LLM, DKL performs EPT on its corresponding base LLM to infuse new knowledge. These knowledge infused weights are then merged with the Instruct LLM, imparting new knowledge without affecting their instruction-following capabilities. DKL is a lightweight method that avoids expensive instruction fine-tuning and relies on model merging to infuse the new knowledge into the Instruct LLM without destroying its instruction following capabilities. Empirical results show that DKL improves RAG accuracy from 54.17 to 79.26 on retrieval failure cases, while outperforming prior approaches with substantially less training data.

Deploying 3D point cloud models on edge hardware such as the NVIDIA Jetson Orin Nano is severely constrained by compute and memory budgets. Existing compression methods require access to the model's original source code, rendering them inapplicable to the Open Neural Network Exchange (ONNX) binaries commonly distributed by vendors and model repositories. We present \textbf{H3DNAS}, a hardware-aware model compression framework that operates directly on ONNX computational graphs without requiring original source code, architecture class definition, or gradient access during search. H3DNAS makes three contributions: (1) a \textbf{Channel Dependency Graph (CDG)} that classifies ONNX operators into four constraint classes and formally establishes that the free parameter fraction $ρ_f$ is topological invariant, a provable compression ceiling computable in $\mathcal{O}(|V|+|E|)$; (2) a \textbf{Two-Stage Hierarchical Search} that prunes candidate architectures by $L_1$-importance channel selection, ranks them by output fidelity as a zero-shot label-free proxy, and applies GhostConv structural mutation to Pareto-optimal candidates; and (3) the \textbf{first source-code-free compression pipeline for 3D point cloud models}, operating entirely via ONNX graph surgery with no original architecture definition required. On ModelNet40, H3DNAS reduces the number of parameters in PointNet, PointNet++, and PointMLP by $65.5\%$, $43.2\%$, and $49.1\%$, respectively, while achieving $1.99\times$, $1.29\times$, and $1.67\times$ inference speedups with negligible loss in accuracy. The source code is publicly available\footnote{https://github.com/ClarityLab-Org/h3dnas}.

Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramids that nest fine detail within wide coverage. Current generative models of satellite imagery, however, operate along a single axis: they either zoom to enhance a single tile's resolution or pan to extend imagery at a fixed scale. As a result, no existing method produces a complete pyramid that stays consistent across both scale and space, where a high-zoom tile must agree with the coarse context it refines and with the neighbors it meets. Motivated by this gap, we introduce a new task, multi-scale tile completion: given a sparse set of seed tiles at arbitrary zoom levels and positions, synthesize a complete, uniform quadtree that is globally consistent across both scale and space. We approach this task with Genesis, a generative engine that brings both axes together by composing two specialized operators over the quadtree: a vertical super-resolution model and a horizontal mask-based outpainting model, producing pyramids that are consistent across zoom levels and seamless across neighboring tiles. Each operator achieves state-of-the-art results on its subtask, and the engine propagates sparse seeds into seamless, multi-resolution maps from any initial configuration. To evaluate the task and benchmark Genesis, we introduce dense500, a fully observed multi-scale pyramid dataset spanning diverse geographic regions, together with a suite of pyramid-level metrics. Code, models, and our dataset are available at https://github.com/mvrl/genesis.

When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and institutions, while false alarms consume limited human-review capacity. When no trusted context or reference document is available, we study two signals accessible through black-box model APIs: semantic entropy, which measures disagreement among sampled response meanings, and uncertainty derived from token log-probabilities. Their failure modes can be complementary: semantic entropy becomes uninformative when responses form one semantic cluster, while token uncertainty can miss consistently confident errors. We extend token-based uncertainty detection by aggregating token-level signals across sampled responses through our TopK method, evaluate the hybrid CoCoA method, which combines target-response uncertainty with semantic dissimilarity, and propose and study two supervised methods: Gated, which routes single-cluster cases to an aggregated-token-feature classifier, and Stacked, which learns jointly from semantic uncertainty and broader token features. We evaluate seven benchmarks, including five public benchmarks (four text datasets and multimodal handwritten-cheque extraction) and two constructed benchmarks (Financial Summaries and Long-Text QA), using four language models. In our evaluation across models and datasets, Stacked gave the best performance in nearly half of the cases, while TopK and CoCoA remain competitive without supervised training labels, although their thresholds require careful calibration. No method is universally strongest. We therefore evaluate performance at false-positive-rate budgets from 1% to 15%, assess their sensitivity to generation and calibration choices, and examine variation across dataset characteristics.

Recent 4D Gaussian representation frameworks have demonstrated strong performance in language-guided dynamic scene understanding. However, these methods remain highly sensitive to verbose and narrative-style queries that contain noisy contextual information. In this paper, we investigate the impact of query rewriting for complex object segmentation in 4D Gaussian representations. Inspired by recent findings in retrieval-augmented language models and keyword-guided query reformulation, we propose a training-free reinterpretation strategy that transforms long descriptive queries into concise keyword-grounded forms. Our approach progressively reduces linguistic noise while preserving semantic anchors relevant to object-centric representations. Experiments on HyperNeRF and Neu3D demonstrate that concise rewritten queries significantly improve both temporal localization and spatial segmentation performance. In particular, our method improves average temporal accuracy from 60.92% to 92.21% and average vIoU from 20.08% to 76.94% without any additional fine-tuning. Extensive ablation studies further reveal that shorter, keyword-focused queries consistently yield stable video-feature similarity distributions and better alignment with object-centric Gaussian representations

Humans can perform complex manipulations given a simple intent through an overall instruction, while continuously adapting to evolving visual observations. However, current vision-language action (VLA) models and other action policies struggle to realize this high-level intelligent behavior under dense, evolving visual inputs and sparse language guidance. Visual correlations can then dominate semantic intent, leading actions to follow visual shortcuts rather than human goals. We present HINT (Human-INTent INcepTion), an agentic framework inspired by the human manipulation principles: semantic intent changes sparsely at manipulation-pattern transitions, whereas continuous control primarily depends on the evolving object-hand relationship. HINT invokes semantic reasoning only at pattern transitions to resolve the current subtask and target, then maintains this commitment through multi-view grounding and visual tracking. We explore two visual interfaces-image-space semantic highlighting and attention-prior injection-to communicate the tracked intent to the action policy without introducing additional trainable parameters into the foundation action model. Experiments across three long-horizon tasks and out-of-distribution variants show that HINT substantially improves intent understanding, task progress, and end-to-end success across two foundation policies while preserving low-latency control.

Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol. Its kernel decodes one shell; we found no implementation of the multi-shell decoder the rate requires. This paper supplies one and measures its serving cost for decode-phase GEMV at batch 1. First, a serving path for the full 301-class codebook: an offline expansion into GPU layouts and a fused dequantize-plus-matvec kernel reading them without warp divergence, verified against f64. Second, the in-VRAM rate is a design axis distinct from the on-disk rate. Four bit-exact layouts timed in one process show binary bit planes beating one-hot masks on size and speed at constant bandwidth (4.80 bits per weight, 2.15x FP16). Below 4.3 bits a second, irregular stream enters; at 3.6 the decode stops being shifts and masks. Third, deployed four-bit (AWQ) and two-bit (QTIP) GEMV kernels run in the same process. The trellis kernel reads 2.40x fewer bytes than our served layout and runs 2.27x faster at near-equal fractions of their byte bounds: the time gap tracks the traffic gap, the price of unfolding a codebook too large for a lookup table. Fourth, the validity envelope: the trellis kernel outruns our no-weights control, so our launch geometry sets that floor, and on a second memory hierarchy every lattice arm falls below FP16. With the output head held identical across arms, the kernel-and-format path gains 1.11x, 1.29x and 1.41x end to end at 4B, 8B and 14B; with an int8 output head the served 4B reaches 87.0 tok/s in 2.60 GB. The quality cost, 1.38x perplexity and 14.7 MMLU points at 4B, shrinks across the three sizes measured.

While English language models have been widely examined for anti-queer bias, Dutch models remain understudied. To address this gap, we developed a culturally and linguistically adapted Dutch dataset based on the English WinoQueer benchmark, containing pairs of stereotypical and counter-stereotypical sentences. To validate and expand it, we conducted an online survey with 43 Dutch queer participants, confirming 145 of 171 stereotypes as culturally relevant and identifying 22 new biases through free-text responses. The final released dataset, comprising 42,906 sentences, was evaluated using a range of Dutch-specific and multilingual models, including both masked language models (MLMs) and autoregressive language models (ARLMs), with bias measured via a score comparing log-likelihoods of stereotypical versus counter-stereotypical sentences. While the mean bias score across models appeared neutral (~50%), closer analysis revealed significant disparities: some models favored stereotypical sentences up to 97% of the time for transgender identities, but only 6% of the time for gay-related pairs, with transgender and non-binary identities consistently receiving the highest bias scores. Our findings highlight the importance of culturally grounded datasets for evaluating and mitigating biases that disproportionately impact marginalized groups in Dutch language models.

Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industrial settings. While monolithic Large Language Model (LLM) agents offer unbounded expressivity for tasks like Root Cause Analysis (RCA), they suffer from context limits, compounding hallucinations, and prohibitive inference latency. Traditional weak supervision offers statistical rigor but is mathematically restricted to discrete classes. We present Loom, a generative consensus framework deployed for real-world RCA that bridges these paradigms. Loom aggregates open-form hypotheses emitted by modular heuristics (diagnostic templates dynamically populated with episode-specific entities, times, and metrics) by projecting them into a continuous embedding space, and resolves conflicting signals with an iterative centroid-based reweighting algorithm. The resulting consensus weights ground a single lightweight LLM synthesis step. Evaluated on the OpenRCA benchmark, Loom occupies the accuracy--efficiency Pareto frontier: it matches a state-of-the-art autonomous agent on Bank and Market-2 and trails on Market-1 and Telecom, while using a single LLM call per incident on all four datasets ($\sim$26$\times$ faster; $\sim$33$\times$ with an 8B-parameter synthesizer). We discuss our deployment experience, highlighting lessons learned regarding the trade-offs between agentic depth and inference latency, negative results in redundancy detection, and how deterministic consensus fosters trust among Subject Matter Experts~(SMEs).

Face recognition in unconstrained environments remains highly challenging due to diverse and extreme variations encountered in real-world scenarios. To mitigate these effects, existing margin-based approaches model sample quality through feature magnitude. However, magnitude-based modeling alone is susceptible to identity-agnostic noise, which can degrade the reliability and discriminative power of learned representations. In this paper, we propose Dual Quality Margin Learning for Face Recognition (DQM-Face), a novel framework that enables refined attraction and repulsion dynamics during representation learning. Our approach unifies conventional magnitude-based quality estimation with a newly introduced semantic quality learning mechanism, realized via squeeze-and-excitation semantic attention. By jointly leveraging magnitude and semantic cues, we construct enhanced quality-aware margins that adaptively strengthen intra-class compactness through improved attraction during learning. To further enhance inter-class discrimination, we introduce a repulsion margin formulation that explicitly enlarges inter-class separation. The unified integration of semantic quality modeling with dual attraction-repulsion margin optimization results in a more structured and discriminative feature geometry. Extensive experiments on multiple challenging benchmarks demonstrate that DQM-Face consistently outperforms state-of-the-art face recognition methods. Moreover, we show that the quality learned for margin optimization is highly effective for face image quality assessment within the proposed framework, demonstrating that the learned quality signal is intrinsically aligned with the recognition objective. The code is publicly available: https://github.com/RAIB-group/DQM-Face

The rapid advancement of generative models has significantly worsened the problem of manipulated image detection, as these methods are capable of producing highly realistic forgeries, reinforcing the importance of multimedia forensics. Conventional approaches typically frame image manipulation detection as a binary classification task (real vs. generated), which limits the capability to distinguish and localize different forms of manipulation. To address these constraints, this work extends an existing detector by introducing a unified multiclass framework (real vs. fully generated vs. tampered). In addition to classifying image authenticity, the framework incorporates a segmentation branch to enable pixel-level localization of tampered regions. The proposed approach outperforms selected recent benchmarks, offering an efficient solution with improved classification accuracy and higher IoU scores for the localization task. Find the code at https://github.com/anngal01/From-Detection-to-Localization-A-Unified-Forensics-Framework-for-Fully-Synthetic-and-Tampered-Images.

Knowledge graphs have become an important source of structured knowledge for Web applications, including search, question answering, and recommender systems. In these applications, link prediction can serve either as a prediction task itself or as a means to enrich incomplete knowledge graphs for downstream tasks. Interestingly, different link prediction models, or even different training runs of the same model, can produce substantially different predictions for the same query. This suggests a variability in the capture of the underlying knowledge by models, thus raising a fundamental question: to what extent do different models capture complementary knowledge, and how much of this knowledge could be recovered by combining them? We propose to measure model complementarity through the performance of an oracle that, for each query, selects the best prediction among a considered set of models, hence providing an upper bound on the performance achievable through model combination. Across several architectures and benchmarks, we find a substantial gap between individual models and their oracle, revealing that different models capture complementary knowledge. Yet, this complementarity rapidly saturates as more models are added, leaving a persistent subset of queries unsolved even by a large number of models. These findings reveal both the potential of model complementarity and a fundamental limit to what current link prediction models can collectively recover; thereby highlighting the need for further research to build robust Web applications.

Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving their behaviour remain poorly understood. We propose LAVLA, a framework for latent cluster analysis of VLA models, and conduct a layer-wise study of the state-of-the-art GR00T N1.5 model, with particular focus on its action decoder. To better characterise the latent space during action diffusion, we introduce a cross-attention-based embedding-weighting method that amplifies relevant features while suppressing less informative ones. Quantitative evaluation shows that weighted clustering consistently outperforms the baseline. To improve interpretability, we extract human-interpretable concepts for each cluster, linking latent representations to semantic descriptions. Our analysis shows that latent clusters progressively disentangle spatiotemporal and kinematic features, with representations becoming more refined in the middle layers and stabilising toward the output. As such, LAVLA advances the interpretability of language-driven robotic systems.

Simulation-based science often requires a distribution over simulator parameters whose push-forward reproduces a set of real observations: this is the source distribution estimation (SDE) problem. Existing methods fit the source against a likelihood surrogate trained once from a fixed proposal prior. Their objective is therefore stated only in terms of the surrogate instead of the true simulator, which may fail for inaccurate areas in parameter space where the surrogate was never trained. We instead solve SDE by expectation maximization: an E-step trains an amortized posterior on fresh simulations from the current source estimate, and an M-step refits the source to the average of that posterior over the observed data. We give two parameterizations, (1) separate source and posterior flows and (2) a single shared conditional flow. We evaluate our method on three benchmark tasks under both broad and misspecified initial priors. Both improve on existing fixed surrogate approaches and on iterated variants of each, most clearly on Lotka--Volterra, where no baseline falls below 0.96 data-space C2ST while our methods reach 0.64-0.68 in three of four initial-prior settings.

The Mini-Girona Intervention Autonomous Underwater Vehicle (I-AUV) represents an advancement in accessible underwater robotics, designed to bridge the gap between costly, specialized research AUVs and basic Remotely Operated Vehicles (ROVs). Developed with a focus on affordability and usability, the Mini-Girona, priced at approximately $50,000, integrates advanced components such as a 5-DOF manipulator arm, stereo vision, and AI-driven processing for autonomous navigation and intervention tasks. This paper presents the design and development of the Mini-Girona, detailing its performance during the RAMI 2025 student competition. Despite challenges such as thermal management issues and restricted team access, the Mini-Girona achieved second place overall, excelling in vision-based perception and intervention tasks. This work highlights the platform's potential as a tool for underwater robotics research and education, fostering innovation in real-world underwater applications.

Transition metal dichalcogenides (TMDs) in their monolayer form offer a premier platform for next-generation optoelectronics, particularly through the local manipulation of their robust excitonic states using nanoscale electric fields. These localized states can be dynamically controlled through spatial structuring as well as through ultrafast field modulations driven by tailored optical pulses. Characterizing the resulting rapid, nanoscale charge carrier dynamics requires a technique with exceptional spatial and temporal resolution. Here, we report on the spatio-temporally resolved investigation of ground state and excited state photoemission from a lateral heterostructure built of monolayers of WSe$_2$ and MoSe$_2$ using few-cycle light pulses with a photon energy of 0.62 eV. We utilize photoemission electron microscopy to spatially resolve the highly nonlinear photoemission from the monolayer structure with few tens of nanometer resolution. By varying the laser pulse energy, we extract the nonlinearity of the photoemission process and thus the dynamic binding energy of the photoelectrons before and after optical excitation with high spatial and temporal resolution.

Large language models (LLMs) are increasingly deployed as economic agents, yet there is little evidence whether LLM agents are suited for participating in market mechanisms designed for humans, and whether these mechanisms deliver desired outcomes when faced with LLM agents. We address this question by replicating seminal economic experiments, replacing human subjects with LLM agents. We place agents in a double auction environment, which is a widely-used market mechanism. We check whether such a market is able to deliver an efficient allocation of resources, thereby testing a novel dimension of alignment of LLM agents -- their compatibility with a fundamental market mechanism. We find that markets populated by LLM agents exhibit slower or no convergence towards market equilibrium, thus providing less efficient allocations than markets populated by humans. We then analyze agents' individual trading decisions and find substantial heterogeneity both across model families and market roles. We also run a lexical analysis of Chain-of-Thought (CoT) traces generated by the agents. We find that the decision to execute a trade rather than continue incrementally adjusting prices is associated with a shift from strategic considerations toward urgency. We publicly release our testing framework, which can be used for future evaluations.

Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In such multi-image tasks, text typically serves merely as task instructions, lacking deep semantic interaction with the visual content. In contrast, realworld applications like text-image co-creation, character tracking, and spatial reconstruction require constant interaction between text and images. Consequently, models must possess a deep understanding of these interleaved contexts. To bridge this gap, we introduce a novel benchmark, TIC-Bench (deeply interleaved Text-Image Contexts), designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts. This benchmark encompasses three core domains: Logical, Temporal, and Spatial Association, which are further categorized into eight specific types, comprising a total of 2,280 questions. We evaluated 10 state-of-the-art MLLMs and observed a substantial performance gap compared to human experts, together with persistent difficulties in integrating evidence distributed across interleaved visual and textual inputs. Ultimately, this benchmark provides a valuable analytical tool for assessing and advancing the ability of multimodal models to effectively integrate text and image information in deeply interleaved contexts. TIC-Bench is publicly available at https://huggingface.co/datasets/pino10010/TIC-Bench

Machine-learnt corrections can complement numerical weather prediction only if they adapt to the evolving model state while preserving dynamical consistency and numerical stability. To test this within a global forecasting model, we couple the Met Office (UKMO) Unified Model (UM) with distributed RL agents through rank-local tensors. A DDPG actor shares weights across the 70 vertical model levels of each atmospheric column and applies bounded potential-temperature corrections to the model tendencies. Across ten nudged training forecasts, nudging calculations towards the UKMO operational analysis provides an immediate counterfactual target. The frozen policy is then evaluated in a non-nudged forecast for inference. The coupled workflow successfully completes training and remains numerically stable in the evaluated case. Relative to a matched native UM forecast at +6 h, the learnt policy reduces Z$_{500}$ MAE in four of six latitude bands, including reductions of 45.8% and 40.8% in the northern and southern tropics. MSLP error too decreases in three bands, with a maximum reduction of 27.3% at 0-30°N. This single-case experiment demonstrates significant promise and feasibility of distributed online learning followed by non-nudged inference, laying the groundwork for RL-based bias correction and parametrisations within operational systems.

Text-video retrieval requires representations that can distinguish videos with similar scenes, actions, and temporal patterns. Recent multimodal large language models have been adapted as embedding models, but they often represent each input using a single token from the final layer. This can compress diverse video-text cues into a single vector and limit fine-grained retrieval. To address this limitation, we propose MARS, a multi-layer and multi-slot embedding framework for text-video retrieval. MARS constructs multiple adaptive representation slots by combining hidden states from different decoder layers, compares corresponding text and video slots, and aggregates their similarities for retrieval. To better handle confusing candidates, we further introduce a hard-negative-aware slot specialization objective that encourages the slots to capture discriminative matching cues. Experiments on four text-video retrieval benchmarks show that MARS achieves state-of-the-art results in both direct similarity-based retrieval and reranking settings. Ablation studies and analyses demonstrate that multi-layer fusion, multiple slots, and hard-negative-aware slot specialization provide complementary gains. Code is available at https://github.com/sejong-rcv/MARS.

Zero-shot generalization to unseen embodiments is important for generalizable vision-language-action (VLA) models as robot hardware evolves and task-specific data collection remains costly. However, a systematic understanding of this problem remains limited, in part because the literature lacks a unified zero-shot transfer definition and controlled evaluation settings that isolate embodiment changes from differences in tasks, scenes, or protocols. To address this gap, we first distinguish strict zero-shot transfer, where the target embodiment is absent from all training data, from pretrain-exposed zero-shot transfer, where it appears only during pretraining. We then introduce a controlled benchmark spanning 14 held-out target embodiments across simulation and real-world validation. Within this framework, we conduct a controlled analysis of four factors: state-action representations, pretraining embodiment diversity, auxiliary co-training objectives, and target-embodiment exposure. Experimental results show that local end-effector (EEF) state-action representations, the source embodiment diversity, and auxiliary co-training improve cross-embodiment transfer by around 15, 18, and 7 percentage points, respectively. We further find that adding only 5% target-embodiment data during pretraining improves average target-embodiment progress by 13.4 percentage points, showing that strict and pretrain-exposed zero-shot transfer are distinct and should be reported separately. Together, these findings provide practical guidance for evaluating and improving cross-embodiment VLA transfer in stationary tabletop manipulation with two-finger grippers, while motivating future investigation of broader settings including mobile-base control, dexterous hands, and long-horizon tasks.

Foothold-constrained terrain is characterized by sparse, discontinuous, or geometrically restricted feasible foot contacts, as encountered on stepping stones, across gaps, and on narrow stair treads. On such terrain, a single misstep often leaves little room to recover, so policies that base foot-placement decisions primarily on the immediately visible terrain are prone to failure. We ask whether a learned predictive summary of near-future observations and rewards can provide the anticipatory information required in such settings. We present World-Model-Augmented Visual Locomotion (WM-LOCO), which jointly trains a recurrent world model and a PPO policy. Conditioned on proprioception and a single onboard depth image, the world model produces a predictive recurrent feature that guides the policy, without explicit foothold labels. In simulation, WM-LOCO succeeds on gaps and stepping stones where a matched baseline fails completely, and matches the baseline's success rate on stairs while improving stride efficiency and reducing pelvis acceleration. We deploy the same policy onboard a physical Unitree G1 humanoid using onboard proprioception and a single depth stream; it traverses all three terrain classes with an average success rate of 93.3%.

World Action Models (WAMs) leverage the capabilities of large-scale pretrained video diffusion models to jointly predict future observations and actions, inheriting rich visual and physical priors from internet-scale video. This has made them a promising paradigm for robot policy learning, yet the prevailing models operate exclusively on RGB observations and do not leverage 3D information. To bridge this gap, we introduce a Spatially Aware World Action Model (SA-WAM), which repurposes a pretrained video model for joint action, RGB, and depth prediction, enabling 3D-aware world modeling and action prediction within a single diffusion backbone. We use a nonlinear encoding that maps the unbounded depth signal into the bounded input domain expected by the frozen VAE tokenizer. This allows us to reuse the tokenizer without 3D-specific fine-tuning, incorporating geometric information without sacrificing the pretrained priors. SA-WAM achieves state-of-the-art results on the RoboCasa and LIBERO-Plus benchmarks, while simultaneously improving future-state predictions. Furthermore, SA-WAM outperforms strong baselines in real-world evaluation using a UR5 robotic arm, with strong gains in randomized environments. We analyze the correlation between world model prediction quality and rollout success, providing insights into WAM performance and avenues for its improvement.

Conventional fabrication of suspended nanomechanical resonators typically relies on wet-chemical process steps and critical point drying, which can compromise sample yield and cleanliness. Here, we present an all-dry fabrication process for strongly stressed 3C-SiC nanomechanical string resonators that entirely avoids wet-chemical etching and cleaning. Using a negative-tone electron-beam resist as an etch mask and a three-step reactive-ion etching process for both structuring and release, we achieve high fabrication yield, clean suspended structures, and extreme aspect ratios of 8.500. We perform full mechanical characterization of the resulting doubly-clamped nanostring resonators, and establish a benchmark intrinsic quality factor for dissipation-diluted 3C-SiC of Qintr = 4.200.

Image enhancement and restoration have become standard back-end operations on short-video and social media platforms to boost UGC visual experience. Yet these processes inevitably introduce visual anomalies--especially in faces, texts, and textures--that directly undermine perceptual fidelity and viewer trust. While existing IQA methods perform well on classic distortions, they target holistic quality assessment and fail to capture the specific, localized anomalies caused by enhancement algorithms in real-world UGC. To bridge this gap, we formally define a new task-quality Anomaly Perception for UGC image Enhancement (UEAP), and contribute the first UEAP benchmark dataset, named UEAP-4k, curated from the real business scenarios. It provides fine-grained annotations for anomaly categories, localization and severity levels. Furthermore, we propose a Difference-Fusion Anomaly Perception Method (DFAP-UGC) for wild UGC-enhanced images, which leverages explicit problem-reference difference fusion with dense spatial querying, regional verification, and quality-aware ranking, enabling robust anomaly identification in challenging scenarios. To handle the inherent coupling of subtasks in this new task, we propose a Locality-Aware Dynamic Task Prioritization (LADTP) training strategy that enables effective end-to-end learning and eliminates multi-stage overhead. Extensive experiments show that our method outperforms baselines adapted from classical approaches for this task, validating the value of this dataset and the superior of DFAP-UGC for robust UGC-enhanced image anomaly perception. Code and data will be public.

Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous confidence score. Since most possible triples lack observed confidences, recent methods rely on semi-supervised learning to generate pseudo-labels. These methods initialize entity embeddings without using the confidence-weighted graph, discarding its global community and hub structure. We introduce QUEST, which adds no trainable parameters to the standard confidence-distribution learning pipeline. First, QUEST initializes entity embeddings using the smallest non-trivial eigenvectors of the confidence-weighted graph Laplacian, incorporating community and hub structure before training. Second, QUEST applies an unbiased mini-batch Dirichlet energy regularizer to enforce early-stage structural consistency. On two UKG datasets, QUEST improves confidence prediction and link prediction on six of eight metric-dataset pairs over prior methods and matches the previous best on the remaining two, while removing the instability spike observed on dense graphs. These results indicate that spectral structural priors combined with a graph Dirichlet energy regularizer improve accuracy, training stability, and checkpoint reliability in UKG completion.

With the recent rapid progress in generative models, image editing has made remarkable advances, yet achieving faithful edits that precisely modify only the target regions while strictly preserving all other regions remains challenging. Since externally provided region annotations are often difficult to obtain in practice, a growing body of work seeks to improve preservation by automatically inferring edit and non-edit regions, and then enforcing consistency on the latter. However, these approaches still suffer from inaccurate region estimation and heuristic correction strategies that distort the native inference process, making methods designed for fidelity themselves a new source of artifacts. We propose SR-Edit, an image editing framework that overcomes these issues via iterative self-refinement. Specifically, at each iteration, SR-Edit first (i) extracts progressively precise and self-consistent region separation from the model's own predictions by lightweight post-processing, and then (ii) enforces preservation in non-edit areas through correction updates that remain aligned with the original sampling dynamics. Extensive experiments demonstrate that SR-Edit achieves superior preservation and overall image quality compared to existing editing techniques.

Photon-number-resolving (PNR) detectors are essential for photonic quantum computing, where a single measurement outcome must reliably herald a specific quantum state. However, detector fidelity is conventionally evaluated using ensemble-averaged statistics obtained from many measurements, which can remain high even when individual photon-number assignments are frequently misidentified. Here we introduce a universal single-shot fidelity that directly quantifies the probability of correctly identifying a photon number in a single measurement. The framework combines an efficiency-based POVM with a resolution-driven confusion matrix derived from the detector response, allowing photon loss and photon-number misidentification to be treated separately and then recombined into a single operational metric. This distinction reveals two fundamentally different limitations. Detection-efficiency loss represents an unrecoverable hardware constraint, whereas resolution-driven misidentification can be reduced by introducing a rejection region, trading generation rate for confidence. Because the metric is defined independently of detector architecture, it enables direct comparison between energy-resolving detectors such as transition-edge sensors and multiplexed click-based detectors on the same footing. Applying the framework to calibration data from three distinct detector architectures, we demonstrate quantitative comparison across photon-number regimes relevant to both discrete-variable and continuous-variable photonic quantum computing. The resulting benchmark provides a common operational metric for evaluating photon-number-resolving detectors and connecting detector performance to photonic quantum-computing requirements.

Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined. To bridge this gap, we introduce VMetaphor-Bench, the first benchmark for evaluating visual metaphor generation in T2I models. It comprises 1,500 visual metaphors curated from real-world creative imagery, organized into three levels and ten categories, with each sample paired with two prompts of differing specificity. For evaluation, we develop a hybrid framework within an MLLM-as-judge paradigm, combining a multiple-choice question (MCQ) based protocol of 9,594 questions across four levels of metaphorical fidelity with a dimension-based scoring protocol along three perceptual dimensions. Extensive evaluation of 11 representative T2I models reveals that even the strongest proprietary models struggle with compositional structuring and cross-domain mapping, key aspects of metaphorical expression, highlighting visual metaphor generation as an important frontier for future T2I research.

Recommender-system experiments often rely on a single random training seed, assuming that run-to-run stochasticity has limited impact on evaluation conclusions. This assumption is risky, as a training seed may influence several algorithm-dependent mechanisms, including parameter initialization, mini-batch ordering, dropout, masking, latent sampling, and training-time negative sampling. We examine this assumption by fixing the data partition and varying the training seed across hyperparameter configurations. We analyze seed effects at three levels: user-level metric sensitivity, validation-based model selection and recommendation-list agreement. Results show that seed variation is often detectable. Its impact depends on whether configurations are clearly separated, whether validation results transfer to test, and whether similar scores lead to similar top-$k$ lists. Findings suggest that reporting single-seed results can overstate the stability of recommender system evaluation, and that training seeds should be treated as part of the evaluation protocol rather than as incidental implementation noise.

Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as SparseGPT, can amplify existing biases in models, with outputs varying significantly depending on persona cues in the prompt. In this paper, we introduce Debias-SparseGPT, a post-training pruning method incorporating representational debiasing using a second-order term defined over demographically contrasting inputs. We perform empirical validation of our method over a wide range of generative LLMs. Across models and sparsity regimes (25%, 50%, and structured 2:4 sparsity), Debias-SparseGPT consistently reduces pruning-induced bias compared to SparseGPT while preserving model perplexity and zero-shot accuracy. Under the most restrictive 2:4 structured sparsity pattern, which most aggressively degrades model quality, augmenting the calibration set with long-context, content-rich examples further improves both downstream performance and fairness. Overall, Debias-SparseGPT advances the bias-performance trade-off while preserving the computational efficiency of sparse models.

Accurate scene understanding in confined, cluttered spaces such as shelves is essential for service robots, as many everyday tasks require them to locate and retrieve objects reliably. Yet, it remains challenging due to severe occlusions, restricted accessibility, and the need to avoid excessive scene changes. In this paper, we propose Multi-Skill Manipulation-Enhanced Mapping (MS-MEM), an evidential framework for uncertainty-aware mapping that integrates active viewpoint selection, object pushing, and grasping. MS-MEM combines scene-level metric-semantic evidential belief estimators with an uncertainty-aware grasp representation. This representation is learned using a novel full-evidential grasp estimator that models both grasp affordance and orientation uncertainty. In our framework, candidate perception and manipulation actions are evaluated within a unified action selection pipeline using a common information gain criterion. For manipulation actions, we further introduce a collateral disturbance constraint (CDC) that discourages excessive changes to confident regions of the scene belief. This enables MS-MEM to select actions that effectively reduce map uncertainty while limiting collateral scene changes. Experimental results show that, compared with single-skill and unconstrained baselines that ignore scene disturbance, MS-MEM achieves higher mapping accuracy while substantially reducing scene disturbance, highlighting the synergistic effects of active viewpoint selection, push, and grasp actions.

Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to identify document pages relevant to a user query, before answer generation by a Large Vision-Language Model (LVLM). Existing approaches typically retrieve a fixed top-$k$ number of pages regardless of query complexity, which increases LVLM latency and may degrade answer accuracy. We introduce ViSAR (Visual Semantic Activation Retrieval), a training-free adaptive-$k$ retrieval method for late-interaction visual document retrieval. ViSAR operates directly in the embedding space to construct a query-conditioned page-level similarity matrix that highlights query-relevant semantics and dynamically determines the number of pages to retrieve. Across multiple encoders and LVLMs, ViSAR retrieves compact, query-adapted page sets that reduce RAG latency by up to 58.7\%, while maintaining or improving answer accuracy compared with fixed top-$k$ and adaptive retrieval heuristics. Furthermore, we show that the similarity matrix structure correlates with answer accuracy, suggesting future directions for retrieval quality-aware document understanding.

In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusing on setting as one measurable dimension of storyworld construction. We compare 1,000 AI-generated stories per model in English and German with human-authored fiction from Project Gutenberg. Building on prior work, we operationalize setting through five types of narrative space: "action", "perceived," "visual," "descriptive" and "no space", identified using fine-tuned BERT classifiers for German and English. We generate narratives using GPT 4.1, LlaMA 3.3, Mistral 3.2, and Gemma 3 and compare their spatial distributions to a human-authored baseline. We find that human-authored texts predominantly employ "action space," grounding narratives in embodied character-environment interaction, whereas LLMs systematically overproduce "perceived space," emphasizing atmosphere and affect. This divergence remains stable across narrative time. Overall, our findings show that LLMs exhibit worldbuilding patterns that differ consistently from human-authored fiction in ways that are both model-specific and language-sensitive.

Synthetic dialogue generation can support research in privacy-restricted service settings, but generated conversations must preserve communicative intent, affective meaning, and natural dialogue flow. We introduce PragAlign, a feedback-guided framework for controlled synthetic dialogue generation conditioned on service context, target intent, and target emotion, with auxiliary trait-style controls. PragAlign uses a generate--evaluate--revise loop in which an LLM-based evaluator scores intent alignment, emotion alignment, coherence, fluency, and aggregate quality, then provides criterion-specific feedback for up to three refinement rounds. On 800 matched dialogue specifications, PragAlign achieves 99.50\% evaluator-defined acceptance, compared with 72.25\% for one-shot generation and 95.88\% for repeated generation without structured feedback. This indicates that repeated attempts account for much of the gain over one-shot generation, while structured feedback primarily improves last-mile multi-constraint satisfaction rather than broad average quality. Refinement gains are concentrated in emotion alignment, which is also the dominant failure mode in ablations. A separate human evaluation of 1,200 generated dialogues shows that intent expression and dialogue flow are highly recognizable to annotators, while emotion appropriateness is less stable and more subjective. These results support PragAlign as a quality-control framework for improving evaluator-defined communicative constraint satisfaction, while showing that affective realization and independent human-perceived quality remain open challenges.

Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLMs) can generate differential diagnoses from the same patient description, but their predictions lack an equally clear evidence trail. Rather than asking which system should replace the other, we ask whether an LLM can improve the ranker without giving up its evidence. Our behavior-based fusion model examines the two ranked lists, their agreement, and the ontology support behind each candidate, and learns how much to rely on each system for the individual case. Before comparison, we remove a documented test-set leakage pathway caused by benchmark cases and ontology annotations being derived from the same publications. Across eight open LLMs, fusion improves Phenomizer Recall@1 by 7.86 percentage points on Phenopacket Store and 20.18 points on RAMEDIS. When paired with DeepSeek-V4-Flash through an API, a fusion model trained only on the other LLMs improves Recall@1 from 0.1657 to 0.2176, a 5.19-point gain, without retraining. For 90.8% of correct fused diagnoses, the disease retains candidate-level ontology evidence that can be inspected. These results show that LLMs can strengthen an established diagnostic tool without discarding the structured evidence that makes it useful.

Target templates define what a visual tracker searches for, yet the templates available at inference trade off localization certainty with appearance freshness: the initial ground-truth template is exact but becomes stale, whereas recent templates better reflect the current appearance but are cropped from uncertain predictions. We quantify this bottleneck with a non-deployable oracle that supplies an exact current-frame target crop, improving AUC on LaSOT by 15.2 percentage points. This gap reveals a training-only opportunity: frame-level ground truths provide exact current- and future-frame target crops, although such crops are unavailable at deployment. We introduce Privileged Appearance Transfer for Tracking (PATT), a teacher-student training framework that transfers these privileged appearances to a deployable tracker through multi-level representation prediction. The privileged teacher observes exact target crops from past, current, and future frames, whereas the student receives only past-frame templates and learns to predict the teacher's search representations. To avoid transferring unreliable teacher signals, PATT weights this transfer by the teacher's relative localization advantage over the student and its absolute localization accuracy. After training, the teacher, latent predictor, reliability weights, and privileged crops are removed, leaving standard student-only inference. Across seven benchmarks at two model scales, PATT achieves consistent gains under both long- and short-term tracking protocols.

End-to-end autonomous driving in urban environments requires robust decision-making under partial observability and complex multi-agent interactions. Severe occlusions and dense traffic at intersections limit the perception capability of single-agent systems, motivating recent efforts on Vehicle-to-Infrastructure (V2I) cooperation for perception and planning. However, existing evaluation protocols face a fundamental trade-off: open-loop evaluation fails to capture error accumulation and recovery from deviations, while closed-loop evaluation is costly, difficult to scale, and often relies on simulated environments that may suffer from domain gaps. To bridge this gap, we propose VIPS, a benchmark for cooperative autonomous driving in V2I settings based on pseudo-simulation. VIPS extends pseudo-simulation by integrating vehicle and infrastructure observations. This enables scalable yet realistic evaluation of robustness and error propagation without full simulation. We further present CoS-V2X, a cooperative planning framework based on sparse representations. CoS-V2X models vehicle-infrastructure interactions using compact features for efficient communication and robust decision-making under heterogeneous observations. Code and dataset are available at https://vips2026.github.io.

We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol. Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns, agents do so only every 30 to 75 turns, and in 7 of 20 detectable defeats they failed to query within the 20 turn warning window before game end. Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp

Restoring images degraded by adverse weather remains challenging due to spatially heterogeneous degradations. Many existing weather-specific restoration models rely on weather-agnostic global aggregation, naive cross-scale fusion, and deterministic objectives, which struggle to handle heterogeneous degradations in all-in-one adverse-weather settings. To address these limitations, we propose an Uncertainty-guided Adverse-weather Restoration Network (UAR-Net), a weather-specific AiO framework that integrates a gated transformer with balanced multi-scale skip connections. Specifically, we employ Gated Dual-scale Transformer Blocks (GDTB) to jointly model selective global interactions and multi-scale local structures, a progressive Balanced Multi-scale Skip Connection (BMSC) for balanced multi-scale feature integration, and an Uncertainty-Aware Refinement Head (URH) that performs artifact removal, detail enhancement, and predictive uncertainty estimation. The model is supervised by a Brightness-Aware Energy Loss (BAE-Loss) to encourage accurate reconstruction with well-calibrated uncertainty. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple adverse-weather benchmarks. The codes will open source upon acceptance.

Broad Learning System is an efficient randomized learning model that expands network width through feature and enhancement nodes and estimates the output weights without deep backpropagation. Its standard least-squares training, however, is vulnerable in two different ways: (i) large residuals caused by noise, outliers, or corrupted labels can dominate the objective, and (ii) all samples are treated as equally reliable even when some lie in ambiguous or locally conflicting regions. This paper proposes IFW-BLS, an Intuitionistic Fuzzy Wave Broad Learning System that addresses these two sources of fragility within one optimization model. The first robustness mechanism is residual-level protection, obtained by replacing the squared loss with the bounded, smooth, and asymmetric wave loss. Boundedness prevents extreme residuals from receiving unbounded influence, while asymmetry allows positive and negative deviations to be penalized differently when the dominant error direction varies. The second mechanism is sample-level credibility control, obtained through intuitionistic fuzzy scores that combine global class-center consistency with local neighborhood conflict. The resulting model evaluates the wave loss on credibility-weighted residuals, so unreliable samples are down-weighted before the bounded loss further limits the effect of extreme errors. A Nesterov accelerated gradient based optimizer is used to solve the proposed objective, avoiding the explicit matrix inversion used in conventional BLS. Experiments on UCI benchmark datasets validate the superiority of the proposed IFW-BLS model over the baseline models; additional corruption experiments also show more stable performance than BLS under noise and outlier contamination.

Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected stochastic delays frequently inval- idate otherwise feasible schedules. Existing benchmarks like TravelPlanner and TripCraft assume deterministic environments, evaluating only static constraint satisfaction and ignoring whether generated plans remain robust when such uncertainties arise. To address this limitation, we introduce UTP-Bench1 , a large-scale benchmark for uncertainty-aware travel planning. The dataset integrates real-world travel data spanning 504 cities of India, including attractions, restau- rants, accommodations, and multi-modal trans- portation networks. To model realistic disrup- tions, UTP-Bench incorporates empirical delay distributions and crowd-density patterns col- lected from major cities, enabling evaluation of travel plans under stochastic conditions. We further propose three evaluation metrics, namely Buffer Adequacy Score (BAS), Crowd- Aware Timing Score (CATS), and Transport Delay Absorption Score (TDAS), which quan- tify the ability of generated itineraries to main- tain robustness against transit delays and crowd variability. Experiments with state-of-the-art LLMs like GPT-5, Qwen3, Mistral and Phi-4 re- veal substantial gaps between model-generated and human-authored plans, particularly in tem- poral buffering, delay-aware transportation scheduling, and crowd-sensitive planning.

Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattered. We identify the structural quantity that predicts when this is the right move, the verifier information density V_d = k/C (the fraction of an agent's C-step causal chain whose per-turn correctness the verifier exposes), and show that terminal-state verifiers sit deep in a low-V_d regime where targeting is the wrong axis. In controlled shared-rollout comparisons on tau^2-bench that separate reward density from credit geometry, a continuous dense reward spread uniformly beats the sparse binary outcome reward (net-harmful on 4/5 seeds), while concentrating the same advantage on progress turns or on random turns is equally harmful: targeting is second-order. The mechanism is coverage: terminal-state verification collapses the observable signal to a single final-write turn (k=1 in 98% of rollouts) while success requires a 5-8 step chain of prerequisite tool calls. A synthetic phase boundary places the crossover at V_d* ~ 0.8, whereas measured V_d is ~0.15 on tau^2-bench and ~0.4 on BFCL V3; uniform also wins on BFCL, where a matched-concentration shuffled control is negative on 8/8 seeds. The effect reproduces across model families on ToolACE-2-8B (Delta = -0.048 over 32 pre-registered seeds; an independent 20-seed replication is itself significant), and a pre-registered matched-budget breadth sweep traces a monotone dose-response whose deficit vanishes only at full chain coverage, with a reward-to-go arm reaching full-coverage parity. Uniform redistribution is the zero-information coverage default that per-turn schemes must beat; we contribute the matched-concentration shuffled control that any targeting claim should clear.

Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mechanisms drive vulnerability. We introduce BLUEPRINT, a safety-evaluation framework separating a factorized social-influence strategy space from WORLDVIEWSIM, a cross-turn situational context module. Monte Carlo Tree Search optimizes turn-level combinations of 18 theory-grounded influence factors across a four-turn trajectory. Across six frontier models, BLUEPRINT achieves near-ceiling ASR on major open-weight and proprietary models, while requiring the fewest average queries (2.46). The resulting trajectories further reveal model-specific vulnerability among resistant targets: each responds to distinct influence factors and strategy transitions, yet all share a common recovery pathway-shifting toward concrete, executable task framing consistently escapes hard-refusal states. Ablations confirm operational cues matter most: making requests actionable has the largest impact, gain framing is unusually potent, and some legitimacy appeals can backfire. These findings suggest robust multi-turn safety requires monitoring not only harmful content, but also how dialogue state makes unsafe requests appear concrete and locally executable.

Conventional task-level evaluation asks whether a robot policy completes a specified action, but can miss failures that emerge only during physical human contact. This limitation is critical in contact-rich assistive tasks, where meaningful evaluation requires a physically responsive human, interaction-quality assessment beyond task success, and a leak-free observer-scorer protocol. We introduce a physics-consistent benchmark for contact-rich human-robot interaction, instantiated in robot-assisted bathing. The benchmark combines a deformable, passively responding human, physics-aware scores alongside task-level success, and a frozen vision-only / scorer-only evaluation protocol. To establish physical validity, region-wise simulated responses are calibrated against force-indentation measurements from Franka impedance pushes on a medical-care manikin. Under a frozen T1-T7 protocol with 140 runs per method, an LLM-augmented state machine (State Machine) achieves 72.9% task success but drops to 56.4% after correct-region and force-safety screening; VoxPoser produces lighter and more stable contact but completes only 27.9% of trials; and zero-shot pi0.5 achieves 0.7% task success with no correct-region or safety-gated successes. These results show that task completion alone does not imply physically valid contact and motivate physics-aware screening before deployment of contact-rich assistive robot policies.

Autoregressive vision language models unify heterogeneous perception tasks but are highly susceptible to compounding errors. On-policy distillation (OPD) bridges the training-inference mismatch by training students on their own rollouts. However, unreliable student predictions, especially early in training, can derail the trajectory and degrade the quality of teacher supervision. While recent interleaved distillation methods allow the teacher to verify and replace student tokens, they primarily rely on rigid ranking metrics rather than exact teacher confidence, and they overlook how intervention decisions can inform token-level supervision. To address this, we introduce Confidence-Aware On-Policy Distillation (CA-OPD), a framework that couples reliable rollout construction with adaptive supervision. CA-OPD utilizes teacher confidence to selectively correct unreliable student transitions, gradually transferring rollout control to the student via a strict-to-relaxed schedule. Crucially, CA-OPD aligns knowledge transfer with these intervention decisions: corrected positions receive direct cross-entropy supervision from the teacher's prediction, while retained positions benefit from the teacher's full predictive distribution. Evaluated in a multi-teacher setting for GUI grounding and optical character recognition, CA-OPD substantially improves the Qwen3.5-0.8B baseline across all six target benchmarks, including gains of $9.50$ points on ScreenSpot-Pro and $6.72$ points on OCRBench-v2 English. Controlled studies further show that the gains depend on intervention placement, progressive rollout control, and intervention-aligned supervision, rather than intervention frequency alone.

Radiology reports are written primarily for clinicians, and their specialized terminology often makes them difficult for patients to interpret. As a result, many patients turn to publicly available Large Language Models (LLMs) to help explain their reports, despite well-documented risks of factual inaccuracies and hallucinations. Automated lay-summary generation has emerged as a promising alternative, yet the effectiveness of retrieval-enhanced and clinically informed approaches for radiology-specific communication remains underexplored. This study investigates the extent to which Retrieval-Augmented Generation (RAG) and Named Entity Recognition (NER) improve the quality, factual consistency, and readability of automatically generated lay summaries compared with standard LLM-based generation. We develop a framework combining NER-based extraction of clinically relevant findings with a RAG mechanism for contextual grounding, evaluated across few-shot and fine-tuned variants of two models (Qwen, BioBART). Results show that NER consistently improves readability and overall quality, while RAG alone offers no benefit and can introduce hallucinations from irrelevant retrieved terms. Combining RAG with NER degrades performance in few-shot settings but improves readability when fine-tuned. Fine-tuned BioBART with NER achieves the best overall performance, highlighting entity-aware extraction as the primary driver of improved patient-friendly summaries.

Sampling error yields exclusively reactive, non-lesional brain parenchyma in a significant proportion of intracranial biopsies, leaving the underlying disease undiagnosed. We benchmark four pathology foundation models (UNI2-h, Virchow2, Prov-GigaPath, H-optimus-0) as frozen patch encoders within a shared attention-based multiple-instance learning framework using 245 whole-slide images from 186 patients with confirmed downstream diagnoses. We first show that coarse disease-category prediction can be reproduced largely from slide size alone. After restricting classification to three finer diagnostic distinctions within common tissue categories, this confound no longer explains performance, yet disease labels remain predictable above chance under permutation testing (p $\le 10^{-4}$ throughout). Surprisingly, performance is statistically indistinguishable across all foundation-model encoders, suggesting that recovering these weak morphological signatures is not limited by current patch representations. Signed instance-contribution maps and expert review further test whether predictive evidence localizes to reactive parenchyma rather than sampling-induced bias like blood introduced during tissue sampling. These results position acquisition-shortcut auditing via a provenance-only baseline as a necessary control in computational-pathology benchmarks, and show, once that confound is removed, that weakly supervised models still recover disease signal from tissue conventionally regarded as non-diagnostic.

While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled settings, or relatively outdated models, with the few multilingual studies considering only relatively short texts. We introduce MultiGhostBench, a multilingual benchmark comprising 928 books generated by five recent LLMs across six languages and three scripts, with an average length of approximately 59K words per book. The benchmark supports evaluation under domain, author, and language shifts. Evaluation of representative AA methods shows that no single method consistently performs best across settings, and performance generally degrades under distribution shifts. Transformer-based detectors can retain generator-related information across languages, although transfer effectiveness varies by language pair, whereas statistical and fingerprint-based detectors are more language-dependent. We envision MultiGhostBench as a valuable resource for the development and evaluation of robust AA methods. The dataset and code can be found at https://github.com/GrecoMT/MultiGhostBench.

High-resolution Synthetic Aperture Radar (SAR) imagery is critical for precision analysis such as automatic target recognition, yet its acquisition is costly. Although generative image super-resolution (ISR) models offer a promising alternative, current smooth-approximation based diffusion frameworks often struggle to preserve the coherent scattering statistics, causing stochastic structural distortions that are less consistent with real SAR physics. To address this, we propose Semantic Prototype-Guided Super-Resolution (ProSR), reformulating SAR ISR as a semantically-guided discrete token prediction task within a quantized latent space. By mapping signal features to discrete scattering primitives, ProSR preserves the impulsive nature of SAR without over-smoothing. Furthermore, we integrate a Self-Supervised Learning backbone into SAR ISR to extract label-free semantic priors, overcoming label scarcity. Guided by these priors, we introduce Semantic-Aligned Detail Encoding to decouple high-frequency signals into discrete scattering primitives. In parallel, the Semantic Prototype Map Generator explicitly constructs semantic prototype maps, allowing Prototype-Map-Guided Attention to route the information flows within identical categories and mitigate inter-class interference. To validate our approach, we present a large-scale 0.25m resolution benchmark from the Umbra Open Dataset. Experimental results show ProSR achieves superior visual quality while preserving essential scattering characteristics required for practical SAR applications.

With the proliferation of LLM agents, the ability to understand and diagnose failures in agents is essential to achieving superior effectiveness and trustworthiness. As agent failures often manifest via long and complex trajectories, manually finding the needles in the haystack is untenable. However, traditional diagnosis techniques for software bugs can hardly address LLM agent failures, while completely relying on LLMs as the judge yields unreliable diagnosis results. To overcome these challenges, this paper presents AGENTSCOPE, a new neuro-symbolic approach for agent failure mode diagnosis. The key principle of AGENTSCOPE is to abstract agent behavior, based on its trajectories, into structured representations. Furthermore, AGENTSCOPE introduces the concept of neural invariants to specify agent behavior properties. AGENTSCOPE leverages LLM-guided reasoning atop the structured representation against neural invariants to pinpoint both the failure step and its type in the trajectory. We show the effectiveness of AGENTSCOPE on publicly available agent failure datasets (Who&When) and a more comprehensive dataset created by us (AgentErrata), where AGENTSCOPE significantly outperforms the current state of the art in fault localization and attribution accuracy. Our work shows that integrating structured abstractions with LLM-guided reasoning enables effective, reliable, and interpretable diagnosis for agent failures.

Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of long-tail and domain-specific entities remains challenging due to the deficiency in parametric knowledge. Retrieval-augmented generation (RAG) offers a promising remedy by injecting external knowledge, but it also introduces noise and unnecessary cost when dealing with familiar cases. In this paper, we propose NE-R1, a novel framework for adaptive retrieval-augmented NER. We design a "retrieval-on-demand" mechanism for NER. Then we integrate it into models by a two-stage training method: (1) multi-task instruction tuning initialization; (2) end-to-end RL optimization with CoT. To achieve reasonable selection between parameterized and external knowledge, we design a multi-dimensional reward considering both accuracy and retrieval benefit. NE-R1 achieves state-of-the-art performance on various benchmarks, with an average F1 score gain of 2.52% in in-domain evaluation and 1.18% in zero-shot cross-domain evaluation.

Visual grounding maps language referents to spatial targets and is central to open-vocabulary perception with vision-language models. Existing methods have made substantial progress on single-frame and video-based visual grounding, yet under streaming inputs they still suffer from identity drift, cross-frame inconsistency, and fragile localization under partial occlusion. To address these issues, we present TempoGround, a VLM-native framework that detects cross-frame object correspondence and explicitly models object presence states, thereby enabling accurate and consistent visual grounding under streaming inputs. The key is a curriculum prediction mechanism guided by state-aware cross-frame correspondence: TempoGround resolves 2D instance association, predicts whether each object newly enters, continues in, or leaves the view, decodes the 2D box, and then lifts it to a camera-frame 3D box. As token-level supervision alone cannot capture the geometric objectives of streaming grounding, we further introduce Streaming Grounding Reinforcement (SGR), which optimizes TempoGround with verifiable Grounding, Identity, and Consistency rewards, jointly reinforcing persistent localization and temporally consistent predictions. We carefully design a three-stage training strategy and train TempoGround on large-scale data. We evaluate visual grounding under causally streaming inputs on multiple challenging benchmarks: TempoGround improves [email protected] and [email protected] by 4.4 and 0.5 on average, and [email protected] and AP_3D by 6.2 and 7.5, respectively. These results demonstrate that TempoGround provides a practical foundation for visual grounding under streaming inputs.

Humanoid robots responding to emergency stop commands typically execute a fixed maneuver, without reasoning about whether a safe stop is actually feasible from the current state. We cast emergency stopping as a reach-avoid problem and propose Safe-Stop, a task-agnostic framework that pairs a learned stop policy with learned stoppability estimators. The estimators are complementary: a stop-probability estimator supervised by the actual outcomes of the fixed stop policy, and a reach-avoidance estimator supervised by a Hamilton-Jacobi backup over physical state. The first captures emergent stopping behavior of the learned controller; the second provides a complementary recoverability signal. Because the stop policy and estimators do not depend on the behavior policy that preceded the stop command, they transfer across diverse upstream tasks without retraining. At deployment, the two estimates are combined: Safe-Stop commits to the stop only when both estimators indicate that stopping remains feasible, otherwise it hands off to a fall policy, instantiated as a damping fallback. This agreement check yields decisions that are robust without sacrificing reactivity.

Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions in unseen environments. Recent progress has been largely driven by Multimodal Large Language Models (MLLMs). Existing methods follow a next-step action prediction paradigm, supervising only the expert action, which requires a high quantity of data for training. They also rely on cognitive maps, accumulated historical frames, or external 3D tools to maintain states, leading to high computational and memory overhead. To realize resource efficiency VLN, we propose LookStep, a unified end-to-end framework that combines Language Centric Future State Modeling and Event Driven Rolling Memory that uses language labels to generate coarse-grained navigation progress and future states for each candidate action, while autonomously deciding whether to write each observation into a bounded rolling memory with a semantic role. We validate LookStep empirically. On VLN-CE tasks, LookStep outperforms existing methods under the same training settings, achieving a 49.7\% success rate on R2R-CE Val-Unseen with better memory efficiency and less data usage. Code and model is available at https://github.com/kunyang-YU/LookStep.

Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arranged text or rare characters. Existing approaches either improve native text rendering through stronger backbones and data-centric training without explicit glyph priors, or incorporate glyph priors through specialized designs that remain insufficiently accurate and robust under challenging scenarios. We introduce GlyphAnchor, a novel text-rendering enhancement method for both text-to-image and image-editing diffusion transformer models. GlyphAnchor enhances the backbone with lightweight glyph patch conditions whose positions are anchored to the target image through the model's native positional encoding. We train this capability with staged supervised finetuning and further refine it with text-aware post-training to improve robustness. We also introduce InfoTextBench, a benchmark for evaluating text-rich visual text rendering in both generation and editing settings. Experiments across multiple backbones and benchmarks, including long, complex, and densely arranged text and rare character scenarios, show that GlyphAnchor consistently improves text fidelity while preserving overall image quality.

Recent advances in audio-language modeling have been driven by large-scale audio captioning datasets. However, existing datasets remain limited by low semantic diversity, generic descriptions lacking acoustic details, and one-to-one audio-caption mappings that poorly reflect the inherent ambiguity of auditory perception. We introduce SonicCaps, a large-scale audio captioning dataset comprising ~15M captions paired with ~700k audio clips, generated using a multi-modal large language model (Qwen3-Omni) conditioned on both audio and text. To explicitly promote diversity, we generate around 24 captions per audio via structured prompt engineering and few- shot generation, spanning main descriptions, rephrased variants (verbosity, style) and semantic tags. Human evaluation shows that SonicCaps is rated significantly higher than existing captioning datasets, with fine-grained analyses indicating that our captions are perceived as more descriptive and precise, which strongly correlates with quality judgments. Finally, training CLAP models on SonicCaps with a multi-caption sampling strategy consistently improves audio retrieval and zero-shot classification, with stronger generalization across public and commercial benchmarks. We release both SonicCaps and two specialized CLAP models on hugging face: https://huggingface.co/datasets/Zineb/SonicCaps.

Vision-Language-Action models (VLAs) have shown strong potential in autonomous driving by leveraging multimodal pretraining for instruction following, visual reasoning, and scene-level generalization. In robotic manipulation, scaling VLA fine-tuning across multiple robot setups--especially when unifying representations across embodiments--has been shown to improve in-dataset performance and cross-embodiment generalization; in autonomous driving, however, VLAs remain largely trained on individual datasets and are rarely evaluated for zero-shot transfer to unseen datasets and camera rigs; furthermore naively adding more datasets to the training data does not necessarily lead to better performance within seen embodiments. To address these problems, we study multi-dataset training for the driving task and BEV-Forcing, an auxiliary objective that transfers ground-plane object-layout information from a specialized Bird's-Eye-View model into the VLA backbone. By encouraging the model to represent object position through a shared BEV spatial interface, we show that an auxiliary task such as BEV-Forcing can improve both in-distribution and out-of-distribution performance when training on a small number of camera rigs. As the number of training embodiments increases, however, the benefits of the auxiliary task are reduced; we present this as evidence that new techniques in the literature may see their benefits diminish when simply scaling up training diversity, which motivates presenting results taking into account data scaling.

World modeling requires a predictive model to maintain and update an internal state adequate for reasoning about the consequences of actions. We introduce the AGI Maze Prediction Datasets and Benchmark, a lightweight controlled testbed for studying this capability in Transformers and other predictive models. Derived from procedurally generated, stateful grid worlds, the benchmark comprises per-step transition prediction, fixed-horizon state prediction, and sequential textual-observation prediction. Source-maze-disjoint training and validation splits, together with greedy exact-match evaluation, distinguish learning transferable action-conditioned dynamics from memorizing transitions in familiar layouts. We establish from-scratch byte-level Transformer baselines and compare them with two working-memory-augmented architectures. A generic auxiliary latent-memory Transformer can fit some training sets perfectly but does not consistently improve held-out performance. In contrast, a pseudo-video spatial-memory Transformer initializes a two-dimensional latent workspace from the input map and updates it from action history without receiving intermediate maps, positions, or state labels. Under the same data, objectives, and evaluation protocol, this model reaches perfect validation accuracy on selected fixed-horizon tasks where the byte and unstructured-memory baselines do not, and substantially improves sequential text-trace prediction. These results suggest that structured, task-aligned working memory can be more useful than additional latent capacity alone. More broadly, we argue that language grounding is mediated by persistent data structures and computations over them; the benchmark offers a compact setting for testing architectures that couple textual interfaces to learned structured state.

Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface similarity fail to capture the underlying problem-solving logic. Recent logic-based methods address this by matching predefined reasoning steps, but the rigid rules and exact-match criteria is improper to handle flexible or diverse reasoning processes. To address the problem, we propose SALA, a Semantic-Aware Logical Alignment framework. Instead of relying on a fixed inventory, SALA automatically learns task-specific reasoning operations. It then embeds these operations into a continuous semantic space and uses dynamic time warping (DTW) to align the reasoning sequences. This approach allows for soft, flexible matching of reasoning logic while remaining highly interpretable. Experiments across four reasoning benchmarks and three LLMs demonstrate that SALA outperforms existing demonstration selection methods. Further analysis confirms the roles of the operation induction and the logical semantic alignment.

The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at all. We frame this problem as continual model construction: an agent maintains an environment-specific model M of an inaccessible world W and curates a persistent library L of reusable representational elements across environments. We propose Representational Empowerment (RepEmp) to score candidate elements by how much they expand the agent's future capacity to model and plan, complementing the classic definition of empowerment, but redefined as control over internal representations instead of external states. We realize the framework as a hierarchical Curator-Actor architecture and test it across three experiments. In a closed-vocabulary causal-learning task, human participants construct causal models at varying abstraction granularities to maximize goal reachability rather than fidelity to the world, a signature better predicted by RepEmp than by information-gain alternatives. Matched simulations reveal that RepEmp-guided construction contributes more than exploration to sufficient structure recovery and cross-task transfer. Finally, in an open-vocabulary planning domain, an LLM-augmented Curator builds more compact symbolic libraries, which also generalize better than baselines. Ablating RepEmp eliminates these benefits. Together, these results identify RepEmp as a key principle for continual model construction: deciding what to build, retain, and reuse under bounded resources.

Generative engine optimization (GEO) enables content producers to increase the visibility of their web pages in generative search engines, but the same techniques can deliver targeted misinformation when adversaries publish ordinary-looking GEO-optimized documents that victim large language models (LLMs) retrieve and synthesize into distorted answers. No existing benchmark evaluates defenses against this threat under controlled conditions. Therefore, we present Counter-GEO-Bench, a defense benchmark that pairs 247 human-verified, quality-gated queries with information-preserving and information-distorting GEO rewrites, and evaluates defenses on attack success rate (ASR), false positive rate, and answer quality across three victim LLMs. Under Counter-GEO-Bench, three off-the-shelf defenses (Granite Guardian, Llama Guard 3, and NeMo Self-Check Fact-Checking) reduce ASR by at most 5.7% relative, while Granite Guardian's reduction is not statistically significant. Safety-taxonomy guardrails target policy violations, while GEO misinformation passes through them as fluent informational content. To this end, a lightweight benchmark baseline, C-GEO Guard, is proposed, reducing ASR by 47.6% relative with near-zero utility loss, which proves threat tractable.

A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction, which is efficient but couples the extraction budget to training. We introduce DIFFIE which instead treats the stochasticity of conditional discrete diffusion as the extraction mechanism itself: independent reverse-diffusion trajectories over per-token role tags produce a pool of candidate triplets, which are clustered under lenient matching and ranked to form the output. Both the pool size and the number of returned extractions are inference-time choices, decoupling the extraction budget from training and exposing test-time compute as a tunable axis. DIFFIE achieves the new state of the art in CaRB (1-1) both F1 and AUC, and outperforms the strongest rule-based system (ClausIE) in BenchIE; it also remains competitive in standard CaRB and WiRe57 evaluations, giving the best average score among systems that report all four benchmarks. Ablations show that uniform discrete diffusion outperforms absorbing state diffusion in our setting, and that a matched non-diffusion stochastic tagger does not reproduce its gains. Our results indicate that diffusion stochasticity is an effective mechanism for structured prediction tasks with multiple valid outputs.

GUI agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task success. We argue that practical deployment depends equally on efficiency: how much context, computation, action budget, and runtime overhead an agent consumes while succeeding. This survey studies efficient GUI agents through an end-to-end systems lens that preserves the current technical axes of observation efficiency, context and memory efficiency, action efficiency, and planner-side/system efficiency. For each subsection, we expand the seed literature through targeted search plus backward and forward citation chaining, then synthesize the dominant mechanisms, reported efficiency signals, and new overheads they introduce. Across the literature, recent progress converges on a small set of recurring ideas: selective reading instead of full-context ingestion, global-to-local visual allocation, recoverable memory rather than raw history replay, verification-aware control, and hybrid runtimes that can switch between GUI and non-GUI execution. We conclude by identifying the main open problems, including honest accounting of verifier cost, cross-benchmark comparability, and co-design of observation, memory, and execution layers under real latency and privacy constraints.

Accurate joint encoder offsets are essential for kinematic consistency in humanoid lower limbs, yet existing calibration methods typically require external motion-capture systems or fiducial targets. We present a self-contained calibration framework exploiting only onboard joint encoders and a pelvis-mounted IMU during static double-support contact. The inter-foot transform from forward kinematics must stay constant when both feet are fixed; minimizing its posture-dependent dispersion yields a nonlinear least-squares problem over the 12-dimensional offset vector. A Hessian eigenstructure analysis shows that parallel pitch axes induce a rotational coupling. Orientation residuals then observe only the pitch-offset sum, while translation and posture diversity set the remaining numerical observability. For the A3 pitch-to-roll-to-yaw ordering, hip-roll and hip-yaw excitation reduce hip-pitch coupling. A standing-posture knee prior then anchors the remaining weak pitch-chain decomposition. Simulation and real-machine injection tests show consistent recovery, and on held-out recordings calibration reduces foot-height RMS residuals from 4.26 to 2.20 mm on A3 and from 8.03 to 1.43 mm on A2. An independent LiDAR-inertial reference checks the pitch-coupled channel. Removing an injected pitch offset moves the leg-odometry vertical drift back toward the LiDAR trajectory. A few static double-support stances thus provide contact-consistent corrections for well-excited directions. Individual offsets in the weak pitch chain remain prior-dependent.

A core obstacle to alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the conclusions a safety evaluation can support. We present two techniques that make simulated alignment evaluations harder to distinguish from real deployments. Our first technique, critique refinement, spends additional inference-time compute on each simulator action: the simulator generates multiple candidate actions, refines them using feedback from an instance of the target model on how to make them more realistic, and continues the evaluation with the most deployment-like candidate. Our second technique, DISH (Deployment-Imitating SWE-Agent Harness), wraps the target in an agent harness, reducing the gap between simulated and real deployment environments in coding settings. We test the techniques on multiple target models and find that they compose: applying both yields larger realism gains than either alone. Our results show that automated approaches can improve the realism of alignment evaluations, and that these improvements use additional compute more effectively than making the audits longer.

Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling massive parameter growth with nearly constant computation. Recent Hybrid MoE architecture adds \textit{shared experts} to capture consistently useful representations, further improving stability and generalization. MoE now powers many flagship open-source and commercial models, yet remains vulnerable to adversarial attacks. Specifically, sparse routing introduces a structural vulnerability: MoE safety hinges on which experts are activated, and adversaries can subvert this selection through jailbreak prompts, malicious fine-tuning, and weight-level pruning of safety-critical neurons. Existing defenses primarily focus on hardening the router, but an adversary may still manipulate or bypass the routing trajectory due to the routing process's nondeterministic nature, thereby collapsing the defense. To cope with this problem, we first identify theoretically and empirically that shared expert, an always-activated component containing a small proportion of safety-critical neurons, can overcome the uncertainty of sparsely activated routing path and serve as a router-independent anchor to enhance global safety alignment. Based on this insight, we propose SEAL, a training-time parameter-efficient defense that produces a plug-and-play adapter attached to shared expert, and SEAL++, a variant that adds an orthogonal constraint preserving pre-existing safety subspaces during training. We evaluate SEAL and SEAL++ across six attack scenarios that combine three adversarial inputs (harmful prompting, jailbreak, malicious fine-tuning) with and without neuron pruning. SEAL reduces attack success rate (ASR) by up to 60\%, at a capability cost of at most 1.4\% on a five-benchmark average. Additionally, SEAL can seamlessly integrate with router-level ......

The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: selecting the right model for the task, while optimizing for speed, cost, and quality at a per-task level. However, inference endpoints can vary widely in quality, price, latency, context support, tool use, domain expertise, and reasoning behavior. This heterogeneity makes manual heuristics difficult to maintain and unlikely to achieve consistently favorable speed--cost--quality trade-offs on their own. We introduce \router{}, a lightweight GLiClass-based router that assigns a suitability score to each inference-time model label without autoregressive generation. The released 0.6B-parameter checkpoint combines a Qwen3 decoder with a shallow bidirectional scorer. Its decoder-KV execution path preserves a text-only key--value cache across a session, encodes only new dialogue turns, and evaluates transient candidate-label tokens without adding them to the persistent cache. The same checkpoint also predicts task type, difficulty, reasoning mode, and expected output length, and supports custom zero-shot labels. For task generation, we construct a task ontology with 23 families, 115 task types, 345 routable subtypes, 1,173 synthetic examples, and an orthogonal axis of 30 domains. Using this structure, we generate 150,000 verifier-scored tasks and 15,000 open-ended tasks. We then train the Qwen3 decoder on these tasks, while explicitly separating learned request prediction from per-task policies for attributes such as eligibility, cost, cache reuse, safety, and sovereignty. Across six LiveBench subsets, the router outperforms the mean candidate; on the selected 1,000-task subset, it achieves an aggregate top-1 score of 0.707 versus 0.696 for the strongest fixed model, with benchmark-dependent gains.

Perceptual illusions have long served as crucial probes into human cognition, revealing biases and limitations of perception. In the auditory domain, such illusions provide a unique lens for testing whether Large Audio Language Models (LALMs) replicate human perceptual tendencies. Despite their importance, most benchmarks focus on visual illusions or general audio tasks, leaving auditory illusions underexplored. To this end, we present AIB, the first auditory illusion benchmark for LALMs, covering ten representative illusions across music, sound, and speech, each annotated for the presence of knowledge-based priors. Our methodology pairs model evaluation with controlled human listening studies, enabling direct comparison of responses. Results show systematic differences: while most LALMs remain signal-faithful on low-level acoustic illusions, several exhibit more human-like responses when linguistic or musical priors are involved, although no model matches the human perceptual profile. These findings highlight the current limitations of LALMs as cognitive models. By establishing auditory illusions as a rigorous testbed, our work offers a new perspective for probing neural black-box models and advancing understanding of auditory cognition. AIB is publicly available at https://github.com/gillosae/aib.

Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%).

Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an agent must distinguish genuine preference drift from temporary context shifts, ambiguity, or adversarial memory poisoning. We formulate this problem as a continuous-time partially observable decision process over a latent user state and show why rules based only on recency and provenance are insufficient. CAPTURE addresses this ambiguity with a neural differential-equation belief tracker, a multi-timescale memory ledger, uncertainty-triggered clarification, and counterfactual auditing of cited memories. On 480 held-out episodes from 96 users, CAPTURE achieves a 71.5% win rate, compared with 69.3% for an identically supervised baseline and 66.1% for the strongest heuristic baseline. It limits fixed-policy poisoning success to 11.5% while accepting 83.5% of genuine preference updates. Under an adaptive attacker with access to the released weights, attack success rises to 24.7%, exposing a real adaptation-security tradeoff. We further evaluate the frozen system zero-shot on an independently constructed benchmark and replay longitudinal interaction histories from 40 users collected over two to three weeks. These results suggest that modeling preference authenticity explicitly can improve both personalization and robustness in memory-augmented LLM agents.

Adapting the communication topology of an LLM multi-agent system to each query improves both accuracy and efficiency, yet current designers treat this as conditional graph generation: a variational, autoregressive, or diffusion decoder searches the $N \times N$ adjacency space, and a graph-network proxy trained on utility and a structural cost such as edge count ranks the sampled candidates. We argue that this formulation is misaligned with the problem. Empirically, topologies that survive a reward filter collapse to about six distinct graphs even when the codebook capacity grows from 8 to 64; edge count is negatively correlated with measured token consumption (Pearson $r \approx -0.4$), so sparsifying the graph makes inference more expensive; and a message-passing scorer over agent-profile nodes is adjacency-invariant whenever agents share a profile---the default configuration of published benchmarks---so it cannot rank candidates at all in that regime. These three facts motivate Codebook Agent: a vector-quantized autoencoder compresses successful topologies into a query-independent 16-entry codebook; a reward-weighted MLP maps the query embedding to a distribution over codes; and an MLP proxy that reads the flattened adjacency, regressed on measured utility and per-task normalized token cost, reranks the top decoded candidates in a single batched forward pass. With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks we compare (84.6 average against 83.0 for the strongest prior designer), emits a topology in 2.4 ms, and uses 21.9--33.2% fewer LLM tokens.

Recent text-to-image models have become increasingly capable of rendering explicit text, but reliable localized text control requires more than generating the correct string. In applications such as product labeling, signage, and interface design, target text should be rendered within a designated text-bearing region without altering the predefined subject identity or surrounding scene semantics. We refer to violations of this requirement as target-text-associated semantic leakage, in which target-text semantics are expressed through non-textual visual content beyond the designated anchor. Existing visual-text benchmarks primarily evaluate readability, spelling accuracy, and layout, leaving this form of semantic leakage largely unexamined. We introduce T2LSC-Bench, a controlled diagnostic benchmark comprising 50 seed subjects and 1,200 prompt cases per model, yielding 7,160 evaluated images across six models. Its factorized design varies semantic relation, scene openness, prompt mode, and language. A dual-branch protocol combines OCR-VLM text verification with structured VLM semantic judgments to measure Text-at-Anchor Accuracy (TAA), Semantic Subject Preservation (SSP), Semantic Leakage Rate (SLR), and Conditional Semantic Leakage Rate (cSLR). Under stress-test conditions, SLR increases from 1.2% to 18.1% and cSLR from 1.3% to 18.2%, whereas TAA decreases only from 91.4% to 90.9%. Anti-leakage prompting reduces SLR from 16.6% to 8.4% without degrading rendering accuracy. Human validation on 420 images shows strong agreement between automatic and adjudicated annotations. These results show that accurate text rendering does not guarantee local containment of target-text semantics.

Deep research agents augment large language models with external tools to answer complex, long-horizon questions through multi-turn reasoning. Learning from prior experience is crucial for continual improvement, yet existing methods either retrieve verbose task-specific traces that burden decision-making, or distill procedural skills that remain decoupled from downstream policy adaptation. We propose APEx, a hierarchical experience utilization framework that organizes interaction history into instance-level trajectory memories and category-level procedural skills, and couples them through a closed-loop architecture of Executor, Distiller, and Planner. The three modules are optimized via a three-stage alternating GRPO training paradigm, enabling reward-guided skill distillation rather than fixed-prompt generation. At test time, distilled skills serve as procedural priors for online Planner adaptation through skill-guided test-time reinforcement learning, allowing ground-truth-free self-improvement with skill-alignment regularization to prevent policy drift. Experiments on 7 benchmarks demonstrate that APEx achieves state-of-the-art performance, surpassing GPT-5.4 by 14.7 points and the strongest memory-augmented baseline by 3.0 points.

In trajectory planning for autonomous driving, hybrid planning architectures are often realized as a collection of disparate modules, each with its own objectives. This lack of a unifying principle can lead to inconsistencies between the initial and refined trajectory, resulting in suboptimal behavior. We address this by introducing DiffuSearch, a novel hybrid planner that uses a unified set of objectives across generation and refinement. Our model encourages all components to follow the same shared driving goals: collision avoidance, drivable area compliance, comfort, and progress. DiffuSearch employs a two-stage architecture. First, a guided diffusion model generates a scene-consistent, joint trajectory prediction, using our driving objectives as differentiable guidance functions to implicitly steer the denoising process. Second, a Monte Carlo Tree Search (MCTS) in a discretized action space performs an explicit, local refinement of this proposal, leveraging the same driving objectives as its reward function. This synergistic design leverages the diffusion model's strength in finding scene-consistent solutions combined with the explainable, constraint-aware refinement of MCTS. Experiments on nuPlan and interPlan reactive closed-loop benchmarks demonstrate that DiffuSearch achieves strong and often state-of-the-art performance, substantially reducing collisions and improving comfort, particularly in complex, interactive scenarios. Our ablation studies indicate that MCTS refinement is the main mechanism behind the gains, while sharing objectives between implicit guidance and explicit search provides further consistent improvements.

Ride-sharing, which allows multiple passengers with different origin-destination (OD) pairs to share a single vehicle, is a challenging operational problem, as it requires orders with different OD pairs to be efficiently bundled and assigned to vehicles under uncertain and varying scenarios. Although multi-agent reinforcement learning (MARL) solutions have achieved promising performance, they suffer from limited generalization (adapting to different environmental scenarios), low transferability (adapting to different platform objectives), and training difficulties in large-scale systems, such as the curse of dimensionality. Recently, motivated by the scaling of large language models (LLMs), several works have incorporated LLMs into ride-hailing systems, either by employing LLMs directly as decision-making agents or using them for automatic algorithm design. However, none of these approaches support vehicle sharing, which complicates the problem by expanding both the state and action spaces exponentially. Moreover, most of them require frequent LLM calls at inference time, making them infeasible for real-time deployment. To address these issues, we propose RideSkill, a hierarchical method for ride-sharing that leverages LLM-assisted automatic algorithmic design. RideSkill consists of a combiner that assigns appropriate skills to each vehicle from a learned skill repository, enabling adaptive dispatch under varying scenarios and objectives, and a repositioner that sequentially relocates idle vehicles to emerging regions, avoiding conflicts among vehicles. Crucially, the skill repository, combiner, and repositioner are all trained by an LLM-based automatic evolutionary method, eliminating the need for LLM calls during deployment and thus ensuring high real-time performance.

Self-improving agent pipelines have a problem at their center. An optimizer rewrites prompts to score higher, and the score comes from a judge that is itself an LLM. That judge has the last word on whether the system is getting better, and our position is that it has not earned it. The judge should be demoted from oracle to advisor: its verdict becomes one input among several, and every change is gated instead by a deterministic verification layer the judge cannot override. We reached this position by building the alternative and running it. Over months of running autonomous prompt-optimization loops in production across contract analysis, compliance review, and code quality, we cataloged eleven ways the evaluation signal failed, in four classes: judge bias, harness and metric failures, ground-truth errors, and reward hacking. Agents achieved perfect scores by reading cached answer keys from their environment, a 100% pass rate concealing 68% true capability. A corrupted ground-truth label caused the optimizer to delete correct compliance rules to agree with it. A syntactically broken prompt was promoted as the winner because a silent parser fallback improved the metric. Attempts to fix the judge by rewriting its rubric plateaued; the only reliable gain came from a structural constraint on its output order. In response we describe PROCTOR, a Teacher-Student loop in which a stateful orchestrator holds all tool access, stateless subagents diagnose failures and draft mutations they cannot apply, and a Teacher grades those mutations under five deterministic guardrails: hermetic sandboxes, capability-disjoint roles, acceptance checks that outrank the Teacher, frozen holdouts, and canary cases engineered so that a perfect score is itself evidence of cheating. We report the failures this prevented, and, because the Teacher is itself an LLM judge, the failures it did not.

Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rewards, it often provides coarse credit for intermediate actions. To obtain more fine-grained credit assignment, recent work such as GiGPO introduces step-level advantages for intermediate actions. However, these step-level signals still rely on the final outcome of each individual trajectory. As a result, actions within failed trajectories can remain poorly differentiated, so effective actions can receive the same unfavorable credit as erroneous ones. In this work, we propose Potential-Guided Policy Optimization (PGPO) for multi-turn agentic tasks. PGPO estimates empirical state potentials from anchor-state-group return statistics within each rollout group. It then derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation. This provides finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop show strong overall performance relative to recent group-based RL methods. Further analysis provides evidence that PGPO yields more informative failure-side credit signals with negligible training overhead.

Interview assessment requires per-criterion judgments grounded in behavioral evidence, yet surging applicant volumes have made human-only evaluation costly and inconsistent, while existing AI approaches yield opaque scores without traceable rationale. We introduce PhoenixNest-Video, an evidence-grounded multimodal agent framework for automated video interview assessment. It builds a semantic video graph as structured working memory, performs rubric-conditioned retrieval with cross-modal verification across visual, audio, and textual streams, and produces per-criterion scores anchored to the candidate's materials. A Scorer trained via Rubrics-based Reinforcement Learning with dual rewards for rubric alignment and score-level differentiation internalizes the discriminative structure of multi-level rubrics. PhoenixNest-Video attains 91.50\% grade-level accuracy on VInterview-2025, outperforming substantially larger proprietary models. A compact, rubric-grounded agent therefore scores candidates in closer agreement with an expert panel than direct prompting of much larger models, and exposes the evidence behind each score for human review.

Foot forward kinematics (FK) is widely used to improve proprioceptive legged odometry by providing reliable velocity constraints during foot support. Existing contact-aided estimators generally rely on binary contact decisions to determine whether the FK measurements of an entire foot should be trusted. However, contact does not necessarily imply FK reliability. Dynamic locomotion often involves partial support, toe dragging, and foot slip, causing binary contact decisions to accumulate significant drift over long trajectories. To address this limitation, we propose FOCUS (Foot Observation Confidence from Unannotated Simulation), which predicts a continuous FK reliability weight for each foot instead of estimating binary foot contact. Rather than replacing the model-based estimator, the predicted reliability weights are used to blend FK velocity observations with IMU-propagated body velocity and to adapt the observation covariance of an extended Kalman filter (EKF), enabling smooth reliability-aware fusion without hard contact switching. The network is trained from automatically generated simulation signals using an FK-weighted velocity consistency loss with lightweight simulator-contact regularization, without manually annotated continuous FK-reliability labels. The deployed model relies only on IMU and joint kinematic measurements, making it suitable for hardware platforms with unreliable torque sensing. Experiments demonstrate that FOCUS reduces absolute trajectory error (ATE) by 83.7% on simulated walking episodes, preserves simulated dynamic-motion fidelity in motion scale and spectral energy, reduces ATE by 70.8% across 19 real walking segments, and reduces mean ATE by 42.7% across four real dynamic-motion routines.

LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks. On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW (Global-Local Weave) around it: the local skills a task writes from its own execution are aggregated into procedural families and compressed into de-instantiated global priors, while the instance detail they hold is regenerated per task rather than stored; a commit gate admits a prior only when real execution shows it does not degrade the deployed library. Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average, with positive gains in all 12 continual-improvement runs, and 18.0 with local regeneration, while the library holds one prior per procedural family, 3.6x more compact than the per-task pool. Under the same protocol GLoW leads a published single-document optimizer on 15 of 21 cells. Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory.

Inductive knowledge graph completion (IKGC) aims to predict missing links involving entities unseen during training, requiring models to learn transferable relational and structural patterns. Existing subgraph- and path-based approaches often encode relational paths independently of their surrounding query subgraphs, although the predictive relevance of a path may vary across structural contexts. We propose PEARL, a Path-Entity Aligned Relational Learning framework that models paths as context-conditioned reasoning signals. PEARL constructs a query-specific contextual subgraph from the union of the query entities' neighborhoods and uses a large language model (LLM)-guided retriever to distill semantically relevant paths. It then builds a bipartite interaction graph over paths, contextual entities, and a global subgraph representation, allowing path embeddings to adapt to local and global structural evidence. To suppress noise introduced by the enlarged context, PEARL employs a dual-view contrastive objective that promotes representation consistency under stochastic contextual perturbations. Experiments on WN18RR, FB15k-237, and NELL-995 show that PEARL obtains the best average Hits@10 among the compared IKGC methods on all three benchmarks. Ablation studies, efficiency analyses, and case studies further validate the contributions of contextual subgraph modeling, semantic path retrieval, path-entity interaction, and contrastive regularization.

Ensuring the reliability of deep learning models in real-time industrial defect detection is critical for high-stakes quality inspection. To mine uncertain samples within continuous industrial media streams, thereby enhancing the reliability of the detection system, this paper proposes a streaming active learning method based on the Fuzzy Dual-dimensional Uncertainty (FuDU) framework. Specifically, we first design a Prototype-based Global Uncertainty Quantification (PGUQ) module on the backbone to evaluate image-level uncertainty via normal/defective feature prototypes. A Dual-entropy defect Uncertainty Evaluator (DeUE) is then integrated into the detection head to quantify box-level uncertainty. Finally, by modeling uncertainty as systematic error, we propose a fuzzy dual-dimensional uncertainty-aware strategy that leverages fuzzy inference to fuse dual-dimensional uncertainties, enabling expert knowledge-driven adaptive sampling decisions. Comprehensive experiments demonstrate that FuDU is efficient and flexible, making it well-suited for challenging industrial inspection tasks such as the detection of nuclear fuel rod defects. Our code is publicly available at: https://github.com/wangzhaoyang-508/FuDU.

Real-world personally identifiable information (PII) redaction often operates on document images---scans, screenshots, and PDF renderings---where OCR errors, layout structure, and visual noise determine whether sensitive information is actually removed. Existing PII benchmarks are mostly text-centric and do not measure document-level redaction risk: a page remains unsafe if even one identifier is missed. We introduce LeakageBench, a challenge set of 500 document images with 11,954 GDPR-aligned PII annotations spanning direct identifiers, linkage keys, and contextual re-identification surfaces. We evaluate generic OCR pipelines, commercial and task-adapted OCR-dependent detectors, and OCR-free vision-language models using entity-level F1, group-wise leakage, and document-level leakage metrics. Code Interpreter raises GPT-5.5 localization F1 from 0.090 to 0.249, but critical page-level leakage remains 0.968. These results show that stronger detection and tool assistance improve localization without making most pages safe for release. LeakageBench provides a diagnostic benchmark for high-recall, spatially grounded PII redaction in document images.

Text-Video Retrieval (TVR) retrieves videos that match a natural-language query, but extending image-text models such as CLIP to videos is fundamentally limited by the lack of temporal modeling. Videos exhibit frame-wise heterogeneity in appearance and motion, and compressing all frames into a single representation often obscures temporal structure and semantic transitions. To address this, we propose Temporal-Aware Mixture-of-Experts for Text-Video Retrieval (TAME), a CLIP-based framework that jointly models frame-level structure and temporal relations. First, we integrate sparse Mixture-of-Experts (MoE) layers into both CLIP encoders and apply frame-consistent routing on the vision branch so that experts specialize according to frame-level visual patterns while preserving the original vision-language alignment. Second, we introduce Frame-Temporal (FT) tokens that aggregate global cross-frame information and feed it back to each frame, enabling the visual encoder to capture long-range temporal dependencies without harming local details. Third, we design a Cross-Temporal Interaction and Aggregation (CTIA) module that refines frame-wise sentence-video similarities through staged temporal filtering and fusion. Experiments on standard TVR benchmarks show that TAME consistently improves over CLIP-based baselines. On MSR-VTT, it improves R@1 by 4.0 over CLIP4Clip, and also achieves consistent gains on DiDeMo, MSVD, LSMDC, and ActivityNet. The code is available at https://github.com/sejong-rcv/TAME.

Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent conversations, in which an agent's reasoning became most vulnerable to external influence. Using the MedQA dataset, this study analyzed simulated doctor-patient conversations to measure how interventions shifted reasoning and accuracy. Correct intervention methods showed an improvement in baseline diagnostic accuracy of up to 40%, while incorrect or bias-related interventions degraded performance by up to 6% and increased diagnostic drift and uncertainty. Beyond performance changes, our analysis revealed behavioral similarities between cognitive biases in simulated agent environments and real-world clinical practice. Examples included premature closure and susceptibility to misleading cues. Overall, these findings demonstrate that identifying and guiding fault points with human interventions may provide a mechanism for improving diagnostic robustness in multi-agent medical systems.

General-purpose vision-language models (VLMs) now support strong visual recognition, instruction following, and generation. However, most pretrained visual encoders are built around three-channel natural images and do not directly accommodate observations such as native multispectral measurements or synthetic aperture radar (SAR). Adapting VLMs to these sensors typically requires dedicated encoders and domain pretraining, slowing the reuse of stronger general-purpose checkpoints. We show that the multi-image interface of general-purpose VLMs offers a lightweight alternative. Our protocol renders each observation as five optical views and one SAR view, names them in the prompt, and adapts the language network and selected visual transformer blocks with LoRA. This exposes band composites, spectral indices, and radar backscatter through an existing visual interface. For land-cover recognition, structured supervision couples predicted classes with sensor evidence. We further construct preference pairs in which a true label is omitted while its supporting evidence is retained, encouraging complete predictions that remain consistent with the observations. On a balanced six-class land-cover benchmark derived from BigEarthNet-v2, the adapted Qwen3-VL reaches 0.8275 micro F1. The same input and adaptation protocol improves all four tested VLM architectures and transfers to Sen1Floods11 flood verification and BigEarthNet.txt captioning. Image removal and mismatch controls show that the adapted models use the supplied sensor observations. Together, these results demonstrate that VLMs can be repurposed for multispectral and SAR tasks through rendered inputs and compact LoRA adaptation, without training a new foundation model.

Quantum generative models offer a promising framework for exploring whether quantum computation can enhance generative machine learning. Flow matching is a generative method in which samples are generated by transporting a simple, known distribution to the target data distribution with a learned velocity field. Its quantum counterpart, known as quantum flow matching (QFM), was introduced recently, and, like its classical counterpart, requires integrating an ordinary differential equation over many time steps during inference. As each step requires the output from the previous step, the circuit submission is sequential and a drawback on quantum computers as they have high input/output costs. To alleviate this problem, we introduce Quantum MeanFlow (QMF), the quantum analogue of the MeanFlow formulation, which allows single-step sample generation. While the QFM learns an instantaneous velocity field at each time step, QMF learns the average velocity over a time interval. We use a parameterized quantum circuit to learn these velocity fields and benchmark the two methods on the MNIST dataset. We show that while single-step QMF has lower image quality compared to multi-step QFM, it performs better than the single-step QFM sampling at every shot count. Both of our models are executed on IBM quantum computers and best-of-N rejection sampling recovers most of the accuracy lost to device noise without modifying the circuit. This is especially advantageous for QMF which has only one circuit evaluation per image. Here, We establish QMF as a viable method for single-step quantum generative sampling, saving on quantum circuit evaluations per generated sample.

Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial suffixes on white-box source models. However, existing GCG-based methods rely on averaged adversarial loss and deep greedy search, which can over-emphasize easy-to-jailbreak behaviors and overlook promising regions of the suffix space. We propose BOSS, a plug-and-play framework that improves GCG-based jailbreak optimization through breadth-oriented suffix search. BOSS uses Tail-Focused Adversarial Loss (TFAL), standard source loss, and behavior coverage to select terminal suffixes, then explores multiple short trajectories and selectively continues promising suffixes. Experiments on public benchmarks show that BOSS improves attack success rates across multiple GCG-based methods while reducing optimization time.

Point-supervised change detection (PS-CD) aims to identify pixel-level changes between bi-temporal images using only sparsely annotated points. Although point annotations substantially reduce labeling costs, their limited spatial coverage often results in incomplete and noisy pseudo-labels. To address this issue, we propose a two-stage framework that introduces SAM2 priors into PS-CD and progressively adapts them to the target task. In Stage I, SAM2 generates object-aware candidate masks from point annotations on the bi-temporal images, and a bi-temporal mask selection strategy is designed to convert generic segmentation responses into more reliable change pseudo-labels. Subsequently, a lightweight CNN refinement module with an uncertainty-aware loss is employed to improve boundary quality and local structural consistency. In Stage II, we construct a teacher-student self-training framework in which the teacher is updated by exponential moving average and periodically refreshes the pseudo-labels. This design establishes a closed-loop optimization process that alternates between pseudo-label refinement and model re-optimization. Experiments on three benchmark datasets, including WHU-CD, LEVIR-CD, and SYSU-CD, demonstrate that the proposed method outperforms previous weakly supervised approaches on most benchmarks and remains competitive with several fully supervised methods.

Advertising recommendation requires continuously tuning complex system parameters while balancing commercial returns and user experience. Recent work has introduced large language models (LLMs) with skill documents to assist this labor-intensive process, but skill optimization remains largely prompt-driven, lacking a principled mechanism to attribute rewards to specific document edits. To address this limitation, we propose Document-Mediated Reinforcement Learning (DMRL), a skill self-evolution framework that models skill document optimization as a sequence of structured editing actions. In DMRL, an upper-level agent performs controlled document edits, while a frozen lower-level task agent evaluates their effects through A/B testing. To address credit assignment and long-term outcomes, we introduce two key components: (1) Dual-Relative Policy Optimization (DRPO), a post-training policy optimization method for robust and risk-aware advantage estimation; and (2) Long-term Reward Predictor (LRP), which estimates long-term outcomes by modeling population heterogeneity with disentangled representation learning and cross-attention transfer. DMRL was deployed on a large-scale short-video ads platform and extensive empirical evaluation shows that DMRL outperforms state-of-the-art baselines across key advertising metrics

Serving useful recommendations under distribution shift is crucial for balancing utility and risk in out-of-distribution (OOD) recommendation. However, most existing OOD methods improve ranking or construct counterfactual candidates without controlling the proxy-label false discovery rate (FDR) of the served set. In this work, we formulate OOD serving as the $α$-Valid Counterfactual Recommendation ($α$-VCR) problem to retain candidate support learned from counterfactual supervision while controlling proxy-label FDR, and propose GenCAR, which couples preference-grounded counterfactual supervision with calibrated set selection. In particular, GenCAR fixes the stable-preference representation while intervening on the environmental factor, grounds offline large language model proposals through preference anchors and trust-radius filtering, and uses conformal $p$-values for Benjamini--Hochberg selection. We theoretically bound conditional counterfactual approximation error and prove finite-sample, distribution-free control of proxy-label FDR under exchangeability and positive regression dependence, with a Benjamini--Yekutieli guarantee under arbitrary dependence. Extensive experiments audit realized proxy false discovery proportions and demonstrate that GenCAR consistently enhances OOD candidate recovery across diverse benchmarks.

World Action Models (WAMs) aim to control robots by stochastically generating visual futures and then decoding actions, but empirical observations indicate that the results can strongly depend on which future is selected. We propose World-Coherent-Decoding (WCD), a self-verifying test-time planning framework that treats WAM rollouts as falsifiable future--action hypotheses. At each decision step, WCD samples multiple candidates from a frozen WAM and ranks them using internal generative signals: flow-based video surprisal for visual plausibility and action path effort for action-generation stability. After execution, the realized observation audits the selected imagination, yielding an imagination--reality mismatch that trains a lightweight online predictor for future candidate selection. Thus, WCD converts delayed self-verification into pre-execution reliability estimation without updating the backbone model. On RoboTwin 2.0, WCD improves Hard success under limited randomized-scene supervision from $55.80\%$ to $60.90\%$, with a $+16.43$ gains on Horizon-3 tasks, and shows qualitative robustness on real Franka visual-shift tests. These results highlight a simple principle: test-time scaling for WAMs depends less on sampling more futures than on selecting reliable ones.

Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets further exhibit severe label imbalance toward guilty outcomes. Consequently, these models suffer from "Guilty Bias", blindly accepting the prosecution's narrative as objective truth. Previous studies employing three-step reasoning structures or training on synthetically generated innocence data improve overall accuracy, but they still fail to mitigate bias at inference time. In this paper, we introduce OBJECTION, an inference-time pipeline that integrates an Adversarial Lawyer Agent into each 3-step reasoning of offense, unlawfulness, and culpability. Unlike generic critics, our agent actively challenges the model's presumptions of guilt by injecting legal defense arguments at each reasoning stage. To thoroughly evaluate this, we present a new "Natural Innocent" dataset including 3.4k real-world cases, overcoming the limitations of synthetic innocence benchmarks. Test results show that OBJECTION drastically reduces the False Guilty Rate (FGR) from 82.93% (SOTA baseline) to 16.69%, proving its capability to perform substantive legal reasoning. This work denotes a key progress toward aligning Legal AI with the presumption of innocence.

Physical reservoir computing (PRC) refers to the use of a physical dynamical system as a computational resource for tasks such as state estimation and control, but there has been a lack of formal study of design rules towards more effective design of such physical reservoirs. Using a pneumatic soft arm with a five-pouch sensing column, this work studies how the pouch interconnection topology, robot stiffness, and the number of instrumented sensors affect bending-angle estimation performance. Across 36 matched trials spanning waveform, baseline pressure of the sensing column, and actuation range, all designs are evaluated under the same-time bending-angle estimation benchmark using 0.2 s of pressure history and a fixed ridge estimator. Our analysis of the experimental results leads to three design guidelines. First, independently sealed pouches preserve a much richer observable state than a shared manifold. Second, increasing the baseline pressure of the sensing column makes the pouch responses more redundant and increases estimation error most strongly in the coupled topology. Third, in the sealed topology, two strategically placed sensors already recover most of the attainable benefit, three capture essentially all of it, and additional sensors provide little or no additional value. In summary, the results suggest that topology, stiffness, and number of instrumented sensors should be co-designed for accurate PRC of soft robot states; stronger excitation alone cannot recover the diversity that poor design choices have already removed.

Large language models (LLMs) are increasingly evolving from conversational assistants into agents capable of operating external digital environments. Graphical user interface (GUI) agents play an important role in this transition, as many real-world workflows remain accessible only through user-facing software interfaces. However, despite recent progress on general computer-use benchmarks, domain-specific professional standard operating procedures (SOPs) remain challenging for GUI agents because they often involve implicit domain knowledge, software-specific conventions, and task-level verification requirements. We introduce OmegaUse-SOP, a human-in-the-loop SOP Engineering system for transforming human demonstrations of professional computer use into reusable SOP skills for GUI agents. Analogous to prompt engineering, SOP Engineering iteratively refines demonstrations, execution rules, and domain knowledge to convert professional SOPs into reusable GUI-agent skills. OmegaUse-SOP consists of four modules: Observe, Reason, Configure, and Execute. Together, these modules record expert operations as multimodal GUI traces, abstract low-level events into semantic step-level instructions, incorporate domain rules and task-specific parameters, and execute the resulting skills in live GUI environments through step-wise grounding, action generation, and verification. To demonstrate its effectiveness, we collaborate with a power-sector client and test OmegaUse-SOP on photovoltaic simulation workflows in PVsyst 7.2. The results suggest that OmegaUse-SOP can improve GUI-agent reliability on professional SOP tasks, highlighting a practical path toward deploying GUI agents in domain-specific professional software environments.

Most vector databases rely on graph-based indexes, notably HNSW and Vamana, for approximate nearest neighbor search. With embedding models widely adopted, the datasets these databases store grow rapidly. At a fixed accuracy, how does search cost scale with dataset size? The prevailing answer is poly-logarithmic growth. Yet the claim is proven only under special conditions and asserted without proof for the indexes used in practice. It is also largely untested: standard benchmarks measure cost at one dataset size, not across sizes. We put the claim to the test. The answer depends on the scale itself. While the dataset size $N$ is small relative to the data's intrinsic dimensionality, search cost grows as $N^c$ for a constant $0<c<1$. We call this scaling the Sublinear Power Law. Once $N$ is large enough, growth slows to subpolynomial, consistent with the poly-logarithmic claim. The Sublinear Power Law appears on every dataset, mostly up to its full size, at every recall target, query hardness level, and index configuration we test. The transition to subpolynomial growth appears on the two datasets that grow large enough relative to their intrinsic dimensionality. One mechanism underlies both behaviors: a dataset's intrinsic dimensionality grows with its size until the data resolves its underlying distribution. Higher intrinsic dimensionality packs more vectors into the query neighborhood the search must examine. We present a unifying theory of beam-search cost that explains our observations. For exact and bounded-degree constructions, we prove the Sublinear Power Law and the eventual transition to poly-logarithmic scaling, and derive the scale at which it occurs. We also develop models that predict the power-law exponents for any recall target and index configuration. These models give a principled way to navigate trade-offs among search cost, insertion cost, and recall as data grows.

Encrypted traffic classification infers semantics beyond the flow record from transport-layer observables, and supervised training rests on labels that hold for the individual flow they are attached to. Recent systematizations scrutinize model in- puts and data splits; we systematize the complementary label side. Across 14 audited benchmark entries, we identify two recurring label-side strategies: coarse inheritance, which risks labelling flows the evidence does not cover, and overstrict filtering, which keeps only self-attesting flows and risks dis- carding relevant ones. No audited entry exposes a countable pre-selection population, and the task objects downstream papers attach to the same labels disagree with the recovered record in 8 of 23 referenced cells. Under strict side-channel features we derive a representation-relative ceiling on bal- anced accuracy for any classifier restricted to those features: on the public benchmarks that inherit, it ranges from 0.56 to 0.76. On the filtering side, only 24.95% of connections in our fully captured corpus carry an observable SNI of their own; yet the discarded connections raise macro accuracy from 0.44 to 0.65 through same-run co-occurrence features. We end with recommendations for benchmark builders and users.

Humanoid learning increasingly relies on transforming vast and diverse human motion data into high-quality robot reference trajectories. However, retargeting human motion to humanoid robots is challenging due to substantial differences in morphology, degrees of freedom, joint ranges, and kinematic constraints between humans and robots. Existing retargeting methods typically address these differences by defining human-robot correspondence through hand-crafted sparse keypoints or body-part pairs. As a result, retargeting quality depends heavily on manual semantic design, limiting scalability across motion sources and robot morphologies and providing only sparse guidance for reproducing detailed poses and interactions. In this paper, we present Unified Motion Retargeting (UMR), a framework that learns dense point cloud correspondence without requiring manually designed human-robot mappings. By treating exterior point clouds as a unified interface between human motion and humanoid robots, UMR decouples retargeting from source-specific skeletal semantics and robot-specific topology. The learned dense correspondence provides fine-grained geometric anchors for constrained point cloud matching optimization, enabling surface-level pose alignment and direct transfer of interaction contacts. Experiments demonstrate that UMR unifies retargeting across heterogeneous motion sources, robot embodiments, and downstream scenarios ranging from locomotion to interaction, while achieving higher motion fidelity and plausibility than state-of-the-art methods. UMR therefore provides a scalable foundation for transforming large-scale human motion references into robot-ready training data.

Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a branching reply tree. We study why sentiment changes in rumor-centric conversation trees by treating discourse moves (e.g., denial/correction, evidence/link, toxicity/attack) as candidate interventions and asking (i) what sentiment a reply expresses, (ii) whether the sentiment shifts relative to its parent, and (iii) which prior message most plausibly drove the reply's sentiment. To support this setting, we introduce CaSiRe, a causal sentiment reasoning layer over public rumor conversation datasets that adds post-level sentiment labels, induced parent-child shift labels, calibrated multi-label intervention tags, and explicitly annotated causal-source labels. We then propose C$^{3}$T (Counterfactual Causal Conversation Transformer), a thread-structured temporal model that jointly predicts node sentiment and shifts, learns sparse ancestor attribution, and supports counterfactual queries by forcing conversational intervention embeddings on or off to estimate potential outcomes. Under an event-level split, C$^{3}$T improves out-of-event robustness and attribution over text-only, graph-based, and temporal baselines, and yields interpretable model-based effects: denials/corrections and evidence reduce downstream negativity, while toxicity increases it. We also benchmark open-weight LLM prompting baselines and find that added conversational context helps, but attribution remains less reliable, motivating structure-aware counterfactual modeling for social-media analysis.

Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful discovery outcomes are typically discarded rather than reused. We introduce persistent discovery context, a lightweight memory layer that stores prior intent-to-object mappings and reuses them to augment future retrieval. Across three structured data environments, persistent discovery context consistently improves retrieval quality over metadata-only search, remains effective with automatically generated memories, and exposes a reproducible interference failure mode. In lexically sparse domains, memory-only retrieval can even outperform metadata-based retrieval. These findings suggest that discovery outcomes constitute a useful form of reusable context for data-centric agents.

Estimating physical parameters from scientific images is a common inverse problem in materials characterization that often relies on expensive physics-based simulations. In electron microscopy, specimen thickness and crystal mistilt are critical parameters that govern how electrons scatter through the sample, and therefore the accuracy of any atomic-scale structure recovered from it. They are commonly inferred by matching experimental position-averaged convergent-beam electron diffraction (PACBED) patterns to simulated ones, but grid searches scale poorly and neural-network methods require extensive pretraining that may not transfer to new conditions. Here, we propose scalable Bayesian optimization of composite functions (SBOCF), a simulation-efficient method that exploits the known composite structure of the image-matching objective and the intermediate information contained in simulated images. By representing PACBED images with patch-level summaries and two correction terms, SBOCF preserves the original pixel-wise objective while reducing the number of modeled outputs from 24,649 to 11. Under a budget of 50 simulator evaluations, SBOCF outperformed standard Bayesian optimization with expected improvement on synthetic SrTiO3 benchmarks with thick and thin specimens, reducing the median final SSE by up to 290x in the thick-sample case. On experimental data, SBOCF produced parameter estimates consistent with previously reported values without task-specific pretraining. For a simulated mistilted specimen, using the SBOCF estimates in a downstream ptychographic reconstruction recovered sharp atoms that were otherwise blurred. These results establish SBOCF as a promising approach for inverse problems involving expensive simulators and high-dimensional structured outputs.

As large language model (LLM) agents shift from tools to participants in human groups, a fundamental question for collective behavior is how their growing presence reshapes consensus formation. Here we study mixed human-AI groups in a collaborative description game, in which shared conventions emerge through repeated rounds of random pairwise communication. Varying the proportions of LLM agents, we identify three distinct regimes of consensus formation: low agent proportions facilitate human-led consensus, intermediate proportions disrupt convergence, and high proportions restore strong consensus while shifting it toward agent-led conventions. Crucially, these regimes differ not only in the strength of convergence, but also in the semantic grounding and communicative form of the resulting consensus: human-led consensus is more concrete, holistic, and grounded in shared real-world analogies, whereas agent-led consensus is more abstract, less information-dense, and more geometrically segmented. Mechanistically, agent influence arises from a shared linguistic prior that places agents near one another in the expression space, combined with relatively stable expression choices across rounds; humans initially resist adopting expressions from partners perceived as AI but gradually yield to conformity pressure. These findings provide evidence that AI composition can shape the emergence, content, and perceived legitimacy of group norms, making agent proportion and transparency important design variables for human-AI systems.

Reverse-logistics operators often decide how to inspect and route returned assets before their condition is fully observed, while full inspection consumes scarce labor. Semantic Signal-Assisted Decision Support converts return notes into a condition factor and a signal-quality score that guide inspection depth and recovery allocation under shared labor capacity. We evaluate the framework in three synthetic benchmark scenarios spanning information technology decommissioning, aircraft maintenance, and consumer-electronics returns. Across 30 paired simulation seeds, the keyword implementation improves net recovery value relative to a structured-feature comparator with noisy full inspection while reducing inspection cost in all three scenarios. A risk-blind comparator that skips inspection altogether still records higher value under the benchmark's purely economic objective. At matched inspection cost, score-guided targeting adds 53.9 thousand United States dollars per batch in the aircraft scenario but has little economic effect in the other two configurations; phrase and large language model extractors provide further gains in the aircraft scenario. These results show how narrative evidence can support inspection allocation before recovery decisions are made.

Natural language interfaces to databases have traditionally suffered from three structural limitations: exclusive targeting of relational SQL, unconditional dependence on large language model (LLM) inference at query time, and absence of any runtime signal when generated queries are semantically incorrect. This paper presents text2ql, an open-source Python framework that addresses all three limitations through a language-agnostic Intermediate Representation (QueryIR) and a pluggable renderer architecture. A single seven-stage detection pipeline serves both SQL and GraphQL targets; a zero-LLM deterministic mode delivers 100% execution accuracy at a median latency of 3.2 ms with no API cost; and every generated query carries a runtime confidence score in [0.15, 0.97] computed from an additive signal model. Evaluated on 50-query random samples from the Spider and BIRD benchmarks (indicative results; full-set evaluation is planned), the LLM-backed mode achieves 62-70% exact match and 84-91% execution accuracy; the deterministic mode achieves 100% execution accuracy with zero parse errors across all 100 test cases. An ablation study isolates schema-aware prompting as the dominant accuracy lever, contributing +18.4 percentage points of exact-match gain over the schema-free baseline on both benchmarks. text2ql is publicly available at https://pypi.org/project/text2ql/ under the Apache 2.0 license.

Dermatology artificial intelligence (AI) models are predominantly trained on light-skinned, cancer-focused image collections, yet they are increasingly proposed for deployment in resource-constrained settings where patients differ from training populations along two confounded axes: skin tone and disease distribution. We investigate whether poor generalization is primarily caused by skin-tone underrepresentation or disease-distribution shift. We evaluate a cancer-trained baseline (ResNet-50 fine-tuned on HAM10000 and ISIC 2019), two dermatology foundation models (DermLIP and MONET), and a general-purpose vision model (DINOv3) as frozen feature extractors. Models are evaluated on a tone-stratified disease-matched dataset (Diverse Dermatology Images, DDI) and a disease-shifted tone-diverse dataset (Skin Condition Image Network, SCIN). Our results show that disease-distribution shift contributes more than skin tone in the evaluated settings. The cancer baseline decreases from 0.62 to 0.21 balanced accuracy when transferred to unfamiliar clinical conditions, while the within-disease skin-tone gap is smaller (0.10-0.18) and inconsistent. Label-free representation analysis shows that this failure reflects a representational limitation rather than only missing output labels: cancer-specialized features poorly cluster unfamiliar conditions (kNN purity lift +0.06 over chance), whereas dermatology-pretrained features retain stronger transferable structure (+0.23). Finally, we show that representation quality predicts recoverable performance under lightweight adaptation. Starting from dermatology foundation models, approximately ten labeled examples per clinical category recover most attainable performance. We release the evaluation protocol and code to support reproducible auditing of dermatology AI generalization.

Physics-informed neural networks (PINNs) commonly evaluate the spatial derivatives appearing in partial differential equation residuals using automatic differentiation (AD), whose computational and memory costs can become substantial when multiple or high-order derivatives are required. We perform a controlled comparison of spatial AD and Fourier spectral differentiation in periodic physical-space PINNs. Within each paired experiment, the neural representation, temporal differentiation, optimizer, sampling procedure, and training schedule are held fixed, so that the two cases differ only in the spatial differentiation procedure. For the Fourier variant, network outputs are evaluated on a uniform periodic grid and transformed to Fourier space, where spatial derivatives are obtained through spectral multiplication and the same Fourier coefficients are reused across derivative orders. We compare the two procedures in standard PINNs for the Allen--Cahn and Korteweg--de Vries equations and in Causal PINNs for the Allen--Cahn, Korteweg--de Vries, and Kuramoto--Sivashinsky equations. Across these five equation--framework settings, Fourier differentiation yields mean paired end-to-end training speedups ranging from $2.90\times$ to $18.52\times$ and reduces peak allocated graphics processing unit (GPU) memory by $68.7\%$--$94.1\%$. The final relative $L_2$ errors remain of the same order, with neither differentiation procedure showing a consistent accuracy advantage. For the one-dimensional periodic benchmarks considered here, Fourier spectral differentiation therefore provides substantially lower training time and memory usage than spatial AD while retaining comparable solution error, at the cost of requiring a uniform structured spatial grid.

Deploying heterogeneous AI models concurrently on a shared GPU introduces resource contention that complicates runtime scheduling. While surrogate models avoid costly online benchmarking, their profiling requirements typically grow combinatorially with the number of co-running models, limiting scalability. We propose a MeanField surrogate that predicts per-model performance from local configuration and aggregate GPU state rather than explicitly modeling all joint interactions. Experiments on concurrent LLM and vision workloads across $N \in \{2,3,4,5,6\}$ show high predictive accuracy ($R^2 \approx 0.96$) with an empirical sample budget that grows approximately linearly in $N$, in contrast to the combinatorial cost of fully joint profiling. Integrated into a genetic algorithm scheduler, the surrogate scales to an $N=5$ problem with 78,732 feasible joint configurations, remaining within 0.10% of the exhaustive search with zero SLA violations across eight dynamic workload scenarios, while complete online GA decisions take 26 ms median, about $5\times$ faster than exhaustive surrogate search.

Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive paradigm. With bidirectional attention and any-order generation, DLMs naturally fit infilling tasks, which require generating a middle span conditioned on both the prefix and the suffix. However, infilling is sensitive to the length of the span, while DLMs require the length to be fixed before generation. Although prior studies extend DLMs to dynamic lengths, they still suffer from two limitations. (i) Sensitivity to initial length. These methods require a preset length to initialize the search and are highly sensitive to this initial length, often yielding suboptimal results. (ii) Inference inefficiency. They either insert length-changing operations during generation or repeatedly search for an appropriate length using multi-step denoising confidence, both of which introduce substantial extra forward passes and computational cost. Therefore, we propose PILL (Probing-based InfiLling with preset-Length-free decoding), an efficient infilling method for DLMs that requires no preset initial length and adds far fewer extra forward passes than baselines, substantially reducing inference time. Experiments show that, across five DLMs spanning different families, architectures, and training recipes on eight infilling benchmarks, PILL improves over the strongest baseline by +4.8 average pass rate on code and +6.0 BLEU-2 on text, while running 1.82x faster than that baseline. The code is available at https://github.com/Hsu1023/PILL.

Large Language Model (LLM) agents increasingly explore many candidate states of relational data in parallel, each of which should remain isolated, reproducible, and auditable, preferably through the same SQL interface used for ordinary data work. Existing tools support this requirement only partially: source-code version control does not scale to large datasets, whereas relational databases manage large data efficiently but rarely expose native branching, comparison, and merging. We present Git4Data, a database-native version-control layer for agentic workflows. Git4Data treats a database as a repository and a table as a versioned object, exposing Git-style operations (snapshot/tag, branch, diff, and merge with explicit conflict-resolution policies) through SQL extensions. Implemented in MatrixOne, a cloud-native relational database, Git4Data leverages immutable object storage and MVCC to make the cost of these operations proportional to the size of the change rather than the size of the data. On the BranchBench agentic branching workloads, Git4Data outperforms DoltDB by up to an order of magnitude. Overall, we believe this work sheds light on how relational databases can better support AI agents through efficient versioning.

Federated learning (FL) lets institutions train a shared model without exchanging data, and Low-Rank Adaptation (LoRA) makes this practical at scale by communicating only compact low-rank updates. Biomedical imaging is a compelling setting for this combination: patient data are archived behind privacy regulations, and institutions differ widely in scanners, protocols, and compute. Such heterogeneity raises the question of how federated LoRA updates should be aggregated, increasingly pressing as multimodal vision-language models become central to medical image analysis. We benchmark federated Parameter-efficient fine-tuning (PEFT) of BiomedCLIP for chest radiograph classification across four public cohorts on three continents (USA, Vietnam, Spain). Federated LoRA adaptation improves shared-class AUC on all four cohorts over the unadapted BiomedCLIP backbone (mean 0.687 to 0.802), showing that the gains come from federated adaptation rather than from the pretrained model's zero-shot ability. Relative to isolated single-cohort training, federation improves the weaker cohorts while largely preserving the strongest and approaches a centralized reference (0.812) that pools all data. The singular value decomposition (SVD)-based product-space aggregation introduced by FlexLoRA is essential to this gain (naive factor averaging drops mean AUC by 0.097), whereas a drift-correcting optimizer (FedProx) shows no benefit over FedAvg in our single-seed runs, consistent with LoRA's low-rank updates already limiting client drift. Biomedical vision-language models can thus be adapted collaboratively across heterogeneous, geographically distributed institutions without centralizing data.

The rapid progress of AIGC has made text-centric image manipulation increasingly accessible, creating new forensic challenges that require not only authenticity detection but also spatial grounding and evidence-based explanation. This paper presents our solution to the GenText-Forensics Challenge at ACM Multimedia 2026. We propose an evidence-guided detector-localizer-reasoner system, where an image-level detector provides a global authenticity prior, a dedicated localizer extracts tampered regions as spatial grounding evidence, and an MLLM-based reasoner generates structured forensic reports grounded in this expert forensic evidence. These modules are connected through a cascaded evidence flow: the detector gates the subsequent localization and prompting process, the localizer converts tamper responses into grounding boxes, and the reasoner is trained to synthesize the detector decision and localized evidence into the final report. As a key part of our method, we introduce iterative difficulty-aware mining to improve localization quality and apply report-mask consistency post-processing to align report grounding with predicted masks. On the official hidden test set, our system achieves a final score of 0.638 and ranks second in the challenge, validating the effectiveness of the proposed evidence-guided system. The code is available at https://github.com/peifengLiu42/ACMMM26-evidence-guided-detector-localizer-reasoner-system.

An AI agent can perform well on benchmarks and still be unsuitable for deployment. Existing AI-agent benchmarks measure whether an agent can complete realistic professional work, whereas enterprise deployment asks a different question: whether an agent can meet a required reliability level, under acceptable human oversight, and at tolerable cost. We introduce Reliable Enterprise Agent Deployment (READY), a framework for qualifying AI agents for deployment on enterprise workflows. READY preserves each workflow's own definition of successful execution while applying a common qualification procedure. Given an agent, a workflow, and a class of candidate oversight policies, READY measures the reliability and operating cost of the human-AI system, selects the minimum-cost policy that satisfies a specified reliability target, and statistically qualifies it on held-out cases. The resulting deployment profile characterizes the supported operating point: reliability, human-oversight burden, and cost. READY is implemented as an open testbed that decouples workflow specification, execution, evaluation, and qualification, and runs on existing agent-evaluation infrastructure. In an end-to-end clinical-audit case study spanning 16 agent systems and 750 cases, READY reveals differences hidden by autonomous performance: two systems separated by only 0.3 points in autonomous accuracy (72.8% vs. 72.5%) require 39.2% versus 29.6% human review, respectively, to qualify at the same 76% reliability target under the evaluated oversight policy. READY thus shifts enterprise agent evaluation from how well can the agent perform the work? to under what conditions, and at what cost, can it be reliably deployed? By making those conditions explicit and statistically testable, READY provides a basis for comparing agent systems, setting oversight requirements, and making evidence-based deployment decisions.

LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection methods build experience memories, but memories are mostly hard to invoke, refine, or scale, while agent skills offer a more actionable unit: structured procedural knowledge that specifies when to act, how to act, and which resources or tools to use. We introduce MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills. MASkills presents a new agent-optimization pipeline that integrates skill-conditioned credit assignment, hierarchical credit aggregation, and momentum-smoothed optimization, enabling agent skill libraries to evolve through refinement, induction, consolidation, and pruning. Experiments on HotpotQA, LoCoMo, and GAIA demonstrate the effectiveness of MASkills across multiple agentic tasks. Our code is available at https://github.com/DaRL-GenAI/MASkills

To address the sequential and evolving nature of time series, the Online Time Series Forecasting (OTSF) task has been extensively studied in multiple domains. Existing research focuses on adapting to non-stationary environments by employing memory buffer-based retrieval strategies. However, we observe that such frameworks struggle with long-term adaptation and fail to generalize to unseen patterns. To this end, we introduce CoSPOT, an LLM-based online time series forecasting framework that leverages a pre-trained LLM as the backbone online forecaster, motivated by its strong few-shot capabilities. For efficient online adaptation, CoSPOT keeps the LLM frozen and employs compositional spectral prompts grounded in frequency-domain bases to guide the model with the overall distribution of the input, thereby substantially reducing the number of parameters updated during the online phase. Specifically, CoSPOT decomposes time series into frequency bases and composes the corresponding spectral basis prompts according to their amplitudes, allowing unseen patterns to be represented as new combinations of learned basis prompts. Our extensive experiments on real-world datasets demonstrate the superiority and practicality of CoSPOT across challenging online scenarios, including extended online phases and cross-dataset settings with substantial distribution shifts. Our code is available at https://github.com/seungyoon-Choi/CoSPOT.

Multimodal large language models have achieved remarkable progress in front-end web development, generating interactive webpages from multimodal references such as screenshots and interaction videos. However, existing work largely emphasizes visual metrics such as aesthetics and layout similarity, while overlooking the more critical validation of interactive functionality. We present RILA, an execution-driven agent that puts browser rendering in the loop, iteratively editing generated code from runtime interaction feedback. RILA introduces an Action Interaction Verification (AIV) module that replays the reference interaction trajectory on the generated webpage to collect grounded execution-aware observations, and an Execution-aware Rendering Score (ERS) that jointly measures interaction correctness and visual fidelity to guide iterative optimization. We further build an execution-verified data synthesis pipeline that produces diverse, high-quality training data, offering gains complementary to inference-time optimization. On IWR-Bench, RILA consistently improves both interaction and visual fidelity across foundation models. Notably, with our training pipeline, RILA lifts the compact Qwen3.5-9B backbone from 40.40% to 57.52%, surpassing far larger one-shot generators, including the 1T-parameter Kimi-K2.6 (55.61%) and the proprietary GPT-5.5 (55.74%).

Removing complete transformer layers preserves a standard serving architecture, but existing depth-compression methods can lose substantial quality, and the loss varies unpredictably across models. We introduce XMerge, a post-training method with two components. Cross-axis selection identifies a block with low relative-magnitude and angular hidden-state change, and local boundary reconstruction re-fits the adjacent surviving block to match the original two-block output. XMerge uses no task labels or end-to-end fine-tuning, and it introduces neither architectural changes nor additional inference-time parameters. Across seven Llama and Qwen backbones (0.5B-8B), five published baselines, and three layer-reduction levels, its advantage over baselines is largest at the most aggressive removal: at k=4 it ranks first on six of seven backbones on CORE (a 22-task aggregate) and, separately, on six of seven on MMLU (five of seven on both at once), while avoiding the large perplexity increases of several competing operators. In a task-level bootstrap, the 95% confidence intervals for the three largest CORE margins exclude zero; the remaining margins are consistent with ties. Across the 14 (model, regime) cells it is also the only evaluated operator that never collapses, ranking top-2 in both zero-shot and in-context regimes; on a first calibration probe (one backbone) it is the best-calibrated operator. Ablations show that local reconstruction provides most of the gain, while cross-axis fusion helps when the two selection axes disagree. The additional construction cost is recovered through per-token decode savings after roughly tens of thousands of requests.

Visual modality enhances the capabilities of multimodal large language models (MLLMs) but also introduces a safety concern: a benign textual query may convey harmful intent when grounded in a visual image. We term this cross-modal safety drift and our pilot studies show that the safety response rate for such requests is substantially lower than that for requests containing explicitly unsafe text. This paper aims to systematically study this issue. First, we conduct an empirical analysis to identify representative unsafe response patterns. Building on these, we interpret model representations and attentions, revealing that visually risky cues receive limited attention and weakly trigger refusal. Motivated by the observation that safety signals from unsafe text processing can be transferred, we propose safety-awareness representation transfer (SRT), a lightweight direction-refinement method that mitigates cross-modal safety drift with a frozen MLLM backbone. Experiments across multiple benchmarks and models show that SRT effectively improves safety in diverse cross-modal settings while preserving utility. Code is available at https://github.com/cucu220123/safety-awareness.

Industrial anomaly detection benefits from anomaly samples, yet newly deployed products typically provide only normal images, making anomaly samples difficult to collect. Zero-shot anomaly generation offers a promising solution which avoids collection of target-product anomalies. However, existing methods mainly rely on texture images or text descriptions as anomaly sources, which often produce unrealistic anomalies. Observing that similar anomalies can recur across different products, we propose anomaly transfer-based zero-shot generation, which reuses real anomalies from existing source products, making target-product anomalies no longer necessary to generate realistic anomalious samples for unseen target products. Since not every anomaly type suits the target product, an anomaly type filtering mechanism first selects plausible source types. To transfer selected anomaly, we propose DPA, a diffusion-based framework that decouples product-agnostic anomaly representations. Instead of directly extracting anomaly representations, DPA learns product-irrelevant anomaly embeddings through training with the mismatched data pair, enabling transferable anomaly concept learning across products. Furthermore, we design an adaptive mask-guided pipeline that leverages adaptive masks to control the positional and geometric plausibility of generated anomalies during generation. A training-free anomaly labeling module is further introduced to produce pixel-level annotations aligned with generated anomalies. Extensive experiments on MVTec-AD, VisA, and a dedicated anomaly-transfer benchmark demonstrate that the proposed setting and DPA generate more realistic anomalies and significantly improve downstream anomaly detection performance under both zero-shot and few-shot settings. Source code and models will be released.

Probabilistic multivariate time series (MTS) forecasting is crucial for modeling complex dynamical systems. However, existing diffusion-based methods rely on task-specific conditional paradigms that lack flexibility and struggle with inherent "information heterogeneity"--the significantly varying noise levels and evolutionary patterns across variables. To address this, we propose DynG-Diff, a variable-sensitive dynamic guidance diffusion framework for probabilistic multivariate time-series forecasting: (1) DynG-Diff adopts a two-stage separated training strategy and uses an unconditional diffusion backbone to model the joint distribution of multivariate time series. (2) DynG-Diff introduces a lightweight state-aware policy network that adaptively infers variable reliability from real-time noisy states and one-step denoising estimates, outputting a dynamic guidance strength matrix. (3) DynG-Diff mathematically formulates this dynamic weight as the local precision of the observation distribution, enabling precise guidance for high-confidence variables during inference while filtering out interference from anomalous noise. Extensive experiments on real-world benchmarks demonstrate competitive probabilistic forecasting performance against state-of-the-art conditional diffusion models and improved robustness under severe observation corruption.The implementation code is available at: https://github.com/TT-20011031/DynG-Diff

Single-image super-resolution (SISR) requires global context modeling for structurally consistent reconstruction. Fourier operators are increasingly adopted for global feature modeling. However, their periodic spectral bases constrain the representation of localized aperiodic variations, limiting the recovery of irregular structures and fine details. In dynamical systems, the Laplace neural operator extends Fourier modes to complex frequencies and decomposes the output signal into complementary steady-state and transient responses to jointly model periodic and aperiodic information. We derive, for the first time, an approximate steady-transient decomposition for two-dimensional feature maps, providing an analytical basis for the proposed complex-frequency decomposition. Accordingly, we propose LaST-SR, centered on a Complex-Frequency Decomposition module that couples a global full-spectrum Fourier branch for image-wide dependencies and long-range structural consistency with a window-conditioned local complex-frequency branch for localized, content-dependent aperiodic variations. To fuse the resulting features, we further design a Steady-Transient Collaborative Aggregation module for cross-branch interaction and joint aggregation. Experiments on five benchmarks show that LaST-SR achieves the best PSNR/SSIM among the compared methods for $\times2$ and $\times4$ SISR. Ablation studies further validate the effectiveness of the proposed architecture and its key modeling mechanisms.

Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing benchmarks typically evaluate these domains in isolation, leaving underexplored a key capability: whether models can use textual context to determine how chart evidence should be selected, interpreted, and aggregated. We introduce DocHop, a benchmark for integrated chart--context reasoning in document-style images. In DocHop, the document narrative specifies multi-step compositional constraints, while charts provide the corresponding data values. Questions are grounded on a semantic reference label defined in the narrative, requiring models to resolve target entities from context before aggregating evidence across multiple charts. To enable systematic evaluation, we construct DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, covering 2,074 examples across six task categories. Experiments on a wide range of proprietary and open-source MLLMs show a substantial gap to human performance: annotators achieve over 90% accuracy, while the best model reaches only 62.83%. Reasoning-enhanced models consistently show improved results, but performance degrades as reasoning complexity increases. Overall, DocHop provides a controlled testbed for challenging multi-hop document reasoning.

Scientific knowledge graphs organize entities and relations extracted from scientific literature, but they remain inherently incomplete. Missing typed links in such graphs can therefore represent plausible scientific hypotheses, such as unexplored associations between materials and applications. However, scientific hypothesis discovery is challenging because true discoveries are extremely sparse among typed candidate pairs: graph neural networks (GNNs) are efficient but unreliable for ambiguous cases, while large language models (LLMs) are knowledgeable but too costly to apply exhaustively and are not naturally grounded in graph structures. We propose HyGRAIL, a cost-aware and evidence-grounded framework that combines heterogeneous GNN triage with LLM-based hypothesis review. HyGRAIL first uses a GNN to score candidate hypotheses and identify a validation-calibrated ambiguous region, routing only graph-uncertain cases to LLM review. For each routed hypothesis, HyGRAIL retrieves node-level associations and multi-hop relational paths from the knowledge graph (KG), then converts this structured evidence into natural language through template-based or LLM-based naturalization. An LLM review agent finally judges each hard hypothesis using the naturalized evidence and validation-selected decision criteria. On MatKG, HyGRAIL achieves the best F1 score of 0.429, improving over the strongest prior baseline by 0.242 F1 points and over the GNN-only baseline by 0.322. Meanwhile, GNN triage reduces the LLM call rate by 54.36% on average. Ablation studies further show that retrieved graph evidence is crucial for reliable hypothesis verification and that compact, two-sided evidence is more effective than simply increasing retrieval quantity.

Large Language Models (LLMs) are increasingly deployed in interactive systems where understanding user intent precisely is paramount. A key capability for such systems is effective question clarification, especially when user queries are ambiguous or underspecified. This paper introduces a novel tri-agent framework for the robust evaluation of an LLM's ability to engage in clarifying dialogue. Our framework comprises three distinct LLM-based agents: (1) a Question Clarifying Agent (QCA), the system under evaluation, tasked with identifying ambiguities and posing clarifying questions; (2) a Respondent Agent (RA), designed to simulate human user responses, potentially including irrelevant or challenging replies; and (3) an Evaluator Agent (EA), an LLM-as-a-judge, which assesses the quality of the dialogue based on a comprehensive set of metrics. We detail a methodology for synthetic data generation in the supply chain domain as an example. We propose metrics evaluating ambiguity handling, question quality, dialogue efficiency, language appropriateness, and final intent alignment. We also briefly discuss the validation of the EA against human judgments. This work provides a structured approach to benchmark, validate, and improve the clarification capabilities of conversational LLM applications.

Monolithic world models predict the entire next state at every step, spending capacity re-predicting the static majority of a scene and injecting error into it. We ask whether explicitly modeling change (a per-object change gate plus a residual delta head that perturbs only the objects the gate flags) is a more effective and interpretable bias for physical prediction and control. On a MuJoCo tabletop pushing benchmark scaling from 3 to 8 objects, the sparse/residual model predicts next-state poses 2.5 to 4.6 times more accurately than a dense multilayer perceptron at 8.6 to 11.1 times fewer parameters, sustains change-detection F1 of 0.80 to 0.87 where the dense baseline is degenerate, transfers across object counts with zero retraining (99.4 percent F1 retention), and reaches about 90 percent of its full-data accuracy with a quarter of the data. In autoregressive rollout it compounds far less error, hugging the no-motion floor while the dense model drifts. Finally, inside a sampling-based planner, prediction-only models fail (though a true-simulator oracle solves the task with the identical planner, confirming the planner is sound), but once featurized and trained for the states a planner visits, the sparse model begins to plan (0.23 plus or minus 0.06 success over three seeds) while the dense monolith stays at zero at every seed. Modeling what changes, rather than re-predicting the whole world, is a simple, effective bias for object-centric physical AI; code, data generators, and all checkpoints will be released upon publication.

Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequent replanning, it is inefficient for long-horizon tasks where many rounds are spent on routine action sequences. A natural alternative is to let the agent emit variable-length action chunks. However, naively training such policies with standard reinforcement learning fails: the agent either collapses to single-action behavior or over-commits to excessively long sequences. Both failures share a common root cause: the inability to learn chunk boundaries. We propose SPACE, which addresses this challenge by distilling chunk-boundary supervision from trajectory-induced programmatic skills. We induce two-level programmatic skills from successful trajectories, where subskill boundaries serve as direct chunk-boundary supervision. This temporal structure is then distilled into a primitive-chunk policy via hybrid on-/off-policy optimization with chunk-aware credit assignment. Experiments on ALFWorld and ScienceWorld show that SPACE improves success rates by 7.0%-31.3% over the strongest baseline in each setting while reducing average LLM decision rounds by up to 78.9%.

Vision-language models (VLMs) have achieved remarkable performance by leveraging complementary information from large-scale image-text pairs. However, missing-modality inputs are commonly encountered during real-world deployment, often leading to significant performance degradation. Existing methods primarily enhance model robustness by learning modality compensation strategies from source training data. However, their reliance on source training data makes them difficult to apply when original data are unavailable due to privacy, storage, or accessibility constraints, such as clinical applications and personalized AI services. This raises an important yet underexplored question: can VLMs be efficiently adapted at test time for visual recognition with missing modalities without accessing source training data? To this end, we propose Test-Time Logit Prompting (TLP), a lightweight source-free test-time adaptation framework for visual recognition with missing modalities. To address missing-induced prediction shifts, TLP optimizes logit prompts with uncertainty-aware adjustment and modality-complete consistency regularization, adaptively adjusting prediction confidence while preserving semantic consistency. Extensive experiments across diverse vision-language benchmarks demonstrate that TLP consistently enhances recognition performance under missing-modality scenarios, achieving up to 8\% improvements while requiring only hundreds of tunable parameters and a few test-time optimization steps.

Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often characterize visual grounding using attention from individual layers, leaving its evolution across layers underexplored. We propose CADMP, a lightweight object hallucination detection framework that combines adjacent-layer cross-modal attention drift with prediction sensitivity to targeted visual masking. During decoding, CADMP quantifies distributional changes between consecutive cross-modal attention maps to capture abrupt transitions in visual grounding. It then selects the transition with the largest drift, locates the corresponding visually relevant regions, and measures the change in prediction probability after masking these regions. These two signals provide complementary evidence: attention drift characterizes the stability of internal visual grounding, while probability variation verifies whether a prediction truly depends on the identified visual evidence. A lightweight detector integrates both signals to identify hallucinated predictions. Experiments on multiple benchmarks and representative open-source LVLMs demonstrate that CADMP achieves consistently competitive detection performance. Ablation studies further confirm the complementary contributions of adjacent-layer drift modeling and mask-based grounding verification.

This study proposes a novel Model Predictive Path Integral (MPPI)-based task-space control framework. The proposed framework explicitly solves rigid-body dynamics within a real-time MPC formulation and enforces safety constraints, enabling accurate motion and force control that yields compliant behaviors for safe and effective physical interaction of robotic manipulators in unstructured environments. By leveraging MPPI, the proposed framework efficiently handles nonlinear dynamics that are difficult to solve with conventional MPC approaches in real-time. Furthermore, we develop a torque-sampling-based control architecture that enables efficient exploitation of GPU-based parallelization, resulting in effective compliant and force-aware behaviors. As a result, the proposed framework achieves a solver update rate of over 166 Hz with a 0.18 s prediction horizon, and its performance is validated through real-world experiments on a 7-DoF manipulator.

Image super-resolution, which aims to reconstruct high-resolution images from their low-resolution observations, is fundamental to medical imaging, remote sensing, surveillance, microscopy, and scientific visualization. Traditional model-based methods formulate super-resolution as an inverse problem with hand-crafted regularization priors. While interpretable and theoretically grounded, they rely on fixed assumptions and require computationally intensive iterative solvers. Deep learning methods offer data-driven flexibility by learning nonlinear mappings from low- to high-resolution images, among which diffusion models have achieved particularly impressive perceptual quality. However, the standard diffusion training objective is a pixel-domain noise-prediction loss that does not explicitly enforce perceptual fidelity, which can lead to oversmoothing and loss of fine image structure. To address these limitations, we propose a perceptually regularized diffusion framework that incorporates prior knowledge through perceptual-loss-based regularization, improving training convergence and encouraging the recovery of meaningful image features. Experiments on benchmark datasets demonstrate improved perceptual quality and competitive distortion metrics, highlighting the effectiveness of regularization for diffusion-based super resolution.

Instruction-tuning data are judged by quality metrics, and tuned models are judged by benchmarks, but both judgments pass through an output interface: the surface format in which an answer is written. Using gradient signatures across 12 tasks, four semantically equivalent interfaces, three model families, and controlled corruptions, we show that this interface confounds both measurements. Spectral statistics such as effective rank are provably invariant to interface rotation and empirically blind to semantic corruption, while the direction of the update carries the quality signal. The interface-varying residual is not noise: it identifies each unit's own target task perfectly across all three families. Capability itself is stored relative to the training interface: a skill that raises accuracy by more than 40 points under the training format can be nearly invisible under every other, and correcting a single generation budget flips the measured effect of fine-tuning on GSM8K from a gain into a large loss. Pre-registered interventions delimit where this geometry stops short of control. Data quality and model capability are interface-conditioned quantities, and current practice often reports the interface instead of the content.

Point-of-interest (POI) localization -- matching a user's close-up storefront photograph against large-scale geo-tagged street-view imagery -- underpins map construction, POI verification, and location-based services. Its closest existing paradigm, visual place recognition (VPR), assumes symmetric, whole-image matching of the same scene at a comparable scale; POI localization instead must match a close-up query, in which the target fills the frame, against wide references in which the same POI occupies only a small, off-center region among visually similar shops, under a substantial capture-domain gap. We introduce GeoStore, to our knowledge the first benchmark dedicated to this asymmetric, fine-grained, open-set formulation, and show that global-descriptor methods tuned for symmetric VPR are systematically limited on it, since a single global vector dilutes the small target. We further propose GLAM (Global-to-Local Asymmetric Matching), which couples a retrieval-anchoring global descriptor with an asymmetric local pathway: each reference is kept as a compact set of pooled region tokens and matched against a single query probe through a learnable soft late interaction; at inference, the same tokens enable a lightweight mutual-nearest-neighbor re-ranking. GLAM surpasses strong global and two-stage baselines on Recall@1/5/10 and mAP, with ~5x smaller re-ranking features and ~two orders of magnitude lower per-pair matching cost than prior local re-ranking. The benchmark and code will be publicly released.

Accurate segmentation of polyps and skin lesions is pivotal for clinical diagnosis, yet existing methods struggle with low contrast, ambiguous boundaries, and cross-domain distribution discrepancies. Discriminative networks and most diffusion-based segmentation approaches predict standalone binary masks, leaving the visual priors of large-scale pretrained generative models largely unexploited. We propose InstEditSeg, a unified generative framework that reformulates medical segmentation as an instruction-driven image editing problem. Instead of emitting a mask, the model renders a color-coded overlay on the original image, conditioned on a textual instruction, so that the edited output aligns with the natural image distribution learned by latent diffusion models and mitigates the domain gap between natural and medical imagery. To recover fine anatomical structures, we introduce DINOv3 as an auxiliary visual encoder and a DINO Feature Guidance Block that builds a multi-scale feature pyramid. The pyramid is fused into the diffusion U-Net by channel concatenation and zero-initialized convolution so that hierarchical discriminative priors can be injected without perturbing the pretrained weights. A dual-branch classifier-free guidance strategy requiring only two forward passes per denoising step reduces inference cost. On polyp and skin lesion benchmarks the framework achieves accuracy competitive with strong discriminative baselines, and it further demonstrates concrete advantages of the generative formulation: notably better cross-domain generalization on unseen data, more complete multi-lesion segmentation, instruction-conditioned task control, and sampling flexibility. We also analyze the strengths and limitations of the paradigm, including its color sensitivity and unsupported attribute-conditioned selection. Code is available at: https://github.com/wincharm001/InstEditSeg.

Guideline-consistent semantic segmentation requires more than category recognition, as real-world labeling policies demand fine-grained, task-specific decisions. Recent multi-agent refinement systems improve compliance with such textual guidelines by detecting and correcting errors. However, they are stateless: feedback from the critiquing agent is discarded, causing the same guideline-specific mistakes to be repeatedly rediscovered and corrected across the dataset at the cost of additional refinement. We introduce InsightSeg, an episodic memory mechanism that converts successful correction episodes into reusable, visually grounded insights. A meta-analyzer distills each qualifying episode into directive natural-language insights and anchors them to the local image regions that caused the error using patch-level visual concept vectors. On subsequent images, these concepts are matched against dense patch embeddings to retrieve relevant insights, which condition the segmenting agent before making its first prediction. This shifts the system from correcting recurring errors to preventing them, improving segmentation quality before any refinement occurs. Across Waymo and Cityscapes, InsightSeg improves both first-pass and final guideline-consistent segmentation performance while requiring fewer refinement steps, demonstrating that multi-agent refinement can become more accurate and efficient by drawing on past correction experience.

Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess final-answer quality and reveal little about how different information sources shape the generation process. We propose a causal and temporal evaluation framework that traces the evolving roles of visual input, question text, and generated prefixes during autoregressive decoding. Grounded in a Structural Causal Model, we use interventions and backdoor adjustment to derive three step-indexed causal-drive metrics---Visual Causal Drive (VCD), Question Causal Drive (QCD), and Prefix Causal Drive (PCD)---for characterizing source-specific generation patterns without requiring reference answers. Experiments on Qwen3-VL-8B-Instruct across MAVIS, LLaVA-Video-178K, and MiraData, together with cross-model validation on InternVL2-8B, reveal a consistent transition from stronger early question and visual guidance toward increasing reliance on generated prefixes. Randomized-intervention validation shows that QCD and PCD reduce recovery error over observational PMI baselines by 34.8\% and 47.1\%, respectively. On VLMBias, the prefix--visual imbalance score achieves 0.767 AUROC and 0.873 AUPRC for distinguishing prior-driven from visually grounded generations. These results show that causal-drive trajectories provide complementary source-level diagnostics for multimodal generation.

Agent evaluations face two distinct evidentiary questions: whether a reported claim is recomputable from retained evidence (sufficiency), and whether the retained records cover the committed experiment set (coverage). Generic logs and hash-linked transcripts answer neither reliably. We introduce ClaimReceipt, a claim-relative receipt specification and selective verifier that binds typed transaction evidence to a signed experiment manifest and returns PASS, INVALID, or INCONCLUSIVE per claim. We freeze the specification before implementation (SHA-256 18d109...b81). On 1,392 historical buyer--seller records, a CR-2 verifier reproduces all five manually labeled audit verdicts, exactly replays 600 deterministic and 792 post-generation records, makes every one of 13 declared field groups non-redundant under tested ablations, and returns the expected result on 11/11 semantic faults with 0/8 false positives. We then run a separate prospective CR-3 epoch: 30 assignments are committed before inference, terminal receipts are signed and chained, and private evidence is encrypted for an auditor. Complete evidence yields coverage and accounting PASS; withholding one terminal receipt returns INCONCLUSIVE_COVERAGE, while withholding all private openings preserves coverage and protocol verification but makes economic claims inconclusive, exactly matching a preregistered prediction. Receipt instrumentation adds 0.021% of model-inference time and 9.9 KB per transaction. A specification-legibility probe indicates that our own frozen specification is not yet unambiguous to an independent reader. Claim verification therefore requires both claim-sufficient evidence and a committed universe against which omissions become visible.

As LLM coding agents increasingly perform end-to-end engineering work, we lack empirical characterization of how they behave on systems-level requirements: schema design, async orchestration, configuration correctness, and retrieval-filtering trade-offs. We present a case study of one such agent implementing a multi-component data system against a detailed pre-existing specification. Storage technologies, schema, entity-resolution algorithm, and retrieval-filtering strategy were fixed in advance; the agent autonomy was in the implementation, in diagnosing and fixing defects it introduced, and in interaction-design choices left open. Over a single session, we catalog five such defects, categorized by constraint violated and detection method. We further evaluate, on the public HotpotQA benchmark, the one retrieval trade-off specified in that architecture: restricting candidates to a graph-identified entity set before ranking versus unfiltered search. We substitute the benchmark gold evidence labels for entity identification, since we lacked LLM access to run that stage, and report standard recall rather than the benchmark own accuracy metrics. Across retrieval budgets from 1 to 10 and 100 questions against a pooled corpus of 2994 paragraphs, filtered recall reaches its ceiling by a budget of 3, expected once candidates are restricted to the gold paragraphs themselves, while unfiltered search recovers all required evidence only 69 percent of the time even at a budget of 10, a gap that holds at every budget tested, with sign test p less than 0.0001. We close with a discussion of where the agent autonomy succeeded versus required correction, including one instance where a claimed performance fix was never re-measured on the regression that motivated it.

As ambitious space telescope concepts such as ultra-lightweight planar diffractive optical elements (DOEs) emerge, validating the performance remains a major computational challenge. Conventional Fourier propagation algorithms were observed to fail at meter-class apertures due to severe memory limits caused by rigid grid-sampling requirements, and the scaled-down proxy models used for reflector telescopes cannot be applied, since scaling compresses the outermost zones that govern resolution. We benchmarked five Fourier-based propagators against a common Fresnel diffraction integral and found that only those decoupling the focal-plane grid from the input aperture converge within a 1% error threshold. With these findings, we implemented an optimized, stripe-processed Chirp Z-Transform (CZT) framework, evaluating the focal spot strictly within a fixed region of interest to reduce peak memory usage. Applied to five full-aperture configurations from 1.0 m to 5.0 m at f/# = 5, the framework predicted spatial resolution and diffraction efficiency to within 0.001% and 0.16% of analytical references, with modulation transfer function results cross-checked by two analytical extraction methods, all within 6.4 GB of memory on a single consumer-grade GPU. This simulation study represents first steps toward quantifying the expected results of ambitious space telescope concepts and aids the mission development (or selection) phase. With a highly accurate, memory-efficient validation tool, the findings obtained will be used to guide the fabrication decisions of future hardware, optical testing, and physical deployment mechanisms of large-scale diffractive telescopes.

AI is rapidly advancing neuroscience, yet many laboratories fail to fully unleash its potential due to significant interdisciplinary barriers. While pre-trained neural models for physiological data are progressing quickly, their heterogeneous architectures and modality-specific constraints hinder systematic integration, selection, and evaluation. Despite recent advances in large language model (LLM)-based agent systems for intelligent scientific applications, existing approaches often still lack the domain expertise required to effectively select and coordinate diverse neuroscience pre-trained models and handle unique data types in this domain. We present NS-Copilot, an LLM-driven multi-agent system for neuroscience analysis that autonomously supports end-to-end workflows for diverse professional tasks. It unifies domain-specific pre-trained models and supports key neuroscience modalities, including EEG and extracellular spike data, through a natural-language interface. Given raw data and a task description, NS-Copilot orchestrates agents with specialized roles for planning, adaptive control, code generation, and result synthesis, enabling analysis without dataset-specific heuristics. We evaluate NS-Copilot on neuroscience benchmarks spanning Alzheimer's disease, Parkinson's disease, and working memory spike decoding. Across 8 trials per task, the system consistently outperforms strong baselines on the primary metric, demonstrating the ability of NS-Copilot for effective and scalable neuroscience analysis.

Augmenting the dexterity of human surgeons has the potential to free them from tedious subtasks. We consider debridement (removal of diseased or dead tissue fragments), which is challenging due to imprecision in spatial perception and cable actuation. We develop an augmented dexterity system for surgical debridement that uses visual servoing to align the cable-driven gripper with the target position in the image plane, and then introduces a novel approach to depth control, MACAW: Monocular Adaptive Compact Attention Windows. Across 100 physical trials using the da Vinci Research Kit (dVRK) robot, camera-frame servoing reduced average gripper position offset from 37 to fewer than 5 pixels within 4 optimization steps, taking an average of only 0.39s. MACAW significantly outperforms procedural and learned VLA baselines, achieving a 93% success rate at 11 seconds per fragment, yielding a throughput of 304 fragments per hour. Extending MACAW to a bimanual debridement setup maintains a 92% success rate at an average of 7 seconds per fragment, increasing the throughput to 473 fragments per hour.

Autonomous agent runtimes execute tool actions that mutate databases, repositories, and cloud services across organizational boundaries. Authorization and local compensation cover pre-action admission and in-runtime rollback, but neither settles the residual harm left after a permitted action fails. We design Recourse, a smart-contract settlement protocol for compensable agent side effects that binds each admitted action to scope, recovery, evidence, payout, and collateral. Recourse separates ex ante eligibility from ex post objective settleability: typed receipts make objective residual claims computable under an optimistic-oracle challenge pattern, while subjective or incomplete claims route to ERC-792 arbitration or exclusion. We implement the contract suite, deploy it on Base Sepolia, build adapters against Postgres, Git, and cloud-compatible local sandboxes, and evaluate the system on a deterministic harness, sandbox traces, adversarial sweeps, and property-based fuzzing. Against authorization-only and local-compensation baselines, bonded coverage cuts uncompensated harm. The on-chain tier supplies neutral custody, public challenge, non-cooperative payout, and portable history under cross-organizational trust assumptions.

Dexterous manipulation with multi-fingered robot hands promises human-level dexterity, but collecting large-scale dexterous robot hand data remains difficult. Learning from human demonstrations has emerged as a scalable alternative to robot teleoperation, providing strong priors on object interaction and contact strategies. Recent sim-to-real RL methods incorporate such priors, but often (i) omit rewards that explicitly incentivize precise contact, yielding weak real-world performance, and/or (ii) generalize poorly to unseen object instances. We propose DemoMimic (Dexterous Motion Mimic), a policy that manipulates objects by focusing on their geometry local to the contact points. Its contact-centric rewards encourage precise contact and improve sim-to-real consistency, yielding a single real-world policy that transfers across objects of varying shape, scale, mass, and friction wherever local contact structure is preserved. Real-world ablations show that DemoMimic achieves 71% success across 16 objects, four tasks, and two robot-hand embodiments, with the smallest sim-to-real drop compared to baselines.

Long-horizon agents execute thousands of actions, resulting in sequential failures rather than isolated errors. When a coding agent deletes a production database or a prompt injection spreads across agents, the incident raises questions of causality, authority, and non-repudiable third-party verification. The Agent Flight Recorder captures each agent action as a structured, canonically serialized event binding eight semantic fields from intent through execution to provenance. Hash chaining and Merkle batching provide tamper evidence and compact inclusion proofs. For cross-organizational disputes where no party's infrastructure qualifies as neutral ground, periodic on-chain anchoring of epoch roots lets any verifier with the disclosed payload and Merkle proof check the record independently, without pre-agreeing on a trusted intermediary. The on-chain footprint is minimal: each anchor stores a 32-byte epoch root and a back-pointer, and no event content touches the chain. We evaluate the system across five cumulative ablation configurations on synthetic agent workloads. The full system adds ~48 microseconds median per-event latency and 512 bytes per event. L2 anchoring costs $2.30 per 100K events at 100-event epochs. The full integrity stack detects edit, delete, reorder, and fork tampering at 100% with zero false positives. Structured forensic queries achieve 1.0 precision on guardrail and delegation lookups where unstructured text search yields 0.013 and 0.077 respectively.

The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe computational bottleneck. Traditional sparse attention methods mitigate this through fixed patterns or offline profiling, but lack the flexibility to adapt to input-dependent attention structure. Recent dynamic methods address this by routing heads to sparse patterns in real-time, but rely on indirect routing proxies with overhead and budget allocation mechanisms that overlook the post-softmax mass hierarchy. We present CRISP (Cliff-awaRe Input-adaptive Sparse Prefilling), which identifies and addresses two structural challenges in this dynamic routing paradigm. First, we show that the routing decision can be read directly off the structure of the proxy attention map. We replace the Jensen-Shannon Divergence (JSD) routing with C_struct, a structural proxy that measures mass at Vertical-Slash compatible positions and reproduces JSD's routing decisions while eliminating both the pooled matmul and subsequent KL divergence overhead. Second, we formalize the post-softmax mass cliff and demonstrate theoretically that strictly cumulative coverage thresholds accumulate O(n) background noise at long contexts. CRISP navigates this via a sink-aware threshold grounded in the noise floor. Empirically, across InfiniteBench, RULER and LongBench on two model families, CRISP is the strongest sparse method overall and matches or exceeds exact dense attention on retrieval-heavy benchmarks, recovering up to +28.0 pp on retrieval tasks over baselines and achieving up to a 5.30x attention speedup at 512k tokens, driven primarily by our O(n) noise elimination during selection while preserving structural integrity.

Energy poverty is nearly absent from NLP-for-social-good, and the little existing work is either static retrieval/QA or relies on carbon-intensive cloud LLMs, a self-defeating "computational irony" for a humanitarian setting. We present EqGrid, a closed-loop simulation in which a low-frequency, open-weight LLM policy agent sets price and carbon bounds and targeted subsidies over a community of empirically-grounded household personas, while high-frequency multi-agent RL traders clear a continuous double auction constrained by a physical distribution grid (IEEE-33-bus with Dynamic Operating Envelopes). Our contribution is threefold and directly addresses how to measure the social impact of AI: (i) grounded personas (region-matched socio-demographics) whose load curves are checked for shape and level realism against real smart-meter data; (ii) formal energy-poverty equity metrics (Energy Burden, Gini of EB, LIHC) showing the intervention reduces burden inequality without raising net grid cost; and (iii) a compute-efficiency frontier that measures how much equity performance survives compressing the policy agent from a 235B teacher down to a sub-1B model deployable on a laptop, in estimated energy/carbon per decision. A decoupled-safety design (the LLM sets bounds; a validate-and-project grid gate executes) yields zero grid-constraint violations versus 55 under direct LLM control. On energy-poverty equity, the LLM policy lowers the Gini of energy burden to 0.305 (from 0.351) and mean burden by 28% while cutting cost (outperforming a tuned rule baseline), and a 3B-active model retains 95% of the benefit at roughly 9x lower inference energy than the teacher, with even a 0.8B on-device model retaining 92% at roughly 24x lower energy. We will release code and configs.

Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another agent is not another observation: apparently independent reports may descend from the same evidence, and genuinely independent evidence can produce nearly identical reports. We formalize this as an epistemic Sybil problem. A report Z is an epistemic Sybil extension relative to reports R when I(Theta; Z | R) = 0. No report-only aggregator can generally distinguish replication from independent corroboration: identical reports can warrant different posteriors under unobserved ancestry. A Gaussian shared-root model shows common ancestry does not imply complete redundancy. Repeated extraction adds information toward a source-level ceiling, and correlated extraction errors, which a shared base model can induce among independent agents, lower that ceiling further. We test these predictions with more than 20,000 controlled LLM-agent report and extraction calls on synthetic evidentiary documents. Holding one evidence root fixed while report multiplicity rises from 1 to 32 collapses naive posterior coverage from 0.940 to 0.263. Holding report count fixed while evidence-root multiplicity rises from 1 to 16 closes the gap, and the aggregators are statistically indistinguishable at k = 16. The agent's replicate extraction errors are correlated (gamma_cal = 0.719, estimated out of sample), and a correlated-extraction aggregator restores calibration accordingly. A controlled manipulation isolates representation similarity from evidential ancestry. It changes a report-space deduplication mechanism's mean inferred cluster count by 1.425 (95% CI [1.363, 1.485]), whereas a fourfold change in true ancestry changes it by only 0.040 ([-0.045, 0.120]). Collective inference should therefore track evidential ancestry and dependence, not agent or report multiplicity or similarity.

Multi-agent systems have shown strong performance in domains with reliable verifiers such as coding, where multi-parallel candidate generation selected by a verifier is effective. However, such pipelines would not generalize to open-ended, long-horizon research tasks without a verifier. While majority voting or self-consistency is often used to reach consensus as a proxy verifier, parallel agents repeatedly explore the same evidence, while access to peers' partial findings cause search to converge on an early candidate before alternatives are tested. We present ArcticSwarm, a multi-agent research architecture that separates evidence gathering from evidence integration. Subagents publish findings to a shared bulletin board, while gated isolation lets selected search tasks maintain their own prior, preventing early consensus. Structured review at three commitment boundaries enforce only confident candidates to be propagated. As a result, ArcticSwarm reaches 82.6% on the full BrowseComp-Plus set with the open-weight Qwen 3.5-27B model, compared with 78.8% without gated isolation and 74.5% additionally with structured review disabled, outperforming aligned baseline MiroFlow runs (70.6%). Extending to live-web BrowseComp, ArcticSwarm reaches 73.6% with GPT-5, which is well above the reported provider system (54.9%) and MiroFlow (63.4%). Overall, the results show that restricting peer reads during evidence gathering and strengthening commitment boundaries before a hypothesis is shared can broaden search and improve long-horizon multi-agent deep research.

Embedding-based code retrieval is a core component of coding agents and retrieval-augmented code generation, where retrieving correct code matters more than retrieving lexically similar code. Existing code-retrieval benchmarks do not plant controlled, execution-verified single-edit variants of each query's canonical implementation in the search pool, leaving the question of whether embeddings can functionally discriminate correct from near-clone-but-incorrect code unanswered in a retrieval setting. Resolving this requires a benchmark whose search pool itself contains the relevant counterfactuals -- execution-verified buggy variants near-identical to each canonical -- so that a retriever's rank ordering can be directly tested for functional discrimination rather than topical or identity overlap. We introduce ExecRetrieval, 939 Python tasks each paired with one execution-verified canonical implementation and up to four execution-verified buggy distractors, each generated by a mechanical mutation making a single targeted edit, and evaluate 23 dense embedding configurations plus BM25 under provider-native invocation with paired McNemar tests and query-level bootstrap intervals. With near-clone counterfactuals in the pool, the top hosted system reaches exec@10 = 1.00 but only exec@1 = 0.331; rank-1 misses are paired buggy variants 91.5-99.4% of the time across the four leading systems, and the canonical scores below at least one of its four paired distractors in 67-78% of queries on the leading systems. The full dataset, execution oracle, embedding matrices, environment snapshot, and pairwise statistical tests are released at the URL in Appendix D.

Persistent memory supports personalized agents, but a stale stored fact can override current authoritative evidence without warning. We study when this harm begins as model capability changes. We evaluate a frozen, closed-set, action-scored benchmark with 2 suites that represent 2 different meanings of "no memory" (a Benefit suite, unsolvable without the stored fact, and a Safety suite, in which an authoritative tool always holds the correct value), on a same-family model-size series (Qwen3 0.6/1.7/4/8B). The Memory Trust Gap reflects over-trust rather than confusion. In the Benefit suite, models answer with the stale value 0.92-1.00 of the time at every scale. In the Safety suite, harm below the no-memory baseline under the trap conditions ($Δ_{\mathrm{mem}}$) is capability-gated, with the larger models collapsing most once a stale note is made to look current. In a $2\times2\times2\times2$ factorial, which feature triggers over-trust depends on both the feature and model scale. Removing a label amplifies over-trust at every size, and a recency feature (stale dated newer) fools the larger models harder. Source authority is weak and scale-flat, and position changes from positive to negative across the Qwen3 model-size series. We confirm these scale interactions with direct cross-size contrast tests rather than overlapping per-model intervals. Mitigation is likewise capability-dependent: exposing metadata improves accuracy for the capable models, but only pre-resolving the conflict restores accuracy for the 2 smaller checkpoints. The same pattern appears on the capable models in an independent Llama-Instruct model-size series and on 2 external datasets (RGB, MisBench). A framing control finds no consistent advantage for the memory label: at the 3 smaller scales, models trust a stale document more than a stale memory; at 8B, the difference is not significant.

Recorded lecture videos, often enhanced with search and summarization features, are a standard study resource. However, students cannot easily ask course specific questions or verify answers against an instructor's lecture. We report a semester-long deployment of VideoPoints platform with a retrieval-augmented chatbot that answers from course lecture materials and returns timestamped citations. The chatbot retrieves only from the active course, uses chapter summaries to guide transcript ranking, and returns clickable timestamped citations. Students used it for quick lookups and exam review. Across 833 messages, 70.5% included citations, none crossed a course boundary, and when no lecture evidence matched, the chatbot usually declined rather than answering. Among the users, citations were the most consistently useful feature, while practice-question generation was the strongest unmet request. We also evaluated the design on the real-world test split of EduVidQA, a public multimodal benchmark for lecture-video question answering. Our design improved correct-lecture retrieval by 6.3 percentage points over dense-only retrieval. Together, the results show that effective deployment depends on course isolation, supported citations, and alignment with students' study practices.

We introduce a novel Divide and Conquer control design methodology leveraging differential games in single-agent, multi-objective dynamical systems. The proposed framework associates each control objective with a virtual input and establishes a non-cooperative, finite or infinite horizon differential game among representative players. Each player optimizes a distinct virtual cost function tailored to its specific goal, the full system state, and the other virtual inputs, while accounting for the remaining players' optimal policies. By establishing a Nash Equilibrium for this game, we synthesize a composite controller that achieves a stable balance across competing objectives, providing control engineers with an intuitive and modular framework for parameter re-tuning throughout the design cycle. We provide formal mathematical derivations for both continuous-time and discrete-time dynamical systems, targeting large-scale single-agent applications where complex, dynamically conflicting control objectives make global weighting intractable. To demonstrate the methodology, we developed an open-source Python package implementing a novel numerical algorithm for solving Coupled Algebraic Riccati Equations arising in infinite-horizon differential games. We evaluate the approach on two benchmark case studies: an inverted pendulum on a cart and a non-linear hierarchically controlled quadrotor. The resulting closed-loop performance is compared against the classical Linear Quadratic Regulator (LQR) across various transient and steady-state control metrics, demonstrating superior trajectory tracking and robust multi-objective regulation.

Farsi, spoken by more than 120 million people, lacks a comprehensive benchmark for dialogue generation and understanding. We introduce TALKFA, a unified benchmark comprising three complementary datasets: (1) WIKI-FADIAL, 4.2K Wikipedia-grounded dialogues for knowledge-grounded generation; (2) DAILYDIALOG-FA, 6.6K dialogues annotated for dialogue acts and emotions; and (3) PLAYDIAL-FA, 2.1K theatrical dialogues with sentiment labels. While LLMs assist data construction, every dialogue undergoes multi-stage review and revision by native Farsi speakers, and only the final human-approved dialogues are released. Experiments with six LLAMA and MISTRAL models show that LoRA substantially improves dialogue generation while requiring only 25-50% of the training data to recover over 90% of the final performance gains. Across classification tasks, FABERT achieves the best dialogue-act performance, LORA-MISTRAL-7B performs best on emotion recognition, and MISTRAL-24B achieves the highest sentiment score. Human evaluation and independent external validation demonstrate the reliability of the benchmark, while comparisons with GPT-4.1 as an LLM judge reveal that automatic metrics substantially overestimate dialogue quality. Zero-shot evaluation with frontier LLMs further shows that TalkFa remains a challenging benchmark. We will release all datasets, annotation guidelines, code, and checkpoints.

Real-world communication often requires pragmatic reasoning: interpreting meanings implied through context and cultural convention rather than stated literally. Existing pragmatic evaluation remains largely limited to English and high-resource languages, leaving Indic languages unexplored despite their linguistic and cultural diversity. We introduce VakyArth, the first pragmatic benchmark for Indic languages, designed as a diagnostic evaluation covering Hindi, Punjabi, Tamil, and Malayalam. VakyArth evaluates models across five phenomena: deixis, speech acts, implicature, social pragmatics, and coherence; through multiple-choice questions, natural language inference, and translation, with all items authored by native speakers. Across multilingual large language models (LLMs) of varying families and sizes, we find consistent failures on pragmatic meanings rooted in Indic linguistic and cultural conventions. Our analysis shows systematic differences across languages and tasks: MCQ accuracy exceeds NLI accuracy in all model-language combinations, translation performance does not reliably track pragmatic understanding, and Indo-Aryan languages show a translation advantage over Dravidian languages. We further show that automatic translation metrics can miss fluent but pragmatically unfaithful outputs, especially for implicature and deixis.

Future 6G networks will rely on Large Language Model (LLM) agents to manage the Radio Access Network (RAN). However, current architectures assume inter-agent messages convey objective facts. A message is instead a \emph{trace} of the sender's reasoning: it carries a subjective conclusion, so a syntactically valid report can propagate an AI hallucination and trigger a cascading outage invisible to protocol validation. Reading such a trace requires a Theory of Mind (ToM)---before acting, the receiver must model what the peer believes, and what a peer in that position should have believed. Modeling these interactions as cognitive channels on a cellular sheaf, we obtain a unified framework for resilient multi-agent systems, from which five design principles emerge: (i) a message is evidence of the sender's hidden reasoning; (ii) trust is a continuous cognitive Signal-to-Noise Ratio (SNR)---asserted precision over deviation from the modeled peer belief; (iii) network-wide consistency and resistance to hallucination contagion are computable via the sheaf's Laplacian; (iv) peer-modeling must halt at exactly two levels to conserve compute and survive mutual information decay; and (v) credible capacity is bounded by operational goal alignment, not link bandwidth. A signaling-storm study on locally deployed 1B-parameter telecom language models validates it: cognitive SNR isolates a hallucinating peer that three of its four neighbors agree with, where a divergence gate ranks every wrong peer above the right one; only depth two ToM recovers the correct action; and the spectral gap decides whether a topology reaches consistency inside the near-real-time budget.

Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vision-language models still lack. We introduce MemeCULT-1K, a multilingual benchmark of 1,000 South Asian memes in Bengali, English, and Hindi, where each meme is paired with a cultural context note and three human-written explanations, along with a supplementary set of 54 Bengali regional dialect memes. We evaluate thirteen popular Vision Language Models (VLMs) under two settings: meme-only and context-aware. Providing minimal cultural context yields consistent gains across all models and languages: mean SBERT similarity improves from 44.6 to 56.4 (+11.8), BLEURT from 37.3 to 42.3 (+5.0), and LLM-as-a-Judge scores from 2.57 to 3.43 out of 5 (+0.86). Fine-grained error analysis reveals that closed-source models fail mainly on entity and reference misidentification, while open-source models are bottlenecked by broader cultural knowledge gaps, with linguistic and phonological failures proving the most context-resistant across both. These results highlight the difficulty of culturally grounded meme understanding and motivate future work on explicit cultural knowledge integration. Our dataset and code are publicly available at TawsifDipto17/MemeCULT-1K.

Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, existing approaches suffer from two key challenges: brittle multi-step and multi-turn reasoning caused by incompatible tool output types and API schemas, and performance degradation under large tool catalogues. To address these, we introduce \textbf{Tool Primitives}, a design that replaces rigid API schema-based invocation with natural language as the interface for tool calling, where each tool is wrapped with an LLM interface that handles schema resolution and execution internally, enabling natural inter-tool communication for nested and multi-turn tool calling. Building on Tool Primitives, we host \textbf{ToolFace}, a centralized repository of 25,519 functions from which LLMs dynamically retrieve only the relevant tools at inference time, eliminating the need to enumerate raw API schemas in context. To orchestrate Tool Primitives and ToolFace reliably in complex settings, we further propose \textbf{HEART}, a \textbf{H}arness \textbf{E}ngineering framework via \textbf{A}gent-native, \textbf{R}eusable \textbf{T}ool Primitives, comprising a Planner, Router, and Verifier that jointly support dynamic tool invocation planning, multi-step execution, and feedback-driven recovery. Experiments on five benchmarks demonstrate that HEART outperforms SFT-based models by $10\%$ on average and surpasses GPT-5.4, Claude-4.6-Sonnet, and Gemini-3.1-Pro by $6\%$ on average while reducing API cost by up to $85\%$. On 50 real-world tasks, HEART achieves $84\%$ task completion, $3.8\times$ the average of three frontier commercial models ($22\%$).

LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the internal procedure by which they assign a rating remains poorly understood. We investigate this procedure mechanistically through an eight-attack perturbation taxonomy across the Readability and Adequacy dimensions of NLG quality, a generation pipeline that produces paired clean and corrupt summaries with controlled error intensity and explicit token-level modification maps, and a four-experiment battery of causal tracing, logit-lens vocabulary projection, and attention-head knockout applied to Themis (Llama-3-8B) and Prometheus (Mistral-7B). Both evaluators implement a structured, coherent evaluation pipeline operating in two stages: below layer 15, attention performs local error comparison and routes the result to the final input position; above it, the MLP cascade integrates the signal and writes the rating, with the decision crystallizing in the residual stream at a sharp late layer (L = 26 on Themis, L = 25 on Prometheus). Furthermore, a base-model control at the same scale (Llama-3-8B) reproduces the routing architecture and crystallization but not the stage separation, isolating the two mechanisms that fine-tuning specifically installs, suppression of below-L15 MLP contribution at the last position and a two-layer advance of the crystallization depth, indicating that fine-tuning sculpts an existing substrate rather than building the pipeline from scratch. We release the source code and data at https://github.com/himil-v/judge-mech

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We propose PTA-IRT, a Privileged Trajectory-Aware Item Response Theory framework that fuses process and outcome signals. Historical execution trajectories supply process-level evidence beyond pass/fail, such as explored context, attempted edits, and solving paths, which PTA-IRT uses as privileged information for calibration subset selection and ability estimation. Under low calibration budgets, PTA-IRT consistently outperforms prior IRT baselines on score and ranking recovery across four SWE benchmarks. Code and data are publicly available at https://github.com/DeepSoftwareAnalytics/PTA-IRT.

The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods typically provide context as task-level support, without explicitly identifying the critical tokens that require fine-grained repository context during generation. During the autoregressive generation process of LLMs, errors often concentrate at a small number of decisive positions: once such tokens are generated incorrectly, subsequent code may follow an incorrect semantic path and eventually lead to functional failure. We refer to these positions as "critical tokens". In this paper, we propose ACToR, an adaptive critical token-aware retrieval framework for repository-level code generation. ACToR identifies critical tokens during generation and triggers targeted retrieval on demand to provide repository context at these decisive positions. In addition, we design a position-aware weighting method for dense retrievers to prioritize context that is more informative for generation. We evaluate ACToR on two representative repository-level benchmarks, RepoExec and CoderEval. Experimental results show that ACToR consistently outperforms state-of-the-art methods, achieving relative improvements of 8.4% on RepoExec and 15.4% on CoderEval. Beyond performance gains, we systematically quantify the impact of critical tokens, revealing their central role in major generation failures and highlighting the necessity of targeted retrieval strategies. We provide the code and data at https://github.com/DeepSoftwareAnalytics/ACToR.

Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate through dependencies and cleanup. We introduce CordisBench, a 1,200-question benchmark of this lifecycle reasoning. It combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencies and cleanup, and asks models to identify affected components, predict state after a specified teardown order, determine which conditions hold under all or some orders, and choose reconfigurations that succeed when executed. Across these tasks, we evaluate three efficiency-oriented models at low reasoning effort with 2, 4, 8, 16, 24, or 32 relevant interactions, using deterministic task-specific scoring. Models usually handle small systems well but grow less reliable as more interactions become relevant, especially when predicting final state and when reasoning across teardown orders. Additional inference effort recovers marked gains for some models. The cost is nontrivial: on our 16-interaction subset, GPT-5.6 Luna uses nearly 3,000 reasoning tokens per question at medium effort. For these controlled instances, that cost is avoidable: an independent finite reference semantics agrees with Cordis execution on every observation and action outcome used for scoring across all 528 executable questions.

Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent, preferences, and causal structure in forms interpretable by both humans and modern language models. We call this paradigm Verbal Reinforcement Learning (VRL) and offer the first unified account of it. We organize the field around a single axis, \textit{when} verbal feedback takes effect in an agent's lifecycle and \textit{what} it modifies, yielding three pillars: (1) \textbf{Language as Grounding Signal}, where language defines the task itself by specifying goals, states, and reward structures; (2) \textbf{Language as Deliberative Feedback}, where natural language guides reasoning at test time without the need to update model parameters; (3) \textbf{Language as Learning Signal}, where language-based feedback shapes model parameters through training. Within each pillar, we synthesize representative work, distinguish key subcategories of approaches, and outline the distinct role language plays in shaping agent behavior. Together, this taxonomy shows how verbal reinforcement is reshaping agent development, while also defining the challenges and opportunities for building more capable and aligned agents.

Real-world robotic assembly at sub-millimeter tolerances demands spatial precision, compliant interaction, and robustness to contact failures. We present Facet-0, a robotic foundation model that predicts and values the contact consequences of its actions. Facet-0 unifies multimodal representation learning and reinforcement learning (RL) post-training around a joint action-wrench proposal: a causal wrench history is aligned with vision-language semantics and kinematic state, and flow matching generates each action chunk together with the future wrist-wrench profile it is expected to induce. Deployment rollouts train a distributional Action-Wrench Critic to distinguish motions with similar task progress but different contact outcomes, while phase-aware rewards and contact-selective credit concentrate policy improvement on decisive interactions. To accommodate part-specific dynamics, a lightweight bounded actor reuses the frozen representation for on-robot adaptation; RL remains defined over executable Cartesian actions, while an auxiliary wrench head preserves predictive, non-commanded action-contact coupling. Trained on ManuFacet-1K, a 1,000-hour force-synchronized corpus spanning three embodiments and multiple manufacturing cells, the bounded task-adapted system reaches 82% mean success on five sub-millimeter computer-assembly tasks, compared with 15% for the strongest baseline, with 0.5 mm placement accuracy and 50 ms command latency.

We present SG-AMP, integrating robust depth completion with input-conditioned uncertainty, persistent panoptic mapping, plant scene-graph reasoning, and semantics-aware active view-motion planning. Beyond inspecting uncertain observed regions, the scene graph explicitly hypothesizes unobserved pepper--peduncle attachments and directs close-range sensing toward them. Candidate views are selected according to expected information gain, while class-dependent motion costs distinguish protected peppers, peduncles, and stems from conditionally traversable foliage. On pepper data, the perception network achieves $55.27\%$ semantic mIoU, $38.67\%$ PQ, and $40.62\,\mathrm{mm}$ depth RMSE, while input-conditioned uncertainty improves NYUv2 NLL from $-1.6518$ to $-1.6925$ and AUSE from $0.0102$ to $0.0087$.

Generalized semi-infinite programs (GSIPs) arise in robust optimal control whenever the admissible uncertainty depends on the state or controls. Existing GSIP methods either impose restrictive structural assumptions or require global optimization that scales poorly to control problems. We present a general framework that reformulates any GSIP with mild regularity as an existence-constrained semi-infinite program, smoothing its disjunctive feasibility condition into differentiable existence constraints over a fixed index superset. The resulting program is solved by established adaptive discretization (cutting-plane) methods using only off-the-shelf nonlinear-programming solvers, and converges under standard assumptions. Treating the state trajectory as part of the uncertainty extends the framework to robust nonlinear optimal control with state-dependent uncertainty. We demonstrate it on a nonconvex benchmark GSIP and a satellite de-tumbling problem with dynamically varying inertia.

There is tremendous value in humanoid robots taking on physically demanding, hazardous, and repetitive work in spaces built for humans. However, a useful robot for these spaces must coordinate locomotion, whole-body motion, perception, contact, and operator supervision. We present a robot-local, runtime-editable behavior authoring and runtime system that addresses these challenges. We argue that behavior architecture can be a primary enabler of capability, speed, and reliability, and that runtime editability enables fast behavior creation, adaptation, extension, and combination. Our behavior architecture combines object-centric Affordance Templates, a tree structure that provides organization and logic, and runtime-editable perception through a behavior scene and primitive scene actions. Our operator interface remains continuously synchronized to the robot for runtime authoring, monitoring, and repair. Action primitives execute through a whole-body controller that supports concurrent body motions and walking. Demonstrations of our system cover six task variants on Unitree H1-2 and Alex. We execute a push door traversal in 34 seconds and sort six balls by color in 45 seconds under human disturbance. Timed authoring sessions show scratch creation of new loco-manipulation behaviors and adaptation of existing ones in hours. Comparison against the literature finds our approach to be competitive with recent learned systems.

We investigate the refractive index $n$ of LiF using DFT+G$_0$W$_0$+BSE, with ionic-temperature effects included through QMD. We calculate photon-energy dispersions $n(ω)$ and $k(ω)$ at ambient pressure and $n(ρ,T)$ at 532 and 1550 nm under shock compression, where $ρ$ and $T$ vary together. Quasiparticle band structures at ambient and compressed conditions and the ambient-pressure orbital-projected density of states connect the optical response to the electronic structure. At ambient pressure, G$_0$W$_0$ yields a quasiparticle gap of 14.25 eV, close to the experimental 14.2 eV, while BSE reproduces the main excitonic feature at 12.5 eV, close to the observed 12.6 eV. Quasiparticle and excitonic effects are thus essential for accurate optical dispersion; the hybrid HSE functional does not reproduce the optical spectra. Along the principal Hugoniot up to 140 GPa, $n(ρ)$ agrees closely with shock data at 1550 nm and acceptably at 532 nm, and agrees better overall than earlier first-principles calculations. Above approximately 110-120 GPa, QMD produces a downturn relative to cold $n(ρ)$ curves, suggesting that ionic dynamics may contribute to deviations from the linear $n$-$ρ$ Gladstone-Dale relation. QMD-sampling and finite-k-grid uncertainties are estimated, and transition-peak broadening is assessed using a recently proposed criterion. The gap increases under pressure, with a transition to a $Γ\to\mathrm L$ indirect gap near 50 GPa. An exploratory calculation at approximately 1400 GPa finds a gap of about 24 eV, disfavoring gap-closure metallization. Structural and elastic benchmarks of the underlying models are also provided.

The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, which requires agents with partial information to communicate under pressure. We find that language evolution does occur between LLM agents, that the resulting languages are compositional and morphologically productive, and that they deviate from the LLMs' English prior in ways that render them incomprehensible to humans. Moreover, we identify several qualities essential to this evolution: pressure towards efficiency; the strength of the models backing the agents; and access to a "postmortem" stage in which agents can agree on linguistic conventions. Importantly, we observe that different conditions govern the transmission of language to new agents. Specifically, we find that agents learn new languages from usage alone, take an active role in this learning, and that while stronger models are required for novel language emergence, weaker models can learn an existing language once it has emerged. Taken together, our results indicate that current LLMs have the potential for cumulative cultural evolution -- previously attested only in humans -- with mixed populations of agents developing capacities that go beyond their lowest common denominator.

Dexterous manipulation policies learned by imitation are typically evaluated for robustness to variation in scenes, objects, or instructions, but their performance across task execution speeds is less often examined. This leaves open how much temporal robustness a learner retains relative to the expert it imitates. We compare an expert and learner under the same task conditions, initial-condition draws, and speedup factors. We instantiate the evaluation in ParcelStow, a contact-rich task in which the robot acquires, reorients, and inserts a parcel. The demonstrations span the speedup range for the manipulation phases after parcel acquisition. A scripted expert and an Action Chunking with Transformers (ACT) policy trained from the expert's demonstrations both achieve 100 percent task success at nominal speed. Their success rates diverge within the demonstrated range: at its maximum, expert success is 84 percent and ACT success is 53 percent. Two ACT policies with different parameter initializations show similar degradation, decreasing by 34 and 48 percentage points from nominal speed to the maximum demonstrated speed, compared with 16 points for the expert. Stage-level analysis shows that 35 of ACT's 47 failures at the maximum demonstrated speed are insertion misalignments. Under the relative-motion handoff, every ACT acquisition retains the parcel through reorientation and transfer in free space, but only 64 percent complete the overall task, compared with 95 percent after expert acquisition. Across all evaluated policies and speeds, none of the 414 acquisitions without force closure completes the task. Equal nominal task success therefore does not imply preservation of expert performance across execution speeds. Code, data, and evaluation scripts are available at https://github.com/coenwerem/parcelstow.

Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM directly into a drone's control loop, with its entire action space declared solely in the prompt. Recent systems approach this setting but increasingly narrow the model's decision-making. We widen it back. We introduce DroneCATS-Agent, an architecture where the MLLM is a swappable component, and DroneCATS, a benchmark treating the model as the independent variable. Beyond merely flying toward a pixel, our agent entrusts the model to yaw and search, deliberate when unsure, and self-declare arrival---all without fine-tuning or function-calling schemas. Evaluating frontier and open models across four core capabilities---approaching a visible target, tracking a moving one, searching outside the initial view, and commanding a multi-drone fleet---reveals that even the simplest embodied settings are far from solved. Crucially, to identify what breaks first at the edge, our roster scales down to 2B parameters. The findings expose a stark paradox: it is not the flying that fails. Small open models often navigate into the success radius more reliably than frontier models, yet lose the episode by declaring arrival prematurely or not at all. Multi-drone commanding amplifies this divide, with small models failing by blindly copying a single coordinate across distinct views. Viewed as vision-language-action agents, the models' spatial perception holds up, but their action protocol does not. What separates a deployable edge model from a frontier model is not navigation, but the discipline to sustain a declared protocol and emit the correct terminating action. The open problem is closing this gap at onboard compute costs---yielding a fast model that plans persistently and knows exactly when it is done---and DroneCATS is built to measure that distance.

Vision-language-action (VLA) models map visual observations and language instructions directly to robot actions, but long-horizon tasks require more than action prediction. An agent must coordinate perception, planning, execution, progress verification, and recovery as the physical state evolves. An action prediction or a model-generated skill decision does not, by itself, guarantee that the proposed operation is valid in the current state or that its outcome will be verified. We propose EmbodiedSkills, a unified framework that treats each skill decision as an execution proposal: the runtime checks its prerequisites before execution and verifies the outcome afterward. A shared executable-skill interface connects high-level skill selection, bounded low-level VLA execution, and post-action verification within a single agent loop. Because this interface remains fixed, low-level VLA policies can be replaced or adapted without changing the agent loop. The interface also records planning, execution, verification, and recovery events as structured trajectories, which provide supervision for individual components and can support optional online adaptation when interactive feedback is available. We instantiate EmbodiedSkills with Qwen3-VL and OpenPI/pi0.5 on RoboTwin 2.0 and LIBERO. Task-adapted low-level VLA policies achieve an average success rate of 86.20% across 50 RoboTwin 2.0 tasks and 97.40% across the four LIBERO suites. These results establish the execution performance of the task-adapted low-level VLA policies used in EmbodiedSkills. On four memory-dependent RMBench tasks, the same task-adapted execution approach achieves 12.5% average success. The framework provides a trainable and inspectable agent layer for turning these policies into closed-loop embodied systems.

Robotic systems are deeply embedded in both industry and everyday life, where they are expected to act with speed, precision, and reliability. Classical control and planning methods have long delivered strong guarantees, but often at the cost of computational efficiency and adaptability. More recently, learning-based approaches have shown promise in overcoming these limitations, enabling agents to leverage experience to accelerate decision-making and address previously intractable problems. In this work, we bridge these two approaches through a neuro-symbolic perspective on nonlinear motion planning. Inspired by the Thinking Fast and Slow paradigm, we introduce a dual-process architecture that combines the strengths of robust reasoning and learning. Our framework integrates state-of-the-art symbolic solvers as a ``System-2'' component with experience-driven ``System-1'' modules. A metacognitive controller dynamically orchestrates their interaction, selecting when to rely on fast intuition versus slower, more precise reasoning. By evaluating the framework across diverse nonlinear benchmark environments, we demonstrate that this architecture yields consistent gains in planning efficiency, accuracy, and generalization, while promoting reuse across tasks. The results suggest that tightly coupling learning with structured reasoning offers a scalable path toward more capable and adaptive robotic systems.

Open photonic systems provide a versatile platform for non-Hermitian physics, enabling control over complex spectra, transport, and light-matter interactions. Exceptional points (EPs), at which eigenvalues and eigenvectors coalesce and the governing operator becomes defective, play a central role because they combine branch-point spectral topology, nonanalytic perturbative response, and controllable eigenstate conversion. This Review provides a unified framework for EP photonics by systematically distinguishing exceptional degeneracies according to the underlying operator, spectral variable, boundary conditions, and experimentally accessible observables. We discuss Hamiltonian EPs, absorbing EPs associated with scattering zeros, real-frequency scattering-matrix and Jones-matrix EPs, Bloch and Floquet EPs, and Liouvillian EPs in open quantum systems. We review their spectral topology, static and dynamical encircling, higher-order exceptional structures, and coexistence with bound states in the continuum, together with applications in sensing, lasing, coherent absorption, directional scattering, polarization and wavefront control, nonlinear optics, optical storage, nonreciprocal photonics, and quantum photonics. We also critically assess the current limitations, practical challenges, and future perspectives of EP-based photonic technologies, with particular attention to robustness, noise, scalability, and experimentally measurable performance.

Most vision-language-action (VLA) models -- OpenVLA, $π_0$, RT-2, RDT-1B -- are monolithic: they emit raw motor commands or short action chunks without organizing behavior into reusable abstractions, so they degrade on long-horizon tasks and resist interpretation. Existing skill-discovery methods sidestep the core question of when two action sequences are behaviorally equivalent, either clustering contrastive embeddings or delegating the judgment to a language model uncalibrated to the robot's dynamics. We introduce REFACTOR-VLA, a wake/sleep system for learning reusable skills. Its sleep phase clusters motor-program fragments under a Behavioral-Equivalence Kernel (BEK) computed from rollouts of a learned latent world model $M_φ$; its wake phase emits typed lambda terms over a Hindley--Milner-inspired vocabulary, consumed by a library-conditioned rectified-flow action decoder. Abstractions are admitted only if they pass Minimum Description Length and return-preservation gates. On LIBERO we report two findings. First, enlarging the world model from 188M to 430M parameters worsened performance on 4 of 4 suites, so capacity alone does not help. Second, the training objective matters far more: adding an auxiliary supervised contrastive (InfoNCE) loss during world-model warmup substantially improves sleep-phase clustering, giving Normalized Mutual Information at $n=3$ seeds of $0.462 \pm 0.021$ (object), $0.867 \pm 0.025$ (spatial), $0.915 \pm 0.013$ (goal) and $0.754 \pm 0.010$ (LIBERO-10), and beating the strongest published baseline on all 4 suites by a mean $Δ= +0.184$. Across providers ($n=12$) the 95% bootstrap confidence interval for mean pairwise NMI is $[0.683, 0.729]$ (mean $0.705$). The sleep phase also yields the first real-LIBERO task-language library: the decoder uses 2 of 3 admitted abstractions and rewrites all 256 sampled demonstrations.

This paper studies a class of uncertain multi-input multi-output (MIMO) nonlinear systems using extended PID (EPID) control. We focus on systems possessing a well-defined vector relative degree whose components may vary across channels, a setting that received limited attention in the existing literature on PID-type control. We develop a channel-wise EPID controller, where each control input is constructed from the proportional, integral, and derivative terms of the corresponding tracking error, and the highest derivative order is selected according to the relative degree of that channel. Under suitable growth conditions on the unknown nonlinearities, we construct an admissible set of EPID parameters specified by prescribed initial-state bounds, the uncertainties and the reference signal. We show that any parameter choice from this set guarantees semiglobal stability of the closed-loop system and achieves the desired setpoint regulation. These results indicate that the EPID parameters can be designed independently for each channel, justifying the common engineering practice of channel-by-channel tuning in strongly coupled and uncertain MIMO systems, including flight control systems.

Electro-optic frequency conversion and synthetic-frequency coupling are established functions in integrated photonic devices. Their role within a multiport switching fabric, however, depends on how simultaneous optical connections share spatial paths, frequency channels, and device controls. Here, we investigate how coherent coupling among frequency modes can be incorporated into photonic switching fabrics and identify the corresponding architectural and physical constraints. We show that synthetic-frequency coupling does not increase the number of simultaneous orthogonal frequency channels when all channels are freely accessible, but can establish connections that are otherwise blocked by fixed input frequencies, channel-continuity requirements, or unavailable output channels. Under the tested conditions, coupling over the first three frequency spacings in an $8\times8$ fabric with eight frequency channels per port achieves 96.1% of the blocking reduction obtained with unrestricted inter-mode coupling. We further show that a separate frequency-only conversion stage cannot replace missing spatial connectivity. A nominal reduction in spatial switching elements instead requires a joint element whose spatial state can be programmed independently for each frequency channel. Finally, we evaluate a thin-film lithium niobate resonator model using reported electro-optic coupling and photon-decay scales within a multistage Mach-Zehnder interferometer switching fabric. These results clarify the architectural role of synthetic-frequency coupling and the device-level requirements for incorporating it into integrated photonic switching fabrics.

In an edge--cloud collaborative edge-computing environment, an edge node (EN) must decide whether each user task should be executed locally, forwarded to a remote service (or cloud) node (SN), or rejected. The EN observes its local state directly but receives the SN state only through an intermittently refreshed cache. Status updating and task control therefore form an asynchronous closed loop under partial observability. Freshness-driven schemes, including those based on Age of Information (AoI), do not directly value an update by its effect on subsequent task decisions. We propose CoSMO (Co-design of Semantic-state Management and Offloading), a cooperative event-driven reinforcement learning (RL) framework that coordinates semantic status management and selective offloading through realized task utility. CoSMO learns a compact representation of the heterogeneous SN service state. At the SN, a recurrent semi-Markov double deep Q-network (Double DQN) agent jointly selects send/no-send and the next decision interval. At the EN, a task-terminal off-policy value-learning agent makes hierarchical gate--route decisions from local observations and stale remote semantics. The agents maintain separate observations and value targets but share the same realized task-utility stream, without centralized execution. Across the evaluated workload families, CoSMO's reported relative improvement in on-time completion rate over the best-performing competing method averages 18.6%--21.2%. For capacity-aware decision accuracy across the three strict-overload points, the corresponding reported gains average 17.6%--$17.9%.

Executing long-term tasks in dynamic environments requires embodied agents to maintain robust and adaptive 3D scene representations. However, most existing 3D memory frameworks rely on static world assumptions. When objects are displaced by human activities or unobserved events, agents encounter memory-observation conflicts and often require costly geometric recomputations or inefficient global re-exploration. To address this, we propose HitMem, a hierarchical temporal 3D memory framework with a multi-modal context-aware retrieval mechanism. Through continuous perception, HitMem unifies semantic and spatial information into a lightweight topological graph that captures support relationships, while a temporal decay mechanism dynamically regulates memory activeness to mitigate the impact of stale representations. In addition, the multi-modal context-aware retrieval mechanism defaults to filtering candidates using integrated semantic, spatial, and temporal memory features, and activates a specialized two-stage retrieval process when object displacement is detected. This process combines spatial constraints inferred from external agent trajectories with semantic common sense grounded in class affinities, efficiently identifying high-probability candidate regions. Extensive evaluations on our constructed Dyna-THOR benchmark demonstrate that HitMem significantly improves object relocation accuracy, reduces exploration costs, and enhances task execution performance in dynamic environments.

Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-language instructions. Explicit reasoning can improve instruction understanding and semantic grounding, but autoregressive generation at every step accumulates large decision-stage latency over multi-step navigation. We propose VerNav, a verifier-first framework for low-latency LLM-based VLN. The verifier reduces decision-stage latency by replacing per-step autoregressive generation with batched action verification, while an entropy-based adaptive generator is invoked only for uncertain decisions to produce compact state evidence. To further improve navigation performance with the verifier, we introduce a two-stage alignment scheme: (i) VPO improves local action-preference alignment in static verifier training, and (ii) step-level reinforcement fine-tuning provides dense progress rewards over multi-step navigation rollouts during dynamic task execution. Experiments on the Room-to-Room (R2R) benchmark show that the verifier-only decision path of VerNav achieves competitive navigation performance among representative LLM-based VLN agents while reducing average decision-stage LLM latency per step by more than $10\times$ compared with autoregressive methods.

Action chunking is a standard execution strategy in modern Vision-Language-Action (VLA) frameworks, but fixed execution horizons impose a trade-off between efficiency and accuracy. Short chunks require frequent inference and may cause oscillatory behavior, whereas long chunks can become misaligned with newly observed states. We address this limitation with an adaptive action chunking approach based on internal cross-attention dynamics in the action expert. We observe that, as the prediction horizon extends, action-to-observation cross-attention becomes increasingly dispersed and its entropy rises toward a plateau. This pattern is associated with higher action prediction error and provides an online signal that the current observation offers limited grounding for further open-loop execution. Based on this observation, we introduce a training-free truncation mechanism that detects sustained high-entropy plateaus and dynamically selects the execution horizon during inference. The method uses attention weights already computed by the policy and introduces negligible additional overhead. Evaluations on $π_{0.5}$ and X-VLA across RoboTwin 2.0, LIBERO, and three real-world manipulation tasks show improved average task success over fixed-horizon and adaptive chunking baselines, while preserving efficient closed-loop control. These results show that cross-attention dynamics can provide a practical internal signal for adaptive action execution in VLAs.

High-precision insertion remains a fundamental challenge in robotic manipulation due to the strict alignment requirements and contact-rich interactions involved. Although peg-in-hole tasks are widely used for evaluation, existing bench- marks often rely on fixed task configurations, limiting their ability to assess robustness and generalization across different insertion scenarios. This paper introduces a reconfigurable peg-in-hole benchmark designed to evaluate task generalization in high-precision insertion. The benchmark consists of a set of fully 3D-printable modular components, including multiple peg geometries, tolerance levels, and configurable base structures that can be combined to generate a large variety of insertion and assembly tasks. By varying object layouts, orientations, and task structures while maintaining controlled physical conditions, the benchmark enables systematic evaluation of adaptation to unseen scenarios. To support reproducibility, we additionally provide a scenario generation tool capable of producing standardized task configurations and machine-readable task descriptions. The scenario generation tool and the STL files of the benchmark pieces are available through the project repository: https://github.com/aistairc/peg-in-bench.

Robotic throwing enables fast object transport and extends a robot's reachable workspace beyond traditional pick-and-place. While prehensile (grasp-based) throwing works well for graspable items, non-prehensile (grasp-free) throwing is better suited for large, heavy, and/or deformable objects. Existing approaches rely on model-based optimization with simplified contact models (e.g., dynamic grasping) and low-dimensional trajectory parameterizations, which limit solution quality and reachable workspace. We propose a reinforcement learning approach that additionally leverages sliding and rolling contact modes and directly optimizes joint-space trajectories without analytical contact models or custom parameterizations. The Markov Decision Process (MDP) is formulated as a dynamical system that evolves the robot's joint state conditioned on the throwing target, object model, and initial configuration. Joint-jerk trajectories are planned offline at a low control rate and upsampled into smooth, high-rate velocity commands for deployment. For sim-to-real transfer, we minimize the robot-dynamics gap through minimum-jerk system identification and train uncertainty-aware policies to mitigate object-modeling errors, particularly sensitivity to dynamic friction. In simulation, the policy achieves 99% success across thousands of configurations and generalizes to unseen objects. Sensitivity analysis shows robustness to mass uncertainty but high sensitivity to dynamic friction, consistent with the sliding-based release mechanism. Deployed zero-shot on a UR5e operating near its physical limits (5 m/s end-effector velocity), our method throws diverse objects including heavy (790 g) and large (20x20x28 cm) items to targets up to 350 cm distance or 180 cm elevation, achieving a 97% real-world success rate.

This letter presents a compact two-degree-of-freedom (DoF) robotic finger with a flexion-selective passive continuously variable transmission (CVT) to achieve a wide force-speed operating range. Inspired by the functional differentiation of the human metacarpophalangeal (MCP) joint, the proposed mechanism realizes DoF-specific transmission differentiation by selectively assigning passive CVT to the flexion-extension DoF while preserving direct transmission for abduction-adduction. For a wide force-speed operating range, a force-responsive passive CVT is embedded in the flexion pathway, while direct transmission is preserved for the abduction-adduction pathway. To selectively realize transmission adaptation within a multi-DoF MCP mechanism, an output-side passive CVT employing a moving-pulley-inspired wire-routing structure is introduced. The resultant force generated by the wire tensions acting on the pulley that passively increases the flexion moment arm and transmission ratio according to the applied load without additional actuators, sensors, or control. Experimental results demonstrate a maximum output-force amplification of 4.19-fold and a mean amplification of 3.6-fold across the tested flexion angles ranging from 15 degrees to 75 degrees through moment-arm adaptation, thereby substantially expanding the achievable force-speed operating range. Furthermore, dexterous ball-rolling experiments verify that passive transmission adaptation can be achieved while preserving abduction-adduction functionality. These results demonstrate a scalable transmission design strategy for compact multi-DoF robotic hands.

Conventional soft robot actuators excel in compliance, but their uncontrolled deformations compromise accuracy and hinder scaling to multi-degree-of-freedom (DoF) systems. We introduce a MONOlithic ORIGAMI-inspired soft folding actuator design (MONORIGAMI) that establishes a design strategy based on spatially programmed stiffness anisotropy to preserve material compliance along desired folding directions while selectively restricting deformation in unwanted directions. The actuator leverages stiffness tiers based on material thickness, patterned in an origami-inspired geometry with facets and creases, converting unconstrained soft deformation into accurate, repeatable, and composable folding motions without additional reinforcements. The design is fully 3D-printable through a single-material, single-print process that requires no assembly. Each actuator serves as a scalable motion primitive, and linking and orienting multiple actuators mechanically programs multi-DoF trajectories. Using the same fundamental module, we demonstrate three 3D-printed soft multi-DoF robotic systems spanning distinct application domains: (1) a compact 4-DoF wearable haptic device for high-fidelity cutaneous feedback in virtual reality (VR), (2) a 3-DoF joystick for kinesthetic feedback in teleoperation, and (3) a modular robotic gripper capable of underwater operation with geometry-encoded grasp trajectories. These systems demonstrate the module's capabilities for compact multi-axis integration, controlled physical interaction, and geometry-programmed operation across different environments. Together, these results show that MONORIGAMI provides a general, composable, accessible, reliable, and scalable platform for high-precision soft multi-DoF robotics, addressing long-standing limitations in both soft actuator design and fabrication.

Large language model (LLM)-based multi-agent systems (MAS) have shown strong potential for solving complex tasks, yet their development forces a tradeoff: code frameworks are expressive but engineering-intensive, while no-code builders simplify authoring but constrain agent interactions to author-defined workflows. We present ChatDev 2.0: DevAll (hereafter DevAll), a no-code platform for building, executing, and inspecting heterogeneous MAS that delivers both high expressiveness and ease of use. In terms of expressiveness, DevAll pairs a declarative executable graph abstraction with a cycle-aware execution engine, so that heterogeneous agents and dynamic and cyclic interactions can be represented and executed within a single framework. For ease of use, an integrated visual interface lets users author, run, monitor, and inspect MAS, including human-in-the-loop steps, entirely without writing code. Experiments demonstrate that DevAll reproduces state-of-the-art MAS across three representative tasks at competitive performance and without task-specific orchestration code, highlighting its effectiveness as a general-purpose platform for LLM-based MAS. DevAll is available at https://github.com/OpenBMB/ChatDev.

We address a structural tradeoff in distributed dynamic coordination: when the target complexity is unknown, a low controller order saves states but may leave a persistent tracking error, whereas a high order improves tracking but may burden every agent with unnecessary dynamics. To remove this choice without resorting to computationally more involved nonlinear feedback or chattering-prone nonsmooth feedback, we develop an order-adaptive distributed integral controller (OADIC). Specifically, we start with proportional feedback and add integral states only when locally measurable relative errors show that the current order is inadequate. Meanwhile, we organize the candidate controllers in a nested form, thereby preserving the existing states and gains and maintaining continuous control inputs during order transitions. To provide a theoretical basis for this design, we first characterize the consistency of prescribed relative displacements on the augmented agent--target graph. Next, we construct gains that stabilize all admissible fixed-order subsystems and establish a uniform input-to-state stability bound for the variable-dimension closed loop. Furthermore, we prove that OADIC rejects every insufficient order after finitely many decision intervals and explicitly bound the rejection time of the critical order.

We present ADAPT, an end-to-end framework for interactive, text-conditioned humanoid whole-body control. Unlike dominant text-to-motion pipelines that generate kinematic motions for a separate tracker, ADAPT solves language control with an end-to-end closed-loop control framework, where the robot must continuously respond to changing commands while maintaining balance, natural motion, and smooth transitions. ADAPT learns a diffusion-based action prior from text-labeled humanoid state-action trajectories, enabling diverse motion skills to be directly executed from language commands. To improve long-horizon robustness and smooth prompt switching, we train a lightweight residual reinforcement learning policy on top of the frozen diffusion controller. We further show that the same diffusion policy can be reused as a steerable text-conditioned motion prior for downstream task adaptation. Experiments demonstrate robust language-grounded skill execution, smooth interactive transitions, and style-preserving downstream control.

Physical human--robot interaction software often couples desired-behavior specification with constrained realization; we treat these as separate layers. A \emph{behavior layer} supplies a desired contact-port acceleration $a_k^{\mathrm{id}}=f_θ(e_k,\dot e_k,F_{h,k})$. A \emph{realization layer} converts it into constrained robot commands and reports total desired-versus-realized acceleration error instead of hiding it in saturation. A same-objective unconstrained counterfactual separates regularization from constraint intervention, while plant data expose model error. This paper implements a receding-horizon quadratic program realizing memoryless affine behaviors. Changing the behavior modifies objective coefficients through $(C_θ,G_θ)$ while the robot-command variable and feasible set remain unchanged. A planar study instantiates impedance and admittance; the same running layer accepts an impedance--admittance--impedance reassignment without reconstruction, under its existing rate limit. On a torque-controlled 7-DOF Franka FR3 in MuJoCo, the runtime freezes task-space dynamics per solve and enforces torque feasibility across its horizon. Under a sustained 20~N push, it holds a slack-relaxed workspace boundary to within approximately 0.1--0.2~mm, versus 4.4~cm (impedance) and 4.7~cm (admittance) overshoot from instantaneous clipping. A derated actuator budget then activates the torque constraint: horizon-wide enforcement keeps its frozen-model plan feasible to $2.1\times10^{-4}$~N$\cdot$m, whereas a first-step-only ablation plans up to 11.329~N$\cdot$m beyond budget; on the executed nonlinear plant, where both share the same local-model error, the gap is smaller but still favors horizon-wide enforcement (0.161 vs.\ 0.380~N$\cdot$m). These results are a focused proof of behavior--realization separation.

Standardized benchmarks have played a central role in advancing robot manipulation learning, yet most focus on ground-supported manipulation systems, which limits their applicability to dynamics-critical domains such as aerial manipulation (AM). AM presents distinct system-level challenges, including environmental disturbances, coupled dynamics between the manipulator and floating base, and constrained degrees of freedom. Consequently, task performance depends jointly on robot embodiment, low-level control, and high-level policy design. We introduce AM-Bench, a modular simulation suite and benchmark for multirotor-based AM policy learning. AM-Bench includes representative embodiments spanning underactuated, fully actuated, and overactuated systems, 12 tasks across contact, transport, and constrained interaction, configurable aerodynamic disturbances and actuator saturation, standard low-level controllers, and baseline policy-learning algorithms. Unlike prior manipulation benchmarks that primarily emphasize end-to-end policy performance, AM-Bench enables system-level evaluation of how embodiment, control, disturbances, and policy choices interact. We demonstrate its diagnostic value through three simulation studies spanning high-level policies, policy--control interfaces, and embodiments, together with real-world validation of modeled effects and a hardware test of the learning pipeline.

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant content is usually expressed in unstructured language. Based on this, we propose control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication. This design allows optimizers to improve multi-agent behavior without exposing the routing or formatting interface to prompt drift. Across synthetic reasoning, collaborative review generation, and insurance rating workflows, our framework empirically achieves 100% eventual protocol validity while consistently improving task performance.

In indoor environments, object positions frequently change due to human activities or embodied-agent interactions, causing previously constructed scene graphs to become inconsistent with the current scene. To address this issue, we propose DSG, a dynamic 3D scene graph construction framework that detects object changes and performs spatial relationship reasoning. First, we construct a semantic-aware 3D Gaussian scene representation and develop a dual-view rendering-based object change detection method to enable reliable scene graph node updates. Second, we propose a spatial relationship reasoning method that incorporates multi-granularity visual context, enabling a large language model to identify a richer set of interobject spatial relationships. Furthermore, we introduce DynTHOR, a dynamic indoor scene graph benchmark built on the AI2-THOR simulation platform for evaluating scene graph construction in dynamic environments. Extensive experiments on Dyn-THOR, 3RScan, and real-world scenes demonstrate that DSG consistently outperforms existing methods in both object node construction and spatial relationship reasoning, significantly improving the accuracy of dynamic scene graph construction.

We present a system of two wearable pneumatic haptic devices that supports continuous, closed-loop, bidirectional tactile interaction at perceptually relevant force and temporal scales. A single device can contain up to twelve pressure sensing channels connected to textile-based pneumatic pouches. Each channel in a device can be used as a sensor, an actuator, or both. As an actuator with integrated sensing, the channel generates stable skin indentation through local closed-loop control. As a sensor, a channel can be mounted (or worn) on any surface, including on a robot gripper or on the human body, and used to measure touch interactions with the environment or a human user. A distributed architecture supports sustained pressure output, rapid dynamic response, and wireless pairing of identical devices in a system to transmit and reproduce tactile pressure signals in real time. Device-level characterization demonstrates force bandwidth exceeding 30 Hz, rapid and well-damped step responses, and extended pressure retention compared to prior compact pneumatic platforms. Human studies show that pressure-based fingertip feedback enables discrimination of force and stiffness, improves teleoperated manipulation by reducing applied pressures by up to 23.1% and task duration by up to 27.4%, and lowers subjective mental workload by 18.8%, particularly under visually constrained conditions. By unifying tactile sensing and haptic feedback within a single pneumatic modality, the device provides a practical foundation for bidirectional touch interaction in teleoperation.

Language-driven dexterous grasp models, such as DextER, perform well when instructions specify where to grasp, but we find they fail systematically when an instruction also specifies where not to grasp (e.g., "grasp the handle but avoid the body"). Existing training corpora, DexGYSNet among them, contain virtually no avoidance instructions, and collecting examples for every possible constraint is impractical. Moreover, because every part mentioned during training denotes a contact target, models may interpret a forbidden part as another region to grasp rather than one to avoid. We therefore introduce an inference-time framework for negation-constrained dexterous grasping that requires no negation-specific training examples. Combining Sequential Monte Carlo with classifier-free guidance, our method guides sampling toward the instructed part while pruning candidates headed for the forbidden region, without any negation examples during training. A frozen 3D part-grounding model localizes the forbidden region from the language instruction. To evaluate this setting, we construct NegGrasp, a benchmark of paired positive/negative instructions with constraint-aware metrics that credit a grasp only if it both accomplishes the task and respects the stated constraint. On NegGrasp, our method reduces the violation rate of the strongest baseline from 57.9% to 17.2% while improving both constraint-aware and physical success.

Animals' body morphology shapes the gait patterns they can perform, where mechanical resonance reduces the need for active control. By tuning posture and muscle stiffness, they leverage their embodied intelligence to achieve effective gaits for different speeds. In contrast, most quadruped robots are not specifically designed to exploit mechanical resonance due to the complexity of nonlinear dynamics and require dedicated locomotion controllers. To provide an alternative, we present a proof of concept framework making the nonlinear dynamics of a robot predictable in the design process and show how this knowledge can be leveraged such that multi-gait locomotion can emerge from nonlinear resonances, shaped by gravity, inertia, and elasticity. We present the highly compliant quadruped robot eBert, on which we identify six nonlinear normal modes (NNMs) using our new theoretical tools and validate their existence in simulation and hardware. With black-box optimization to determine step length, simulations show how each NNM naturally develops into a distinct gait, manifesting different speeds, which also largely transfers to the robotic hardware. Our experiments show that eBert can exploit its mechanics to generate task-specific movements which may serve as foundation for designing a new generation of agile and efficient robots leveraging embodied intelligence.

In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming ``$\mathsf{ETH}$ for $\mathsf{PPAD}$", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first \emph{radically uncoupled} algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a \emph{layered} variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.

Gaze-based assistive manipulation typically supports object selection, while arbitrary-position placement requires accurate spatial alignment between the headset and robot. However, for gaze-based manipulation, pose accuracy does not necessarily translate into task accuracy: translational and rotational errors jointly affect the transformed gaze ray and may compensate for each other. To study cross-device alignment from this task-oriented perspective, we present a markerless interaction framework and a dedicated cross-device dataset. We propose Graph-based Reference Selection to address sparse robot references. We further develop and benchmark multiple task-specific alignment pipelines under a unified protocol. Specifically, we introduce Gaze--Surface Intersection Error (GSIE), which directly measures the spatial error of the gaze-specified target. Experiments show that alignment methods ranked highly by conventional pose metrics are not always optimal in GSIE, demonstrating the importance of evaluating gaze-based manipulation at the task level.

For embodied systems, predictive agreement alone does not determine whether evidence warrants action; evidential origin matters. Repeated inference over one observation can multiply agreement without adding evidence, while source-local values do not reveal whether outputs have separately countable origins. PACT treats evidence countability as a relational variable for provenance-conserving fusion and typed action admission. A supplied provenance partition defines countable units. PACT retains coordinatewise support shared within each unit, accumulates only across units, and maps unmet release conditions to hold, confirm, or fallback. Under the stated assumptions, source-local values cannot identify countability; the coordinatewise meet is the greatest budget satisfying singleton fidelity and insertion non-amplification, with coarsening monotonicity and fixed-partition stability. Across 31,200 evaluations in 48 scene clusters, PACT attains a common-support normalized risk-coverage area (ncsAURC) of 0.0861. Excluding the constructed adversarial-consensus arm, provenance-partition aggregation reduces ncsAURC by 0.0557 relative to singleton aggregation, while the corroboration contrast vanishes. On complete-source records, native scores favor PACT, but a common posterior-peak score narrows its difference from nested Dirichlet and favors product fusion. Reassigning provenance over unchanged predictions moves evidence budgets as predicted. In offline human-robot collaboration, eightfold within-camera duplication leaves 720 typed responses per checkpoint unchanged; camera-grouped PACT admits 47 of 57 Qwen3-VL-32B reference-consistent candidates with no observed reference-inconsistent admission in 60 episodes. PACT separates computational from evidential multiplicity: agreement constitutes corroboration only when provenance permits separate accumulation.

Open synthetic test systems are essential for reproducible power system research, yet the available cases represent almost exclusively North American and European grids. No open transmission test system exists for any Middle Eastern country, whose grids raise different questions such as single corridor fuel-supply resilience and high-renewable operation within small synchronous systems, and established benchmarks cannot demonstrate. This paper presents a synthetic test system for the Jordanian transmission grid, assembled entirely from public sources, where the real topology is reconstructed from a published diagram and restored to its 2018 energized state, with plant-level generation and renewable fleets, per-site hourly profiles, and loads calibrated to the values published by Jordan's grid operators. The case is validated through structural statistics against real-grid criteria, power flow and $N\!-\!1$ screening, an energy-weighted loss decomposition, in addition to a full-year production-cost run compared against the published per-plant energy, and cross-solver verification. The model reproduces the annual energy mix at technology level (largest producers within 4\%, system total within 0.1\%), and the released dataset includes the bus-identity key, all scripts, and a post-2019 scenario variant. This test case is designed to benchmark system-level resource adequacy, time-series dispatch and unit commitment, renewable integration, fuel-supply resilience scenarios, interconnection studies and steady-state studies.

Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through tool use, interpretation of intermediate results, and iterative planning. Diagnosing and resolving non-convergent power flow cases is a promising yet largely unexplored application, as it requires engineering judgment, experimentation, and decision-making within constrained action spaces. We introduce a benchmark that evaluates these capabilities across multiple LLMs and three architectures: \emph{chatbot}, \emph{single agent}, and \emph{multi-agent} systems. The evaluation covers two power grids and 46 cases per grid, each requiring one or more corrective actions to restore convergence. The benchmark defines the simulation environment, observation and action spaces, and evaluation metrics, providing a reproducible foundation for developing agentic AI systems for power system planning and operation. The code is available at https://github.com/Mansutti081/RestoreBench

Extracting scenarios from unlabelled real-world sensor data streams is a critical but challenging task in the development process of automated driving systems (ADS). Automatically sifting through large datasets to spatially and temporally locate critical scenarios can enable scenario-based coverage analysis of ADS datasets. In this paper, we present a method for extracting scenarios from egocentric datasets using scene graphs and Linear Temporal Logic (LTL). We first process egocentric sensor data and HD maps to generate a sequence of scene graphs representing a driving scenario. Next, we use LTL to formally specify driving scenarios of interest, then extract all instances of the scenarios from the dataset using an off-the-shelf model checker, which evaluates the LTL formula against the sequence of scene graphs. Our approach can be used on both simulated and real world datasets. We evaluate the method on the training and validation datasets from Argoverse 2 consisting of 850 15-second real-world driving logs, and several videos of dashcam footage. We demonstrate the effectiveness of our approach for extracting and querying scenarios by evaluating against a rule-based benchmark based on track annotations and HD maps.

Ultra high field REBCO magnets operate under strongly coupled electromagnetic, thermal and mechanical conditions, where screening currents, localized heating, thermal expansion and Lorentz forces can modify both the structural state and the critical current density of the conductor. In this work, a coupled electromagnetic, thermal and mechanical model is developed for a metal-insulated nested REBCO insert designed for a 40 T class SuperEMFL magnet. The existing electromagnetic formulation resolves the non-uniform screening currents in the REBCO tapes. The thermal model is extended from an explicit Finite Difference Method (FDM) to an implicit Backward Euler scheme with Picard iteration, while a new axisymmetric mechanical FDM solver based on BiCGSTAB is introduced to calculate displacements, strains and stresses in the coil windings and G10 spacer regions. Thermal expansion and Lorentz force contributions are included, and the calculated longitudinal mechanical strain is coupled back to the electromagnetic model through a strain dependent critical current density, which also depends on temperature, magnetic field, and its orientation. A literature-informed Parabolic-Weibull model is used to model reversible and irreversible strain degradation of the REBCO conductor. The numerical methods are benchmarked, and the resulting framework provides a computationally efficient approach for investigating temperature gradients, thermo-mechanical stresses, strain-dependent critical current degradation and quench behaviour in full scale nested high field REBCO magnets.

Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical question is not only whether a model recognizes an unusual object, but whether it infers how that object changes the ego vehicle's feasible high-level actions. We formalize this problem as decision-level driving affordance prediction, where a model maps a front-view image, ego-motion history, and navigation command to a structured longitudinal--lateral meta-action. To evaluate this capability, we introduce CoLT-Drive, a 3,536-sample counterfactual long-tail benchmark that inserts rare objects into otherwise fixed driving scenes and measures whether models predict acceptable action pairs. To improve deployable small VLMs, we propose KPA, a knowledge-preserving adaptation framework that combines structured perception-to-decision prompting, SLERP-based expert merging, and RegMoE, a regime-aware LoRA mixture-of-experts module. KPA preserves the pretrained model's open-world knowledge while allocating lightweight adaptation capacity to different driving decision regimes. Experiments on an in-domain driving split and CoLT-Drive show that KPA achieves 60.8\% pair accuracy on CoLT-Drive, outperforming the pretrained Qwen3-VL-2B baseline (50.3\%) and LoRA SFT (32.4\%) while maintaining competitive in-domain accuracy. Our benchmark and code are available at https://huggingface.co/datasets/tangzx2024/CoLT-Drive and https://github.com/tangzhengxu/CoLT-Drive.

Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before producing an answer. In autonomous driving, the answer is a continuous action. Thus its reasoning must share the same spatiotemporal structure as the physical world. This survey studies the resulting shift from textual CoT to action-grounded reasoning. Surveying 171 papers, including 130 method papers and 41 benchmarks, datasets, surveys, and analysis papers, we propose a representation-centered taxonomy that treats the form of the intermediate state as the organizing axis. We systematize the 130 methods into four categories: language-based, visual-spatial, latent-dynamic, and externalized reasoning, further divided into 13 subtypes tied to distinct regions of interests. Our synthesis shows that the open frontier of reasoning in driving agents lies in intermediate representations that can be grounded in the real world, coupled to real-time action, and verified under safety-critical systems. Project page: https://github.com/tangzhengxu/awesome-av-cot.

World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausible interactions. Existing approaches address this limitation by constraining the generation process with external representations encoding motion, geometry, or semantics. Obtaining these spatiotemporally dense representations typically requires auxiliary estimators or manual annotations, limiting training scalability. We instead revisit the training objective and identify a supervision-allocation mismatch under the globally averaged mean squared error (MSE) denoising objective: prevalent static content dominates the optimization signal, leaving sparse dynamic-object regions critical to interaction generation disproportionately under-supervised. Motivated by this observation, we introduce IMPACT, a scalable Interaction-aware Model training framework with Prior-guided Attention Calibration and Targeting. IMPACT uses cross-attention associated with manipulated-object tokens as an internal spatiotemporal prior for action-conditioned changes. It samples candidate regions from this prior, calibrates them with detached local prediction errors to construct an interaction map, and uses the map to reweight denoising supervision, requiring neither external representations nor inference-time modifications. Extensive experiments on robot-arm and human-hand manipulation, spanning diverse control modalities and DiT backbones, show that IMPACT consistently outperforms the corresponding MSE-trained baselines, improving interaction fidelity, physical plausibility, and visual quality.

We develop a general dressed-state framework for computing fluorescence spectra, probe absorption spectra, and photon-photon correlations of light scattered by ensembles of $N_\mathrm{at}$ two-level atoms with arbitrary $J_g \to J_e$ transitions driven by intense coherent fields. The approach employs a full vectorial treatment of the electromagnetic field, handles any atomic geometries, illumination directions, and polarizations, and yields optical observables as explicit sums of Lorentzian lines whose positions, widths, and weights are directly tied to the eigenvalues and eigenvectors of the Lindbladian. The framework is implemented in an open-source Python package and benchmarked against exact single- and two-atom calculations. We identify geometries in which the full vectorial description is essential, and the scalar approximation fails qualitatively. Applying the method to pairs of atoms with a $J_g=0\to J_e=1$ transition, we show that elastic and inelastic scattered intensities collapse onto universal master curves controlled by a single collective saturation parameter built from the dominant superradiant mode, across several orders of magnitude in drive strength and interatomic distance. We identify collective phenomena that require a description beyond this single-mode picture. Extending the analysis to atoms with ground-state degeneracy, we find that most collective features carry over, while two qualitatively new effects emerge: an incoherent spontaneous Raman channel that modifies the scaling of inelastic emission, and a slow timescale in the time-delayed correlations $g^{(2)}(τ)$ governed by the competition between Raman scattering and subradiant decay, controlled by a single dimensionless parameter. These results provide both physical insight and practical computational tools for engineering collective optical responses in few-atom systems such as optical tweezer arrays.

Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objectives, learning amortizes that behavior into a reactive policy, yet existing protocols discard task semantics, leaving rewards hand-crafted and behavior drifting from what control verified.We introduce Semantically UNified (SUN) Programs, typed executables where geometric and contact relations are defined once and compiled into aligned Model Predictive Control (MPC) costs, satisfaction predicates, RL rewards, transition guards, and diagnostics. Our system, Kuafu, driven by large vision language systems, automatically synthesizes SUN Programs from language and scene semantics, screens feasibility via MPC, and retains semantics while training stage-conditioned policies. Across nine tasks, Kuafu achieves 82.03% macro-success, outperforming sparse-reward (35.67%) and Stage-BC (24.75%) baselines. At 8192-way scale, it generates 10.57x the successful trajectory time per hour of human teleoperation. With 500 trajectories per task, Kuafu data trains DP3 policies to 46.0% simulation success (vs. 22.4% for alternatives) and 34.7% on physical Franka and Kinova robots. These results establish that simulation-screened task semantics can effectively amortize control into robust policies, without demonstrations or manual dense rewards, unifying symbolic planning and data-driven execution.

This paper presents FAIRY, a full-stack smart-agriculture agent system developed for and deployed to an operating soybean research farm at Harbin Institute of Technology's smart-agriculture site. We develop FAIRY to execute and evaluate agentic agronomic operations on full-season spatiotemporal workflows that span ridge preparation, planting, irrigation, fertilization, pest and disease treatment, harvest, grain handling, drying, and storage. FAIRY integrates APIs and infrastructure across production-grade machinery, fixed soil and canopy sensors, multispectral and thermal drones, satellite vegetation products, a weather station, calibrated crop-process models, agronomic records, and multi-season yield histories. The system is built around the novel "everything is an event" execution paradigm, which represents spatiotemporal world evolution, remote sensing and UAV observations, sensor readings, crop-growth transitions, machinery actions, and management interventions as state-changing events in a shared farm process engine. On top of this event-driven world model, FAIRY implements a complete agentic stack: a knowledge library of atomic agronomic skills; multi-agent controller and orchestration backends; frontier- and edge-model execution; full-path trace logging; and deployment profiling on local nodes. We use FAIRY to evaluate nine state-of-the-art agent controllers across one hundred full-season soybean scenarios that preserve the operational coupling between spatial observations in a 64-ridge field, temporal decision sequences, agronomic constraints, delayed effects, and final yield. We develop an evaluation suite that combines agentic success, full-path spatiotemporal correctness, token cost, and edge-device runtime.

Autonomous scientific research agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-ended research tasks often do not clearly specify the analyses, methods, and success criteria required to complete the task. As a result, agents may miss important analyses, use inappropriate methods, or draw conclusions that are insufficiently supported by evidence. To address the problem, we present AutoSciRub, an evaluation-first framework that induces a task-specific executable rubric before research execution, and uses it to guide execution, criterion-level verification as well as iterative revision. AutoSciRub decomposes an underspecified instruction into atomic scientific goals, grounds them in relevant literature and task-visible data, and synthesizes specific, actionable, and verifiable criteria. The resulting rubric makes implicit experimental and evidential requirements explicit, providing guidance for experiments and analyses. During revision, rubric-guided verification identifies unmet criteria and enables targeted refinement of the research report and its supporting artifacts. On ResearchClawBench, AutoSciRub consistently improves all tested configurations, with an average gain of 2.08 points across three backbone LLMs under the fixed Codex harness and 2.95 points across three agent harnesses using a fixed DeepSeek-V4-Flash backbone. On a randomly sampled 20-task subset of AstaBench E2E Discovery, AutoSciRub further achieves an average improvement of 16.8 points across three agent harnesses, while maintaining or increasing the number of successfully completed tasks. These results demonstrate that evaluation-first guidance provides an effective and generalizable control mechanism for autonomous scientific research (Code: https://github.com/zjunlp/AutoSciRub).

End-to-end autonomous driving models plan future trajectories from raw sensor input. While earlier driving benchmarks often measured deviation from the human trajectory, current benchmarks such as NAVSIM and Bench2Drive evaluate models with richer simulation-based metrics intended to capture safe and compliant driving. A high benchmark score should reflect that a model can understand the scene in front of it and act accordingly. But how much of that score specifically comes from reacting to the dynamic part of that scene? To probe this, we remove a model's camera input and replace it with memories from prior drives at the same location. The retrieved memories can provide persistent scene information, including road layout and location-conditioned regularities, but not the current traffic state. Surprisingly, memory is nearly sufficient on NAVSIM, reaching or even exceeding the performance of leading end-to-end methods without actually observing the evaluated scene. Our results suggest that a high NAVSIM score does not require a planner to react to the current traffic scene and should be treated with caution. This effect is benchmark-dependent: driving from memory causes substantially larger performance drops on Bench2Drive and RealEngine. We provide our code at https://github.com/boschresearch/MemoryDrivoR .

Prosthetic hands equipped with cameras can use computer vision to plan grasps automatically, reducing cognitive effort. However, running modern vision models on wearable devices is impractical due to power and processing constraints. We present the first prototype of a 5G-connected mobile edge computing (MEC)-enabled semi-autonomous prosthetic hand, which streams RGB-D images to an edge server for real-time grasp planning. Thirteen able-bodied participants performed pick-and-place tasks under six conditions: manual EMG control, on-device inference, wired Ethernet connectivity, and three 5G connectivity configurations (private 20 MHz network, private 100 MHz network, and a commercial 5G link) to the server. All network-based conditions performed similarly, achieving task times around 8.6 s (34% faster than manual control), failure rates of 20-38%, and 62% lower overall workload. On-device processing performed the worst with 10.3 s task time and a 76% failure rate due to slow embedded inference (3 fps vs. 6-20 fps over the network). Network latencies remained below 180 ms for private 5G and 270 ms for commercial 5G. All 5G configurations, including bandwidth-constrained and commercially variable networks, matched wired Ethernet performance while significantly outperforming both manual control and local processing, establishing 5G edge-offloading as a practical path to deploying compute-intensive prosthesis control.

Agentic coding environments give a frontier large language model (LLM) direct access to a workstation's terminal, file system, and software. This work demonstrates they extend to professional RF hardware design: an active GNSS L1-band antenna - a circularly polarized patch, surface acoustic wave (SAW) prefilter, and two-stage low-noise amplifier (LNA) on one printed circuit board (PCB) - was designed, optimized, and made manufacturing-ready. The LLM agent autonomously operated CST Studio Suite, Keysight ADS, and KiCad via scripting interfaces. Engineer input was limited to the specification, trade-off decisions, and design reviews. Workflow, results, and the RF engineer's evolving role are discussed.

Robotic perception from a single viewpoint is often limited by self-occlusion and incomplete surface visibility. This paper presents DARP(Dual-Arm Robotic Perception) https://doi.org/10.21227/rmv3-be47, a calibrated dual-arm RGB-D-IR dataset for object-centered robotic perception using two independently moving eye-in-hand manipulators positioned on opposite sides of a shared tabletop workspace. Each arm carries an Intel RealSense sensor that continuously records RGB, depth, and stereo infrared data while synchronized robot joint states are logged for pose recovery. Objects are placed without fixed poses or marked locations, and the acquisition procedure performs automatic localization, cross-arm confirmation, adaptive viewpoint generation, and continuous multimodal recording. DARP contains ten unique tabletop objects and preserves the original sensor recordings, robot-state logs, object-level metadata, and calibration information required to reconstruct camera trajectories in a shared metric frame. To evaluate the geometric consistency of the acquisition, we implement a deterministic multi-view fusion pipeline that converts calibrated RGB-D observations into complementary partial point clouds and measured surface meshes without using learned or generative completion methods. Evaluation on 224 held-out RGB-D keyframes comprising 1,563,466 three-dimensional query points yields a median point-to-mesh distance of 2.13~mm and an RMSE of 4.04~mm, with 96.56\% of points within 10~mm of the measured-surface mesh. DARP is intended as a reusable resource for multi-view reconstruction, collaborative robotic perception, multimodal fusion, active perception, and future learning-based reasoning over partial object observations.

Quality-diversity (QD) algorithms have been gaining traction in robot learning, where diverse motion primitive libraries allow robots to adapt zero-shot to constraints at deployment time. However, such methods typically require expert designers to write the success condition, fitness and diversity metrics, and this strongly limits the robot's autonomy. On the other hand, existing LLM-based reward-shaping techniques allow robots to learn autonomously but only output single high-performing solutions, limiting the robot's adaptability. In this paper, we propose an approach designed to output diverse motion primitive archives by autonomously leveraging quality-diversity algorithms, only requiring a free-form description of the task in common language. To address the difficulty of designing relevant fitness and diversity metrics, we propose an autonomous exploration mechanism able to reliably output sets of functionals covering the fitness and behavior descriptor (BD) space. First, we pose policy exploration as a functional design problem, where the functional spaces are lower-dimensional than the full BD and fitness spaces, and propose an LLM-based exploration scheme to sample from these low-dimensional spaces without any task-specific prompts, fine-tuning or expert intervention. We adapt a multi-BD variant of the MAP-Elites success (MES) algorithm, designed to leverage the heterogeneous BD samples. Finally, through experiments based on the genesis simulator, we show that our method effectively generates archives of diverse motion primitives, outperforming classical QD algorithms with inferred and hand-written parametrizations on a set of $4$ robotic manipulation tasks.

Medical referral (directing patients to the appropriate hospital department) is a complex decision-making process requiring the synthesis of multimodal data, including patient narratives, laboratory indicators, and radiology imaging. While Large Language Models (LLMs) have advanced medical dialogue systems, they struggle with real-world referral tasks due to two primary limitations: (1) Information Overload, where models fixate on high-frequency disease terms while overlooking subtle but critical urgency indicators; and (2) Unstructured Collaboration, where existing multi-agent frameworks rely on loose dialogue that leads to semantic drift and confirmation bias. To address these challenges, we introduce MASGR (Multi-Agent Structured Graph Reasoning), a framework that treats referral not as a classification task but as a structured graph construction problem. MASGR deploys specialized agents to extract evidence from distinct modalities and coordinates them through a clinical reasoning graph. This graph forces agents to establish explicit logical connections between conflicting evidence. Furthermore, we integrate a knowledge-guided arbitration mechanism that prioritizes patient safety rules over standard diagnostic classification. Extensive experiments on real-world medical records demonstrate that MASGR significantly outperforms state-of-the-art LLMs and existing multi-agent systems, particularly in complex cases requiring the balancing of chronic disease management and emergency intervention. The AI contribution lies in the Multi-Agent Structured Graph Reasoning framework that transforms unstructured multi-agent dialogue into a verifiable logical graph construction. The engineering application is demonstrated through its deployment in a complex healthcare decision-making system to optimize the precision of complex medical referrals.

Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial priors for visual grounding, spatial reasoning, and pointing, but these capabilities are rarely elicited directly for robot control. Existing navigation systems instead rely on task- or embodiment-specific components, fragmenting perception, reasoning, and action while offering limited generalization. Here we present LightNav-0, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads. LightNav-0 represents diverse navigation tasks through a unified token interface: dual-channel pointing expresses task-, scene-, and embodiment-agnostic spatial intent, while a residual vector-quantized action tokenizer maps this intent to precise, embodiment-specific trajectories. Together with temporally aware visual history compression, ER mid-training, supervised fine-tuning, and reinforcement learning, this formulation supports instruction following, open-vocabulary object navigation, and visual tracking within a single model. The navigation training corpus spans 2K+ scenes and 4K+ hours of embodied navigation data. LightNav-ER, the embodied-reasoning checkpoint used to initialize LightNav-0, attains the highest complete-set average across 8 embodied-reasoning benchmarks, while LightNav-0 achieves state-of-the-art monocular success rates across all 10 public navigation simulation settings. Real-world evaluations further demonstrate zero-shot generalization across robot embodiments, diverse scenes, and static and dynamic targets. These results establish compact VLMs as a unified and transferable backbone for generalist embodied navigation.

Generalizable embodied manipulation remains difficult to achieve through pretraining alone, due to unseen physical conditions in the real world. We argue that robots need to learn from their own physical interactions on the fly during real-world deployment and use this knowledge to inform subsequent actions. We present Zeva, the first framework that enables in-context learning from a robot's own physical interaction experience while keeping the policy model frozen. Zeva employs a Causal Interaction Extractor to encode an executed action and its induced state change into a causal interaction signal, which is stored in a dual-timescale causal memory. For subsequent actions, relevant causal interaction signals are retrieved from memory and injected into the frozen policy model as context. Experiments in simulation and real-world manipulation demonstrate that Zeva achieves the best performance among the compared frontier VLAs and WAMs and, more importantly, enables self-evolution during deployment without gradient updates. Its success rate continues to improve as the robot accumulates interaction experience. Furthermore, the acquired interaction experience can generalize across tasks.

This paper considers decentralized contingency MPC for multi-agent control under a state-only information pattern, with particular focus on limited sensing and plug-and-play operation. The objective is to retain recursive feasibility, safety, and Lyapunov-type convergence while reducing conservatism in local interaction handling. The framework relies on agent-wise fallback regions (safe sets) in which a feasible contingency maneuver to a safe equilibrium is always available. A novel safe-set update mechanism is introduced that supports less conservative decentralized interaction while preserving the underlying guarantees. This, in turn, enables memory-free local interaction and finite sensing ranges without requiring agents to reconstruct the exact neighbor geometry. The resulting scheme remains fully decentralized and preserves the shared-first-input contingency MPC structure. Theoretical guarantees and simulation results illustrate the effectiveness of the approach in dense multi-agent scenarios.

Off-road navigation can fail when physical structures induce irrecoverable states such as high-centering or entrapment, requiring human interventions. Identifying these structures is crucial, yet challenging. Such failure events are rare and costly to collect, resulting in limited training data. Moreover, the collected data associate frames with outcomes, but do not indicate the visual cues responsible for the failure. Learning directly from these data can therefore exploit scenario-specific visual cues, leading to poor generalization. We propose \textbf{Geo-Anchored Fine-Tuning (GAFT)}, a parameter-efficient method that adapts a vision foundation model with a geometry-derived prior. It guides LoRA adaptation by aligning a spatial attention-rollout map with the geometry prior, while preserving pretrained representations. On an intervention-verified forest hazard benchmark, across ten independently trained adaptations, GAFT consistently outperforms frozen DINOv2 and supervised PEFT baselines, improving the repeated leave-one-scenario-out mean $F_2$ from 0.0607 to 0.3757 with statistical significance under paired analysis. Within these independently trained models, the best-performing GAFT model achieves a repeated-LOSO $F_2$ of 0.570. Code and benchmark: https://github.com/Xu-Yanran/geo_anchored_fine_tuning

To improve torque capacity and energy efficiency of humanoid ankles, this paper proposes a 2-DoF parallel elastic actuator (PEA). The main novelty of the proposed design lies in its dual-cam, single-gas-spring architecture, which enables torque compensation in both pitch and roll using a shared elastic element, thereby improving structural compactness compared with conventional multi-element compensation schemes. By leveraging parallel gas springs and customized cam modules, the proposed architecture provides dual-axis torque assistance tailored to specific task requirements. The second key contribution is the formulation of a coupled 2-DoF mathematical model that explicitly captures the interdependence between the two compensation units through the shared spring. Based on this model, an optimization-based design framework is developed to synthesize customized cam profiles from prescribed torque references, establishing a systematic link from task requirements to hardware realization. The complete lower-leg CAD integration is presented in detail. Static FEA and kinematic simulations confirm the design's feasibility and torque-relief effectiveness. The results highlight the proposed design as a compact, customizable solution for 2-DoF humanoid ankle torque compensation.

In animals such as elephants and octopuses, acquiring non-visual information about an object and physically engaging with it are inseparable processes mediated by rich, large-area interactions between compliant appendages and the environment. Soft robots provide a natural platform for translating this principle into engineered systems. Yet current robotic intelligence makes limited use of physical interaction, treating it primarily as a disturbance to be rejected or, at best, as a means of compensating for object misalignment. Here, we introduce a physical intelligence framework in which distributed compliant interactions jointly reveal task-relevant information and organize manipulation behavior. This results in an intrinsically partially observable problem: key task-relevant information is never measured directly, but must instead be inferred from the history of physical interactions. We propose a reinforcement-learning architecture that addresses this challenge by learning a memory-based control policy end-to-end. The key innovations making this possible are (i) a pretrained exploration policy that provides a reference for broad workspace exploration, (ii) joint optimization that integrates exploration and grasping objectives within a single recurrent policy, and (iii) a two-stage sim-to-real adaptation including observation mapping and policy fine-tuning. We demonstrate this principle through blind whole-arm grasping with a hybrid rigid-soft robotic arm that we equip with IMUs embedded directly within its compliant structure, providing its only source of proprioceptive sensing. The learned policy successfully identifies and grasps various objects by autonomously coordinating workspace exploration, object encounter and localization, inference of grasp-relevant properties, and stable whole-arm wrapping.

Source term estimation (STE), which aims to estimate key properties of the gas source, is essential for identifying hazardous gas releases. Information-theoretic approaches have been adopted for autonomous STE using mobile sensors due to robustness in noisy environments, yet their online action selection incurs substantial computational cost. Deep reinforcement learning (DRL) provides a promising alternative with its fast decision-making capability. In DRL-based STE, the agent selects actions based on belief states of the source term updated from noisy measurement sequences. However, existing methods rely on random exploration or solely on belief uncertainty reduction without an effective exploration strategy in DRL, which can limit policy robustness in noisy environments. To address this, we propose a curiosity-driven information-guided reinforcement learning for robust and efficient STE. The proposed method promotes active exploration of novel belief state transitions that have not been sufficiently explored during training. We further introduce an uncertainty-adaptive active perception reward to guide efficient source search under uncertainty. Simulations under high-noise conditions and real-world experiments demonstrate the robustness and feasibility of the proposed framework, highlighting its potential for practical STE problems.

Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-Agent, a hierarchical multi-agent system for long-horizon RS task solving. HiRS-Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-Agent Benchmark and ThinkGeo show that HiRS-Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-agent collaboration for reliable RS agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-Agent.

Large language models (LLMs) are increasingly used in software development, but their use in complex hardware design remains limited. This gap stems from both the scarcity of public hardware training data and the fundamentally different methodologies used in hardware design. In particular, applying LLMs to hardware requires more than direct RTL generation: the model must understand module boundaries, inter-module connections, and verification requirements. In this paper, we present an LLM-based hardware development framework with hierarchical intermediate representations (IRs) and an end-to-end multi-agent workflow. The core idea is to provide an abstraction of hardware design to LLMs through two structured IRs: Architectural Sketch, which captures module topology and interconnection, and Operational Specification, which defines per-module functionality and interfaces. Our framework uses these IRs to decompose a complex design into sub-modules, specify the per-block functionality, and derive how each module should be tested and verified. We incorporate a multi-agent debug loop in the framework, allowing agents to get the error feedback and control the debug details such as the signals to be probed for simulation. We evaluate our framework on Verilog-Eval benchmark, achieving a pass@5 rate of 95.5%, which surpasses current state-of-the-art LLM generation frameworks. To better assess performance on complex, realistic designs, we introduce a new case study spanning applications from general-purpose processors to digital signal processing systems. Experimental results indicate that such complex designs exceed the capabilities of existing approaches, whereas our framework is the only one capable of producing functional end-to-end design. Our generated RTL follows all industry-standard design rules, is lint-clean, functionally correct and fully synthesizable.

Recent vision-language-action (VLA) methods improve manipulation performance by aligning their representations with 3D scene geometry. However, these methods often struggle with long-horizon manipulation and observation aliasing between visually similar states due to a lack of temporal information: the 3D scene geometry captures only the current state, rather than how it has evolved over time. To resolve this, we present Temporal Forcing, a 4D representation alignment method for VLA models. Specifically, we first introduce a history pathway that enables a vanilla VLA model to summarize observation history into temporally aware latent representations. Then, the latent representations are aligned with the geometric features extracted by a pretrained 4D foundation model, which captures the evolving 3D world through temporally consistent geometric representations, enabling a deeper understanding of dynamic environments. Temporal Forcing reaches 98.8% on LIBERO, outperforming its base model by 2.2 points. On a physical hidden-placement task, it raises full-task success from 20.0% to 43.3%. Code will be publicly available.

The increasing integration of Internet-of-Things (IoT) technologies for monitoring and control of inverter-based resources (IBRs) has expanded the attack surface, enabling stealthy manipulation of controller parameters through vulnerable supervisory control interfaces. Phase-locked loops (PLLs) emerge as prime targets, as they interact with all control loops and critically influence the dynamic response of grid-following (GFL) converters. This paper analyzes the underlying threat model to elucidate the mechanisms enabling such stealthy behavior and conducts a thorough stability and transient response analysis to characterize how PLL tampering can degrade system performance without necessarily destabilizing the system. The results reveal critical interactions among frequency estimation, control, and synchronization that can significantly reduce stability margins. To counter the stealthy nature of these attacks, a modified PLL is proposed that exposes gain variations through shifts in its equilibrium points while preserving conventional PLL performance. Experimental results validate the effectiveness of the proposed approach in detecting PLL cyber-attacks.

Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of multiple constituent skills. Existing benchmarks, however, still rely primarily on full-task rollouts and aggregate task-level metrics, making intermediate failures difficult to observe and analyze. We present Behavior-Skill, a benchmark that reformulates the learning and evaluation of long-horizon tasks around executable constituent skills. It contains 235,492 skill instances from 10,000 demonstrations across 50 household tasks and 34 semantic skill categories. Each instance pairs a skill instruction with an aligned observation-action segment, and is further associated with a restorable intermediate state and a skill success condition to enable independent evaluation under valid preconditions. We further introduce trajectory-level and skill-level metrics to characterize policy capability beyond aggregate task success. Extensive experiments across representative VLA policies including pi0.5 and GR00T on the complete 50-task benchmark show that failures are highly non-uniform across skills, with contact-rich manipulation skills forming persistent bottlenecks. These results demonstrate that Behavior-Skill complements full-task evaluation by exposing intermediate capability profiles for analyzing and improving long-horizon VLA policies. Behavior-Skill is publicly available at https://github.com/nubot-nudt/Behavior-Skill.

Flexible sensing arrays are commonly used in underwater acoustic networks, but suppressed by unpredictable geometric deformations. Existing array shape self-calibration methods often estimate individual element positions separately, leading to a high dimensional optimization problem over long arrays. To address this problem, this paper proposes a Bayesian Optimization-assisted Geometry Estimation (BOGE) strategy operating with a hierarchical optimization process and a physics-informed parametric model for array geometry correction. BOGE formulates array shape self-calibration as an optimization problem, where candidate geometries are evaluated by the noise subspace residual. We perform Bayesian optimization to configure the physics-informed parametric model and then refine the selected geometry through numerical optimization. Empirical results show that BOGE achieves lower mean geometric root mean square error (RMSE) than the benchmark methods across a wide range of noise levels. On the public SWellEx-96 dataset, BOGE achieves a geometric RMSE of $0.659$ meters at $166$ Hz. A lake trial further shows that BOGE provides fixed source localization and moving target tracking performance comparable to the comparison methods.

Industrial Control Systems (ICS) are the backbone of many critical infrastructure sectors; however, their growing level of connectivity, long lifespan and integration with the Information Technology (IT) environment introduces numerous cybersecurity challenges. The merging of Operational Technology (OT) and IT along with the deployment of Industry 4.0 technologies increases the attack surface of ICS environments, which in turn makes them more vulnerable to advanced cyber threats. Therefore, many researchers have shown interest in the field of cybersecurity of ICS. The topics of intrusion detection, anomaly detection, threat intelligence, attack simulation and resilience assessment of ICS have received much attention. Nevertheless, the development and testing of cybersecurity solutions for ICS remains to be challenging due to the lack of appropriate datasets and experimental environment. The main objective of this paper is to provide the roadmap of existing ICS cybersecurity datasets, testbeds and digital twins. This paper presents various taxonomies along with systematic analysis of architecture, characteristics, capabilities, pros and cons of these tools. The results of the analysis demonstrate the presence of persistent problems such as lack of standardized benchmarking datasets, lack of modern attack scenarios, insufficient number of datasets based on real operational traffic and difficulty in validating artificial intelligence-driven cybersecurity solutions. In addition to summarizing current research on ICS cybersecurity datasets and testbeds, this roadmap provides the identification of research gaps and recommendations on creation of new tools.

The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing the emergence of Remote Sensing (RS) Agents. However, the practical deployment of these advanced agents is severely hindered by their heavy reliance on large-scale general-purpose LLMs, which lack deep domain expertise and impose prohibitive infrastructure demands. To resolve this, we propose SimCRAFT, a model-agnostic framework that distills sophisticated RS orchestration capabilities into a compact 7B-scale model. Addressing data scarcity, we first pair a multiagent synthesis engine with a Mock Execution Engine that checks schema correctness, inter-tool dependencies, and sensor/tool compatibility, producing SimRS-14k, a large-scale, constraint-validated workflow planning corpus. Second, we propose Contextual Retrieval-Augmented Fine-Tuning (CRAFT) that finetunes the model to reason analogically by adapting retrieved Standard Operating Procedures to novel queries under a noise-robust objective, generalizing RAFT to multi-step RS workflow planning without mechanical copying. Extensive experiments demonstrate that SimCRAFT-7B significantly outperforms openweights LLMs and rivals advanced closedsource models and specialized RS agents, while reproducing across three 7B backbones. This work contributes a competitive open-weights baseline for lightweight RS intelligence, enabling efficient autonomous deployment under resource-constrained or resource-conserving conditions.

This data article presents a high-resolution, long-term synthetic electric-vehicle (EV) charging dataset for Trondheim, Norway, spanning February 2020 to December 2030. Empirically grounded in 14 months of historical charging logs from December 2018 to January 2020, the dataset captures session-level behavioral patterns, including delivered energy, plug-in duration, connection schedules, user categorization (private vs. shared), seasonal variations, public-holiday effects, and daily ambient temperature dependencies. To model future electrification dynamics, the synthetic generation pipeline integrates historical session records, calendar and weather features from MET Norway, annual EV-adoption growth multipliers derived from Statistics Norway (SSB) registration trajectories, a daily session-count model, a Conditional Tabular Generative Adversarial Network (CTGAN), seasonal Kernel Density Estimation (KDE), and post-generation physical charger-power feasibility correction. Under a standardized 7.2 kW AC charging constraint, the resulting medium EV-adoption scenario dataset contains 76,993 hourly charging-activity records. The hourly profile is activity-based rather than a complete continuous hourly time series; hours with no allocated EV charging energy are not included. The records provide total hourly charging energy, equivalent average charging power, active session counts, private/shared user load breakdowns, ambient temperature features, and calendar indicators. The dataset provides a validated cold-climate benchmark for distribution-grid impact assessment, transformer-loading analysis, EV charging-demand forecasting, charger-capacity planning, energy-management optimization, and the development of data-driven smart-charging control strategies.

Multi-agent AI platforms move quickly from staging to production, but the way agents establish trust remains rudimentary: an agent either transmits raw data to a peer or accepts that peer's natural-language self-report that a value complies with policy. The first over-shares; the second is unverifiable and is exactly the channel prompt injection attacks. Prevailing responses emphasise identity, visibility, and post-hoc detection, and recent proposals for cryptographically enforced agent policy have been evaluated in simulation rather than execution. We take provable data minimisation between agents from proposal to running system. In our Zero-Knowledge Proof Gateway, agents exchange proofs of governance-defined predicates over private data rather than the data itself, so exposure is prevented by design rather than detected afterwards; because no interoperability protocol can carry such a proof, we propose a slot and implement it on both MCP and Agent2Agent from one endpoint. A 32-bit threshold predicate proves in 6.2 ms and verifies in 1.0 ms with a 608-byte Bulletproofs proof on one commodity vCPU; eleven adversarial experiments and nineteen protocol checks pass; and the system is deployed to Kubernetes with empirically verified network isolation. Our case study proves a retail client order is within its limit without revealing the amount, instantiating the GDPR data-minimisation principle as an enforced technical measure of the kind EU law now names explicitly. We then address the limitation no comparable work resolves: a predicate proof binds a statement to a committed value, never to the system of record. We give a construction fusing an enclave attestation with the proof in both directions, so verifying one artifact certifies jointly that the predicate holds and that the value was read by a specific measured binary, and test it against a mock authority.

Wood slices under a polarized optical microscope show a spectrum of interference colors, such as cyan, blue, magenta, yellow, and bluish gray because of the birefringent cellulose in the microfibrils. An optical model is established to simulate the birefringent-colored micrograph of wood. Five typical cell wall architectures, line, helix, ring, crossed helix, and twisted helix, are considered. With a retardation wave plate to distinguish fibrils of different orientations, each structure displays its unique birefringent-colored texture, presenting its underlying 3D structure with the vivid colors. Cross sections of the trunk and twig of Eucalyptus grandis presented birefringent-colored profiles. Three identification methods were compared: visible fibril trends, birefringent-colored optical textures, and the simulated look-up library. The three methods gave consistent results, proving that the birefringent-color tags are efficient and accurate. Electron and atomic force microscopy are unable to resolve cellulose microfibrils embedded in the lignin and hemicellulose matrix. Polarized optical microscopy overcomes this by selectively detecting birefringent cellulose, enabling accurate identification of complex helical structures. This method enables statistical and spatial analysis of complex biomaterial compositions. Capable of profiling dozens of cells simultaneously, this high-throughput optical method provides a potentially fully automated analysis framework for plant science, biomechanics, and bioinspired cellulose materials.

The order of cellulose microfibrils in xylem cell walls is identified using polarized optical microscopy. The line, helix, ring, crossed helix, and twisted helix organizations in a cylindrical shell are the equilibrium states of balanced elastic deformation and surface anchoring. A computational model of the five organizations is established to simulate their birefringent-colored profiles. These five textures present unique optical textures, which are clearly recognized in the cross sections of Eucalyptus grandis. The libriform fiber cell for support has a twisted helical cell wall. The vessel cell for high-speed water uptake consists of a helical layer covered by a layer of vortex array. The ray cell for radial transportation is crossed helical. The microfibril angles versus the radius of the cell wall were measured utilizing the distribution of birefringence colors. In fiber cell walls, the MFA is significantly correlated with the curvature, bending, and surface anchoring, respectively. In vessel cell walls, the vortex array includes focal conic domains of chiral order and topological defects of nematic order, suggesting that the phase transition of cellulose fibrils leads to pattern formation. Liquid crystal phases and patterns in the cell walls reveal how the cell wall thickens and how cells differentiate. Out of the frustration of long, stiff, twisting fibrils packed in slender tubes, trees generate the helical channel networks, transforming the brittle lamina into an elastic, tear-resistant, self-healing tissue.

While pretrained Vision-Language-Action (VLA) models offer broad generalization capabilities in robotic manipulation tasks, adapting them to real-world environments or handling task shifts often requires substantial additional data and retraining. To address this, we propose Symmetric VLA Distillation (SymVD), a distillation framework that transfers knowledge from a large VLA teacher to a compact student policy by explicitly exploiting geometric symmetries in manipulation tasks, such as rotational and reflectional invariance. SymVD employs an equivariant actor-critic architecture and trains the student using a symmetry-aware objective that aligns with teacher actions under group-invariant properties. We demonstrate that by enforcing the policy to respect equivariance, SymVD reduces redundant exploration across configurations related by group transformations and improves sample efficiency during distillation. To further stabilize and improve distillation, SymVD introduces an adaptive weighting scheme that dynamically balances the distillation objective and reinforcement learning updates based on training progress, enabling robust transfer even when the teacher signal is imperfect or misaligned. Experimental results on robotic manipulation tasks demonstrate that SymVD consistently improves over standard distillation and also outperforms SAC in terms of sample efficiency and generalization to previously unseen symmetric transformations of the environment.

Developing high-performance CUDA kernels demands specialized knowledge in algorithm implementation, correctness validation, and hardware-aware parallel optimization, creating a substantial expertise barrier and making generating CUDA kernels directly from natural language (Text2CUDA) essential. Meanwhile, the general-purpose code generation capability of Large Language Models (LLMs) prompts a series of works exploring LLM-based CUDA kernel generation. They mainly focus on transpilation from high-level frameworks such as PyTorch to CUDA (Torch2CUDA) rather than Text2CUDA, where models must understand the high-level input semantics and handle low-level kernel implementation and validation. Additionally, these methods are vulnerable to reward hacking due to reliance on predefined test inputs. In this paper, we propose CUDA-Harness, a framework for harnessing agentic CUDA kernel generation and optimization from natural language. Specifically, we introduce Intermediate-Structured Generation to connect high-level semantic understanding with low-level kernel generation. To dilute reward hacking in Text2CUDA, we construct Synthesis-Based Verification to provide isolated test data and progressive validation. Furthermore, we propose Feedback-Adaptive Evolution, a kernel evolution strategy that prioritizes correctness while optimizing performance. Finally, through extensive experiments, we demonstrate the effectiveness of CUDA-Harness, with further evaluations illustrating generalization across LLMs, hardware platforms, and to C-to-CUDA transpilation.

Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving agent reliability. Existing topology- and spectrum-based methods exploit trajectory structures but often overlook fine-grained semantics, while LLM-based attribution methods capture semantic cues but suffer from long-context degradation over lengthy trajectories. To address these challenges, we propose DUOTRACE, a plug-and-play detection filter for LLM-based failure attribution. DUOTRACE follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods. For effective VAE-based anomaly detection on agent trajectories, DUOTRACE integrates dual-view semantic-structural node representations, a Tree-LSTM-based trajectory encoder, and prefix-chain- and LLM-based data augmentation to handle heterogeneous nodes, hierarchical execution structures, and limited failure data. Experiments with six LLM-based attribution baselines show that DUOTRACE improves agent-level and step-level attribution accuracy by 8.7% and 7.0%, respectively.

Large language model agents increasingly solve long-horizon tasks through multi-agent harnesses in which a central agent coordinates specialized sub-agents, tools, and environments. Training the central policy in such a harness raises two challenges. First, an action label is a low-cardinality decision, whereas its args form a high-dimensional conditional sequence; optimizing both with a shared sequence-level signal can produce conflicting gradients. Second, dynamic scheduling creates interdependent sessions with branches, parallel calls, and rewritten contexts, which cannot be faithfully reduced to one flat token sequence. We introduce Harness-RL, a structured reinforcement learning framework that combines Conflict-Aware Policy Optimization (CAPO) with interface-level black-box trajectory construction. The black-box component captures Interface Call Records, builds per-session prefix trees, and aligns outcome and process rewards with trainable tokens. CAPO uses forward activations to identify parameter partitions associated with action and args tokens, then routes their policy gradients to the corresponding subspaces. Harness-RL supports both central-only and joint multi-agent training. Across seven multi-hop question answering and agentic retrieval benchmarks, it reaches average F1 scores of 42.93 and 47.79 with Qwen2.5-1.5B and Qwen2.5-3B, respectively, while ablations validate the contribution of CAPO and favor central-only optimization in the evaluated setting. Our code is available at https://github.com/jiangxinke/Harness-RL.

Safety-critical optimization applications, such as real-time power system operation, maintain feasibility at every intermediate step, not merely at convergence. Existing approaches either violate constraints mid-solve (interior-point methods) or enforce feasibility through per-instant quadratic programming subproblems with cubic computational cost and unbounded worst-case execution time. We propose a continuous-time optimization framework for smooth constrained nonlinear problems that preserves feasibility throughout the optimization process without requiring projection operators, quadratic programming subproblems, or other per-iteration optimization routines. The method is built around a reciprocal multiplier manifold, which establishes an explicit relationship between inequality constraints and their associated Lagrange multipliers. By designing a continuous multiplier update law, the manifold is shown to remain forward invariant, while the resulting dynamics are equivalent to continuous-time logarithmic barrier gradient descent. The proposed framework naturally extends to multiple inequality constraints, equality constraints, nonconvex feasible sets, and infeasible initial conditions. The method is further enhanced through an augmented Uzawa flow that eliminates oscillatory transients commonly observed in classical primal-dual saddle-point dynamics. The effectiveness of the proposed approach is applied to the AC Optimal Power Flow problem of IEEE 9-bus and IEEE 57-bus systems. Numerical results show convergence to solutions within 0.4\% of the benchmark optimum while maintaining strict feasibility of all constraints. A computational complexity analysis shows that the proposed dynamics reduce the per-step computational cost from cubic to linear complexity. Finally, dynamic tracking studies under time-varying operating conditions demonstrate reliable feasibility preservation.

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AgenticRag-R1 consistently outperforms strong baselines. Moreover, AgenticRag-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information-aware optimization for long-horizon reasoning. Our code is anonymous available at https://github.com/jiangxinke/Harness-RL/tree/AgenticRAG-R1-Whitebox.

Across industries, machine-learning systems support applications ranging from prediction and anomaly detection to forecasting, optimization, and scheduling, yet operationalizing these systems requires coordinating application development, model pipelines, cloud infrastructure, security, deployment, monitoring, retraining, recovery, and rollback. We present an evidence-gated multi-agent framework for transforming a natural-language MLOps cloud engineering task into a verified repository and operational cloud deployment. The framework combines graph engineering, loop engineering, and agent harness engineering. A stateful Graph Orchestrator coordinates specialized agents for repository generation, review, execution, verification, release, and monitoring while governing workflow dependencies, evidence gates, retry bounds, recovery paths, and termination. Consequential lifecycle transitions proceed only when their required predicates are supported by verifiable execution or runtime evidence. Verification failures activate bounded reflection, repair, and re-verification, while runtime evidence of failure, drift, degradation, or policy violation can trigger bounded adaptation, recovery, or rollback. Agent harness engineering constrains repository generation, review, and repair, artifact execution, and cloud operations through controlled capabilities and isolated execution environments. We realize the framework on Google Cloud Platform and evaluate repository completeness, controlled execution, evidence-gated transitions, cloud promotion, and bounded recovery. Our experimental results show that the framework prevents unsupported lifecycle transitions and drives each run toward either a verified operational deployment or an auditable terminal failure.

Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward \emph{agentic skills}: modular procedural abstractions that externalize execution knowledge into reusable, executable, and portable artifacts. This paper establishes a unified systems foundation and reference architecture for the agentic skills ecosystem. We formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle: autonomous discovery, authoring and representation formats, memory storage, dynamic retrieval and routing, composition and orchestration, execution and repair, lifelong adaptation, empirical evaluation, and security governance. We further examine marketplace dynamics, public registries, and emerging adversarial threat vectors, alongside runtime verification and defense mechanisms. Finally, we categorize system implementations across software engineering, operating system navigation, embodied robotics, and scientific discovery, while highlighting critical open challenges in continual learning and benchmark realism. This work establishes agentic skills as a foundational paradigm for building scalable, robust, and verifiable autonomous language agents.

Online learning-based control is a promising approach to control uncertain systems, where unknown components are identified during operation to improve control performance. However, resource-intensive online learning algorithms introduce non-negligible computational delays, especially when executed on systems with limited local computational resources. To mitigate this, an in-network online learning-based control structure is employed by deploying the learning-based controller on a remote computation node and connecting it via a communication channel. In this paper, control performance guarantee is first established by deriving tracking error bound for the in-network control architecture, while accounting for computational delays. The derived tracking error bound allows for diverse communication and computation strategies under a specific condition, including time-/event-triggered mechanisms. Additionally, the trade-off between communication and computation performances is shown for a given desired control performance. Furthermore, to enhance the efficiency in both communication and computation, an efficient control framework with an asynchronous event-triggered mechanism in both control and online learning is devised under the existence of computational delay. The proposed event-triggered strategy is proven to achieve the same control performance as time-triggered scenario while excluding Zeno behavior. Finally, we derive an explicit expression of the proposed event-trigger condition for exponentially stabilizable systems, and demonstrate its effectiveness through simulations.

Ensuring the safe operation of multi-agent systems (MASs) under uncertain environments is crucial for cooperative robotic, where external disturbances and inaccurate dynamic models can significantly compromise performance and reliability. To address this challenge, calibrated machine learning models, particularly Gaussian process (GP) regression, are extensively employed due to their interpretable performance quantification. As the interconnected communication of MASs facilitates cooperative learning, agents are able to enhance learning performance by exchanging local GP inferences with their neighbors and aggregating the received information via distributed GP strategies. However, variations in computational power and prediction tasks among agents inevitably lead to heterogeneous computational delays and differences in query points, which are often overlooked in existing aggregation methods. To overcome these limitations, this work proposes an asynchronous cooperative learning strategy that explicitly accounts for prediction accuracy, query point variations and delay effects. Additionally, a distributed control law based on an adjoint MAS is developed to ensure the desired control performance. Simulations on unmanned surface vehicles validate the effectiveness of the proposed approach, demonstrating substantial improvements in both learning and control performance compared to the state-of-the-art approaches.

Optical skyrmions, characterized by topologically stable and spatially varying polarization textures, show immense potential for robust optical communications and metrology. However, conventional methods for generating optical Stokes skyrmions rely on bulky free-space optics, strictly constraining both system miniaturization and dynamic reconfigurability. Here, we demonstrate the efficient and programmable generation of optical skyrmions and bimerons using a compact silicon photonic chip. By integrating a programmable Mach--Zehnder interferometer mesh with a multi-dimensional grating emitter, we dynamically control the amplitudes, phases, and polarizations of emitted fundamental and orbital angular momentum modes. This architecture allows on-demand electrical switching among a complete library of optical quasi-particle states, including Néel, Bloch, intermediate, and anti-type skyrmions and bimerons. Experimental full-Stokes polarimetry confirms high-fidelity polarization textures with near-unity skyrmion numbers. Our foundry-compatible platform translates complex topological light generation into simple voltage controls, paving the way for next-generation communication and sensing systems based on optical skyrmions.

Teleoperation systems are increasingly used in medical, rehabilitation, and remote manipulation applications, where accurate position/force tracking and stable interaction are essential. In such applications, the remote environment may exhibit viscoelasticity, frictional memory, contact transitions, and other dynamic interaction effects, causing the system response to depend not only on the current state but also on its previous evolution. This history dependence, together with communication delays and uncertain nonlinear dynamics, makes accurate uncertainty compensation particularly challenging. Conventional feedforward neural approximators do not inherently retain temporal information, while fully recurrent architectures may introduce additional computational and online training complexity. To address this limitation, this article introduces the first application of a liquid state machine (LSM) to bilateral teleoperation control. A finite-time adaptive controller is developed using a hybrid position/force auxiliary error system with velocity and force filters, while the LSM is employed to estimate uncertain dynamics by exploiting its intrinsic temporal processing and fading-memory capabilities with a simple adaptation mechanism. Closed-loop stability and finite-time convergence are established through a Lyapunov--Krasovskii framework. Simulations in spring--damper and generalized Maxwell viscoelastic environments demonstrate improved position and force tracking and lower mean execution time compared with an RBFNN-based controller.

Rapid and reliable disaster mapping of impacted areas, damaged infrastructure, and affected populations is essential for emergency response and recovery. However, existing AI-based approaches often require extensive manual annotation, lack cross-hazard generalization, and rely on single-modal observations. To address these challenges, this paper proposes RAPIDMap, a rapid multi-agent pipeline for zero-shot interpretable disaster mapping from satellite and street-view imagery. The framework integrates four intelligent agents: Disaster Perception Agent (DPA), Image Restoration Agent (IRA), Damage Recognition Agent (DRA), and Disaster Mapping Agent (DMA). By combining remote sensing and street-view data, RAPIDMap eliminates the need for manual fine-tuning, generalizes across multiple disaster categories, and generates structured, map-ready disaster intelligence with recovery recommendations.

Longitudinal clinical agents must maintain an evolving patient state from evidence distributed across visits, time points, and specialties. However, how agent memory should be designed for this setting remains unclear. We introduce a benchmark of multi-visit, multi-specialty patient records that evaluates long-context evidence retrieval, cross-time evidence aggregation, and cross-specialty clinical reasoning. Using this benchmark, we systematically study four memory design choices: curation, organization, retrieval, and memory-augmented reasoning. We find that temporal validity is more important than simply retaining more history; specialty-factorized memory reduces context but can hide shared evidence; and multiple agents help when specialists must reason together, not merely when evidence comes from multiple memories. Guided by these findings, we propose \textit{MedCache}, a hybrid framework that constructs temporally valid patient memory, organizes evidence into overlapping specialty views, routes each query to relevant memories, and adaptively invokes one or multiple specialists. Experiments show that MedCache improves reasoning accuracy and memory efficiency over strong single-agent and multi-agent baselines, while generalizing across model backbones and external datasets.

Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .

Optical neural networks (ONNs) promise high-throughput and energy-efficient artificial intelligence, yet essentially all implementations so far encode information across space either in free-space arrays or in integrated waveguide meshes, tying the number of neurons to the number of physical components and fixes the routing topology at fabrication. Here we show that moving the computation into time decouples computational dimension from hardware dimension. Exploiting space-time duality, we implement optical diffraction and interference entirely in time domain, using thin-film lithium niobate modulators as time lenses and temporal masks, with chromatic dispersion providing the coupling between successive temporal neurons. We experimentally verify high-order, complex-valued matrix-matrix multiplications using just a single optical input/output port, scaling the computational dimensions far beyond the channel count. By incorporating optical feedback, we extend this platform into versatile neural networks, where the network layers, neuron numbers, and synaptic connections are fully programmable and in-situ trainable. Our temporal diffractive neural networks are successfully validated on various classification benchmarks, alongside image and video generation tasks. Notably, using this platform we demonstrate an all-analogue generative pipeline in which the latent variable is drawn directly from amplified spontaneous emission, so that no digital sampling or electronic modulation appears anywhere in the generative path. Furthermore, high-resolution images and videos are generated at high frame rates, outperforming state-of-the-art modulator-refresh-limited optical generative systems. These results establish a unified photonic temporal computing framework, providing a scalable and deployable pathway toward next-generation machine intelligence.