Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Improving adaptability of models to new tasks and environments without task-specific fine-tuning is critical for scalable embodied intelligence.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in agentic systems2 papers raise it · 1 addresses it

  High computational and time costs limit practical deployment of agentic systems for real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviewsraises · addresses
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Robustness to irreversible failures and accurate state tracking are essential for reliable embodied control.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Evidence-grounded multimodal reasoning benchmarks1 paper raises it · 1 addresses it

  Current benchmarks often fail to ensure models use necessary audio-visual evidence, weakening evaluation reliability.

  • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses
• Length generalization in sequential state tracking1 paper raises it · 1 addresses it

  Models struggle to maintain performance on problems much longer than their training data, limiting scalability.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.CROct 15

  Recoverability-Controlled Safety Miscalibration in Large Language Models

  Yuwei Wang, Xingwang Liang, Yu Xie, Haotian Chi, Haijun Geng

  Safety-aligned language models are expected to refuse harmful requests while remaining useful for benign ones. However, because many evaluations score only the final response, they often conflate intent understanding with response-level safety behavior. To address this, we introduce RiskCueBench, a recoverability-controlled benchmark that separates these two stages by first measuring whether a model can successfully recover a high-level intent and then evaluating its safety behavior on the same prompt. RiskCueBench contains 160 latent intents and 640 abstract non-operational surface prompts across eight risk categories. The benchmark covers 25 completed model groups and 32,000 successful model outputs with final rubric-adjudicated labels. When conditioning on pairs where both surface forms are recoverable, we find that increased contextualized specificity induces a shift toward less safe behavior. Specifically, paired bootstrap estimates show that the refusal rate and global safety score decrease by 0.175 and 0.440, respectively. Furthermore, mixed effects modeling corroborates a 0.107 increase in unsafe cooperation. These results show that the safety behavior can be…

  PDF

  Summarize this
• arXiv cs.CLOct 15

  TRACER: Trajectory-Aware Tool Retrieval for LLM Agents

  Tanish Kher, Sarvesh DK, Abedelkadir Asi, Sparsha Chennarayapatna Sundaresh, Dezhi Hong

  Modern agents select tools from registries, but exposing entire registries incurs high token costs and can impair selection as they grow. We present TRACER, a retrieval front-end that indexes observed tool-call sequences in a trie and ranks continuations using a learned blend of empirical and contextual priors. On a mixed retail-and-telecom $τ^2$ environment, TRACER improves GPT-5.4's tool-selection accuracy by 4.7 points while reducing input tokens per step by 80%, exposing just 5 of 128 tools. In autonomous full-turn execution, it matches GPT-5.4's full-registry task success with 61% fewer input tokens per step. Across six environments and four models, TRACER improves tool-selection accuracy over full-registry selection in 21 of 24 model-environment pairs, with average gains of 6 to 10 points; the three exceptions trail by at most 2.2. We analyze failures in both regimes to identify directions for future work.

  PDF

  Summarize this
• arXiv cs.CVOct 15

  TRACER: A Multimodal Harness for Patient Care in Hospitals

  Zane Durante, Paul Tang, Keshigeyan Chandrasegaran, Amit Kaushal, Shrinidhi Kowshika Lakshmikanth +9

  Continuous video and clinical records provide complementary information for understanding how patient behavior evolves over a hospital stay. A central challenge is how to represent behavior across the entire stay while preserving access to fine-grained visual and clinical evidence. We introduce TRACER, a training-free multimodal harness that constructs minute-level action records from video and combines them with clinical records into hourly reports. The harness equips an LLM agent with tools to query this hierarchy, inspect relevant video, and retrieve clinical records. To evaluate TRACER, we construct two benchmarks. The first contains 397 annotated one-minute clips spanning 15 atomic actions; the second poses 144 clinician-informed multiple-choice questions, grounded in 264 hours of video and clinical records from two ICU patients. TRACER achieves up to 84.8% accuracy for action detection and 61.0% QA accuracy versus 49.3% for the strongest baseline using the same backbone. Across 280 patients spanning approximately 60,000 camera-hours, TRACER identifies significantly less purposeful activity in patients with a positive delirium assessment during their stay than in those…

  PDF

  Summarize this
• arXiv cs.LGOct 15

  Rethinking Learning from Label Proportions via Moment Matching

  Tianhao Ma, Wei Wang, Yivan Zhang, Dong-Dong Wu, Takashi Ishida +2

  Learning from label proportions (LLP) is a weakly supervised setting where training data are grouped into bags with only bag-level label proportions observed, and the goal is to learn a classifier that predicts labels for individual instances. Recently, a large body of methods has emerged; however, most of them rely on the assumption that instance-label pairs are sampled i.i.d. and randomly assembled into bags, an assumption often violated in real-world scenarios. Our experimental results indicate that these methods perform suboptimally under non-random settings. In this work, we adopt a more realistic assumption: bags are sampled i.i.d., and instance labels are conditionally independent given the instances. Under this setting, we show that the label counts follow a Poisson multinomial distribution. Motivated by this observation, we propose LLP via moment matching (LLP-MM), a simple yet effective approach which leverages multi-order factorial moments as training objectives, encouraging the classifier predictions to match these moments and thereby more fully exploit the underlying statistical structure of the data. Extensive experiments on benchmark datasets under various bag…

  PDF

  Summarize this
• arXiv cs.LGOct 15▲ 106

  Behavioral Compositionality of Sparse Autoencoder Representations

  Haotian Ma, Ziye Mei, Frederic Sala

  Sparse autoencoders (SAEs) represent model activations with sparse, linearly decoded features, but the downstream effects of those features need not compose additively. We introduce SAE Additivity Residuals (SAR), which measure the behavioral variation left unexplained above a chosen interaction order. Under independent feature subset sampling, population SAR is exactly the normalized energy of interactions above that order and bounds coalition ordering error for the optimal low order approximation. To distinguish compositionality associated with the SAE representation from that induced by downstream computation, we compare learned SAE coordinates with sum preserving random rotations of the same selected subspace and find lower first order residuals for the learned coordinates across all 18 model and behavior settings. The coordinates are nevertheless not fully additive: pairwise terms improve held out coalition ordering in every setting and outperform parameter matched models using randomly selected third order terms. In a combined steering experiment, pairwise modeling raises rank fidelity from 0.5874 to 0.7790 and reduces ordering error from 0.1444 to 0.0606. Together, these…

  Code
• arXiv cs.LGOct 15

  Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference

  Sunghyun Wee, Geunjae Choi, Hyeonjin Kim, Suyoung Kim, Nojun Kwak

  Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations in linear projections dominate compute and energy cost. Post-training quantization (PTQ) reduces this cost by mapping weights and activations to low-bit integers. Power-of-Two (PoT) weight quantization promises efficient multiplier-free LLM inference via shift-add logic, but suffers significant accuracy degradation at low bitwidths due to its coarse base-2 quantization grid. We introduce Fractional PoT (FPoT), a base-$\sqrt{2}$ (half-octave) fractional PoT grid that achieves practical 4-bit weight quantization while preserving a fully integer shift-add datapath. The method combines (i) the base-$\sqrt{2}$ weight grid with uniform integer activations, (ii) a calibration-time grid-alignment refinement absorbed into the static per-channel scale, and (iii) a lightweight 1-adder $\sqrt{2}$ approximation whose error is absorbed during weight calibration via approximate-grid quantization, yielding a processing element (PE) with significantly fewer gates than a 4-bit integer multiplier. On Llama-3-8B with 4-bit weight and activation quantization, FPoT improves zero-shot commonsense…

  PDF

  Summarize this
• arXiv cs.LGOct 15

  Isolating a Language Model's Judgment with a Label-Free Subspace

  Chaemin Jang, Donggyu Lee, Jeesoo Kim, Dongman Lee, Jihee Kim

  Language models are often asked to make judgments: whether a proposed answer is correct, whether one statement follows logically from another, or whether a response is safe. Yet changing the instructions that specify how the judgment should be expressed can make the final answer less reliable, even for the same input. We ask whether this reflects a change in internal judgment or a failure to express it. Comparing hidden-state vectors for the same input under different instructions, we find that their differences concentrate in a low-dimensional expression subspace. We identify this subspace without benchmark labels and remove its contribution from a linear predictor to obtain an isolated judgment. Across correctness, entailment, and safety, the isolated judgment remains reliable under instructions not used to identify the subspace, even when the model's final answer and the original predictor degrade. When the judgment question is negated, isolation raises the predictor's AUROC from 0.504 to 0.825 for entailment and from 0.480 to 0.891 for safety. We also find that judgment is readable in earlier layers, before the expression subspace begins to disrupt the predictor. Together,…

  PDF

  Summarize this
• arXiv cs.CLOct 15

  LLM-Based Weak Annotation for Cybersecurity Tweet Classification: A Teacher-Student Framework

  Ferry Afit Kurniawan, Kazushi Okamoto, Koki Karube, Kei Harada, Atsushi Shibata

  Cyber threat intelligence (CTI) relies on the timely identification of emerging threats, enabling organizations and security analysts to support situational awareness and decision-making. Social media platforms such as X (formerly Twitter) have become valuable CTI sources because vulnerabilities and attack activities are often discussed there before appearing in formal reports. However, the rapid growth of cybersecurity discussions on social media has created more content than domain experts can realistically review and annotate, making labeled data a major bottleneck for developing supervised learning approaches. While large language models (LLMs) have shown promise as weak annotators in other domains, their effectiveness for cybersecurity tweet classification and downstream training of domain-specific pre-trained language models (PLMs) remains underexplored. To address this challenge, we propose a Teacher-Student weak supervision framework in which a selected LLM serves as a Teacher to generate weak labels for unlabeled cybersecurity tweets, enabling the training of cybersecurity-specific PLMs without large-scale manual annotation. Experimental results show that PLMs trained…

  PDF

  Summarize this
• arXiv cs.HCOct 15

  What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?

  Subigya Nepal, Ruth Heo, Emma M Parrish, Colin A Depp

  Safety evaluations of artificial intelligence (AI) chatbots focus on therapeutic redirection, statements urging users who disclose suicide thoughts to seek help from crisis lines or other human sources. How chatbots respond when users refuse that help is unclear. This cross-sectional audit ran 2,550 scripted multi-turn conversations in September 2026. Each conversation opened with a disclosure of suicide thoughts at 3 levels of severity, answered every referral with up to 10 standardized refusals and then changed the subject. All 2,550 conversations included a referral, 2,542 (99.7%) in the first reply. However, mean persistence ranged from 0.01 to 9.94 refusals across chatbots. Newer versions of all 5 chatbots tested in 2 versions persisted less than older versions (each P < .05). Compared with passive ideation, a disclosure of intent was associated with 1.26 more refusals sustained (95% CI, 1.06-1.46) and higher odds of renewed referral after the topic change (odds ratio, 10.07; 95% CI, 7.43-13.66). Chatbots that persisted less in referral more often presented themselves as the user's support (Spearman rho = -0.80; P < .001). Of 8,818 refusal-phase replies urging outside help,…

  PDF

  Summarize this
• arXiv cs.CVOct 15

  Do VLAs Really Follow Instructions? Diagnosing How-Level Instruction Following in Vision-Language-Action Models

  Sangwu Park, Wonjoong Kim, Yeonjun In, Chanyoung Park

  Vision-language-action (VLA) models are expected to follow instructions like their language backbones, yet prior work has focused on What-level instructions that specify the task rather than How-level instructions that specify how to carry it out. Through our diagnoses, we find that How-level instructions do not help current VLAs and lower task success. We hypothesize that pairing each training episode with a single instruction limits How-level instruction following, and show that training with segment-level enriched instructions makes actions respond to such instructions without consistently raising task success. To measure How-level instruction following beyond standard benchmarks, we introduce SIMPLER-IN, where success requires conditions given only in the instruction. It shows that the gained responsiveness does not extend to demanding or out-of-distribution How-level instructions. How-level instruction following thus remains an open challenge.

  PDF

  Summarize this
• arXiv cs.CVOct 15

  FocusOPD: Structure-Guided On-Policy Distillation for Diffusion Models

  Xinrui Lin, Shumin Wang, Suqi Song, Fan Li, Yanyong Zhang

  Multi-teacher on-policy distillation enables rectified-flow models with diffusion-transformer architectures to combine task-specific capabilities within a single student. However, matching model outputs does not guarantee that their internal representations are aligned, and it remains unclear where and when additional feature supervision is most useful. We analyze the teacher-student feature mismatch across Transformer blocks and denoising timesteps, and find that the mismatch is concentrated in deeper Transformer blocks during early denoising and persists after OPD distillation, indicating ineffective distillation. Motivated by this observation, we introduce FocusOPD, which augments the base OPD objective with token-wise directional feature alignment restricted to deep layers and early denoising steps. Across two rectified-flow backbones and multiple OPD objectives, FocusOPD improves capability transfer in compositional generation, text rendering, and preference-based evaluation. On the primary benchmark, it improves over DiffusionOPD from 0.953 to 0.967 on GenEval, from 23.797 to 23.944 on PickScore, and from 6.052 to 6.199 on LAION-Aesthetic. Ablations show that selective deep…

  PDF

  Summarize this
• arXiv cs.SEOct 15

  Beyond Confidence: Rethinking Uncertainty Calibration in Deep Code Models

  Ravishka Rathnasuriya, Wei Yang

  Deep learning models have shown significant promise in code-related tasks. While confidence calibration techniques have been proposed to improve model reliability, their effectiveness in real-world tasks with strict accuracy requirements remains uncertain. In this paper, we investigate two key questions: first, whether existing measurement metrics, including confidence scores and uncertainty metrics, are effective for guiding selective prediction; and second, whether existing calibration techniques can improve these metrics to better identify cases where model predictions are likely to succeed or fail. We conduct a systematic study on defect prediction and vulnerability detection using seven code models, evaluating thirteen uncertainty signals and three widely used post-hoc calibration methods. Our analysis reveals three major findings: (1) even strong uncertainty signals can remain poorly calibrated and provide limited separation at the high-confidence end, constraining selective prediction in practice; (2) standard post-hoc calibrators often improve calibration scores but do not consistently translate into better selective prediction behavior; and (3) commonly used calibration…

  PDF

  Summarize this
• arXiv cs.CLOct 15

  FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian Optimization

  Hao Chen, Ziyang Ling, Ronald X. Xu, Mingzhai Sun

  Large language model (LLM)-guided Bayesian optimization (BO) uses past observations to guide search, but proposed directions and their revision can remain implicit. We propose Feedback-Guided Search State (FGSS), a structured hypothesis-management interface connecting language-based guidance to observed evidence, executable parameter interventions, and comparative support updates. An LLM reflector proposes and revises hypotheses; a deterministic curator validates them and maintains identities and test records. The evolving state guides candidate construction and priorities. Instantiated on LLAMBO, FGSS-BO retains its surrogate and default expected improvement selection, with a bounded testing policy. On two retrospective protocol/media tasks with nearest-neighbor response oracles, it attains higher sample mean final best and search AUC than the matched LLAMBO baseline and evaluated non-LLM baselines. Prose-reflection and EI-only controls show mixed component effects. Six direct-training hyperparameter-optimization tasks show task-dependent transfer, strongest on diabetes SVM; exact-grid and reaction controls examine other settings. FGSS exposes hypotheses, their execution, and…

  PDF

  Summarize this
• arXiv cs.CLOct 15

  System1-Arena: Which Decisions Can Be Left to System 1?

  Tianyu Chen, Xinyang Liu, Ruyi An, Zhendong Wang, Mingyuan Zhou

  Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the OpenAI Decisions API, return probabilities over options in a single forward pass, while System-2 approaches generate reasoning steps. Which decisions can System-1 models handle, and which require generative reasoning? We introduce System1-Arena, a benchmark that gives all models the same decision requests and scores their probabilities. It contains 92k questions across 105 tasks from 268 public sources, in four groups: text classification and knowledge, applied decisions, evaluation and control, and agent and action. It also includes 138 closed-loop environments, from web shopping and SWE-bench coding control to robotics, games, and driving; in real-time mode, the world evolves while a model decides. We evaluate 30 models: 7 closed LLMs, 13 open LLMs read at the answer token, and 10 System-1 models. The largest System-1 models match or exceed fast closed LLMs in non-agentic accuracy, with better-calibrated probabilities at one-quarter of the latency. A reasoning LLM is the most accurate, at about 70x the cost of a fast LLM. In closed…

  PDF

  Summarize this
• arXiv cs.MAOct 15

  A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems

  Thi-Nhung Nguyen, Viet-Thanh Pham, Linhao Luo, Thuy-Trang Vu, Dinh Phung

  Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective performance. Decentralized approaches alleviate these bottlenecks by distributing coordination across agents, yet often leave responsibility for delegated dependencies and failure recovery unclear. To address this gap, we propose RCM, a responsibility-centered coordination mechanism that leverages commitments to couple task delegation with explicit responsibilities of the involved parties. Through recursive delegation, agents retain their upstream responsibilities while locally orchestrating downstream commitments, thereby preserving accountability across delegation chains, creating a network of local orchestration. We operationalize this mechanism locally through responsibility-constrained decision-making and a responsibility-oriented communication protocol (RCP), enabling agents to autonomously establish, manage, and terminate commitments. As agents act in parallel, their local actions continuously evolve the commitment graph, allowing global coordination to emerge and adapt toward a shared mission without centralized control.…

  PDF

  Summarize this
• arXiv cs.LGOct 15

  Representation Redistribution in Sparse Autoencoders

  Ziye Mei, Haotian Ma

  Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt transformations designed to preserve the underlying request can redistribute activity across them. A feature change observed on one transformed prompt need not recur, and even a recurring change need not affect a downstream computation. We introduce the redistribution sensitivity score (RSS), which identifies large feature responses that recur in a consistent direction, and evaluate the resulting supports on variants excluded from selection. Across 27 pretrained SAEs spanning eight language models, the tested prompt transformations produce a reproducible redistribution profile on these excluded variants. We then separate recurring representation change from signed readout contribution and decision failure. For a fixed linear readout, an exact decomposition shows how response magnitude, readout coefficients, directional alignment, and the clean margin determine downstream consequences. In two frozen safety readouts, combining RSS support erosion with the full clean margin yields recurrent failure AUROCs of 0.935 and 0.958 using median supports of 20 and 19 features, compared with 0.965…

  PDF

  Summarize this
• arXiv cs.CVOct 15

  A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation

  Songlin Liu, Linwei Chen, Li Zhang, Jun Hu, Ying Fu

  A few well-annotated datasets for land-cover semantic segmentation have recently been introduced to advance the field of earth observation technologies. However, these datasets overlook the significant diversity among geographic areas with different climates, which can greatly impact and diversify land cover. Consequently, this leads to a domain gap in remote sensing images and severe performance degradation of the segmentation models. To enhance land-cover semantic segmentation with improved generalization ability, we conducted the first investigation into the impact of climate on this task. In this paper, we present a unique large-scale Climate-Aware Satellite Images Dataset (CASID) specifically designed for domain adaptive land-cover semantic segmentation. It consists of 980 satellite images with a size of 5000 x 5000 pixels, collected from 30 different regions around Asia, covering over 24,500 square kilometers. These images are gathered from four distinct climate zones, namely temperate monsoon, subtropical monsoon, tropical monsoon, and tropical rainforest. It includes four sub-datasets/domains, each representing one of the aforementioned climate zones. This characteristic…

  PDF

  Summarize this
• arXiv cs.LGOct 15

  Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy Distillation

  Stanley Wei, Jiin Woo, Kaan Ozkara, Youngsuk Park

  On-policy distillation (OPD) has recently been introduced as a promising paradigm for continual learning, where a student policy can be supervised at the token-level. Typically, OPD is performed using a single teacher per prompt rollout (or even per training run). However, this ignores a whole other axis of flexibility that is available due to the on-policy nature - token-level teacher selection during rollouts. Building on this insight, we theoretically explore what makes a teacher and a student compatible for OPD, and leverage our findings to derive several empirical heuristics for teacher selection. In particular, our framework captures several desiderata for OPD: compatible teacher-student reasoning patterns, teacher competence, and induced student diversity. Theoretically, we categorize several types of teacher routing schemes, and we prove that under different scenarios, different routing schemes are likely to be beneficial for optimization and student diversity. We back up our findings with extensive experimental results in domains such as math, coding, kernel generation, and visual reasoning, where we find upwards of 10 percentage points of improvement on pass@$k$ when…

  PDF

  Summarize this
• arXiv cs.LGOct 15

  Not All Change Is Damage: Update-Matched Unlearning for Large Language Models

  Jie Li, Youming Tao, Bowei He, Meng Ding

  Unlearning aims to remove selected knowledge from large language models to mitigate privacy and safety risks while preserving useful capabilities. For models that continue to be fine-tuned after release, this goal is insufficient: they must also resist relearning the deleted knowledge while preserving plasticity, the ability to learn new tasks. Existing defenses train against simulated relearning while trying to preserve useful capabilities, but low relearning alone cannot distinguish selective resistance from a general loss of plasticity. Evaluating preservation after an update requires deciding what the updated model should remain close to. A pre-update reference penalizes useful changes induced by the update simply because they depart from earlier outputs. We therefore formulate the reference-timing hypothesis that, at comparable target suppression, an update-matched reference better preserves plasticity than a pre-update one. To test and address this hypothesis, we propose Update-Matched Unlearning (UMU), which applies the same simulated relearning update to the defended model and to an undefended reference initialized from the same unlearned model, and uses new-task learning…

  PDF

  Summarize this
• arXiv cs.CLOct 15

  What Should We Remove? Evaluating the Reliability and Costs of RLVR Data Decontamination

  Esther Xin

  Reinforcement learning with verifiable rewards (RLVR) math corpora are routinely screened for benchmark overlap, but the reliability and data-loss costs of cleaning policies remain underexamined. We audit sixteen open RLVR math corpora comprising 1,673,514 corpus-specific training items against six benchmarks containing 1,949 questions. We evaluate eight policies based on exact, lexical, and semantic matching using 594 independently and blindly dual-reviewed training-benchmark pairs. Calibration and held-out sets have disjoint benchmark questions and training-example families. A separate review of all 83 candidate matches for 80 sampled training items measures item-level false removal. At cosine threshold 0.80, 52 of 59 sampled removals (88%) were confirmed false removals; this is not a demonstrated population rate. No semantic threshold in our preregistered grid (0.80-0.98) meets the 90% conservative-precision target on calibration. The existing judge-adjudicated policy achieves 98.1% resolved precision and 98.2% candidate-frame recall on held-out corpora. It has zero confirmed false removals among six sampled removals, with one unresolved case; this does not establish zero…

  PDF

  Summarize this

• Federated learning43+2.4%
• Forecasting time72−10.0%
• Adversarial training43−10.4%
• Machine learned interatomic45−18.2%
• Anomaly detectors29−19.4%
• Classifier & causal discovery78−19.6%
• Frontier LLMs404−20.0%
• Agents452−20.4%