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.CVComputer visionOct 15▲ 2

  ARC-SORT: Adaptive, Robust, Compensated Multi-Object Tracking with Interacting Multiple Models

  Girish Kumar Adari

  Multi-object tracking in sports broadcasts is hard for two reasons: athletes move fast and change direction abruptly, and the camera pans and zooms at the same time. We present ARC-SORT (Adaptive, Robust, Compensated SORT), a tracking-by-detection tracker that trains nothing and runs in real time. Its design rule: the tracker measures its own uncertainty, and that measurement decides how it acts. An Interacting Multiple Model (IMM) Kalman filter gives every track a predictive covariance, and we turn it into a per-track search region: the less reliable the motion prediction, the larger the region in which a detection may match (uncertainty-adaptive Expansion IoU, EIoU). On identical inputs, this continuous coupling is what matters: the same covariance used as a hard Mahalanobis gate hurts at every threshold we swept, and richer covariance summaries add nothing measurable. When two tracks cross, the assignment cost itself reports whether the decision was close. ARC-SORT keeps such pairs under review and applies at most one corrective identity swap once post-crossing appearance evidence shows the first decision was wrong; this adds +1.0 HOTA (higher order tracking accuracy) on both…

  AI50CodePDF
• arXiv cs.CLEvalsOct 15

  Knowledge That Is Linear Before Fine-Tuning Generalizes After It

  Faridoun Mehri, Hinrich Schütze

  Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond their own recall, from inert facts, which can be recalled but do not support such generalization in a given task. We study this distinction by constructing new relations from existing ones. Take the relation that maps a place to its continent (Paris -> Europe) and assign each of its answers an arbitrary new label (Europe -> crab, Asia -> zebra). The new relation then maps Paris -> crab. We fine-tune the model on the new relation for a subset of subjects, without telling it the original relation or the relabeling rule, and test whether it assigns the corresponding labels to held-out subjects that share an answer in the original relation. Having learned Paris -> crab, does it answer Munich -> crab? Across eleven language models and 70 relations, how linearly readable the original relation is in pretrained representations strongly predicts this generalization. Within each model, the two correlate across relations at Pearson r = 0.87 to 0.92. This association persists when controlling, separately and jointly, for the number of fine-tuning…

  AITraining & fine-tuning60PDF
• arXiv cs.AIOct 15

  Testing the Planning Claims of LLM-Based Agents against Formal Semantics

  Oriol Miro-Lopez-Feliu, Oscar Miró López-Feliu, Victor Gimenez-Abalos, Javier Vazquez-Salceda, Victor Carballo Araruna +1

  LLM-based agents are increasingly credited with the competences of practical reasoning: planning, monitoring, and correcting their own actions. Their success is attributed to the prompting strategies and agent architectures built around the model, such as chain-of-thought, search-based prompting, self-refinement, reflection, critics and tool-using loops. Yet these claims are usually supported by end-to-end success rates, which show only whether a task was completed, or by LLM judges, which are not verifiers. We test LLM planning against formal semantics. Tasks are posed in natural language, but each is grounded in a hidden PDDL model that decides whether every action is applicable, whether the goal is reached, and whether a plan exists at all. Across five domains (two of them new, all released with the paper), four models, six prompting strategies and three agent architectures, the best configuration solves 78% of the solvable tasks offline but only 40% online, where agents mostly act without inspecting the state. Unsolvable tasks are recognised in under 10% of episodes, and heavier prompting strategies use 5 to 22 times as many tokens as direct prompting with no clear gain. In…

  PDF
• arXiv cs.CLEvalsOct 15

  AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions

  Alexey A. Bokov, Ivan I. Panin, Nikolay B. Nechaev, Mikhail Yu. Valkov, Valeria Yu. Chernina +8

  Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clinically coherent, actionable, and safe. We developed a multidimensional benchmark using 300 diagnostically resolved NEJM--MedQA cases: 110 for physician reference ratings and Judge calibration and 190 for held-out evaluation. Eight single-model pipelines generated independent role-specific opinions and interactive-consilium reports under free-form and structured clinical-reasoning conditions. A physician-calibrated LLM Judge evaluated 3,040 final reports and the corresponding structured primary-role outputs. Model identity separated report quality more strongly than response format. Structured final reports had higher overall mean scores in seven of eight model pipelines, with their clearest advantage in management (2.740 vs. 2.436). Compared with the structured pre-consilium primary-role opinion, the complete structured synthesis had higher pooled scores across all five shared criteria, with the largest increases in problem prioritization, factual grounding, and reasoning coherence. GPT-5.6-Sol led every evaluated component and…

  AI70PDF
• arXiv cs.AIRAGOct 15

  Private Retrieval Augmented Generation via Random Projection

  Dixi Yao, Tahseen Rabbani, Tian Li

  Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce privacy risks by leaking sensitive information from the retrieval datastore. We propose a simple method to preserve datastore privacy in RAG systems via random projection. By applying the same projection to both datastore embeddings and query embeddings, our method provably preserves semantic similarity between queries and retrieved items while substantially mitigating data extraction attacks. Across multiple RAG architectures and datasets, we show that this lightweight approach achieves superior retrieval and generation performance compared to prior methods which leverage formal differential privacy (DP) guarantees, while exhibiting comparable empirical privacy under strong attack models. Our results for the first time suggest that random projection can serve as a competitive and practical baseline for privacy-preserving RAG systems.

  AIAI safety80PDF
• arXiv cs.SDOct 15

  Backward Compatibility in Zero-Bit Neural Audio Watermarking

  Admir Krnić, Kosta Pavlović, Petar Nedić, Željko Bolević, Slavko Kovačević +1

  Neural watermarking systems are typically trained as tightly coupled embedder-detector pairs and implicitly assume static deployment. In real-world deployments, embedders and detectors are frequently updated and selectively decoupled for security and versioning purposes, which can break detection in previously embedded content and, more critically, increase false-positive rates on embedders that a given detector is intentionally not intended to recognize. In this paper the concept of backward compatibility in zero-bit audio watermarking is formalized. A training framework is proposed that pairs a new detector with a sequence of frozen legacy embedders (its legacy chain), using a performance-weighted sampling strategy so that the detector retains accuracy across all earlier versions. This coupling, while necessary for backward compatibility, is shown to induce an embedder-collapse effect that catastrophically degrades the true negative rate (TNR) against out-of-chain embedders. To counteract this, a Angular Diversity Loss (ADL) is introduced that explicitly forces each new embedder to occupy a distinct region of the output space. The combined approach restores near-perfect TNR…

  AI20PDF
• arXiv cs.CVComputer visionOct 15

  Grounded Human-Attributed Description and Activity Recognition in Videos

  Jay N. Paranjape, Jurijs Nazarovs, Rohan Sarkar, Yue Guo, Lipeng Ke +3

  Understanding characteristics and activities of individuals in complex multi-person environments is crucial for real-world applications. However, existing datasets often simplify this problem to grounded group activity recognition, single-person activity recognition, or close-set activity recognition, thus limiting the generalizability of models trained on these datasets. In this work, we introduce the task of Grounded Human-Attributed Description and Activity Recognition (GHADAR), which involves describing the characteristics and activity descriptions of \textbf{every} person in a video, provided the location of the person in the video, which is more practical for real-world applications. To facilitate this, we introduce a new dataset derived from AVA-Actions by generating open-set captions for the person description and activity. In addition, we propose a novel method to effectively utilize the information contained in grounding during training by constraining the cross-attention masks during training in VLMs to improve performance for this task. Our experiments show that our method outperforms SOTA VLMs on this task. Finally, we demonstrate the limitations of existing…

  AIMultimodal60PDF
• arXiv cs.CLCode modelsOct 15

  Multi-Target Few-Shot Prompting with Diffusion Language Models

  Anton Xue, Alan Li, Rahul Saha

  Few-shot prompting is useful when instructions and rewards are hard to specify. One such application is editing by example, where a demonstrated formatting change or API migration may need to be applied across multiple sites. However, such edits often depend on both left and right context, making generation with causal autoregressive models awkward. We therefore introduce multi-target few-shot prompting with diffusion language models, where examples guide the infilling of multiple masked regions within a shared canvas. To address the known challenge of reliably following demonstrations in few-shot prompting, we further leverage selective masking of the canvas to derive a likelihood-ratio reward that favors example-supported infills. Across few-shot prompting benchmarks and software refactoring case studies, we find that demonstrations improve infilling accuracy, with example guidance yielding further gains in several settings.

  AIMultimodal70PDF
• arXiv cs.LGTraining & fine-tuningOct 15

  Towards Continual Learning: Mitigating Forgetting With Subspace Tuning

  Arnav Chavan, Kusha Sareen, Rishabh Tiwari, Abhranil Chandra, Johan Obando-Ceron +4

  Large language models (LLMs) acquire new skills through fine-tuning, but it can destroy capabilities they already have: catastrophic forgetting remains a central obstacle to continual learning in LLMs. Recent works connect forgetting to how far, and along which directions, fine-tuning moves the weights. On-policy methods such as reinforcement learning and on-policy distillation avoid updating the principal singular directions of weight matrices and thus forget less. In contrast, SFT concentrates updates along these directions and is susceptible to catastrophic forgetting. In this work, we introduce Subspace Tuning (SST), which restricts each weight update to the bottom singular subspace, eliminating changes along the principal directions. SST is optimizer-agnostic and composes well with fine-tuning recipes including SFT and self-distillation. SST combines tight subspace protection, dense gradient estimation, and a simple refresh mechanism, enabling stronger learning than prior orthogonal fine-tuning methods. With these mechanisms, protecting as much as 99\% of the weight subspace substantially improves retention while preserving strong target-task performance. This behavior…

  AI80PDF
• arXiv cs.CLOct 15

  From Parallels to Divergence: Language Models' Learning of Action Nominal Constructions

  Iskar Deng, Shane Steinert-Threlkeld

  Action nominal constructions (ANCs) express events in nominal form, with their argument marking following patterns found in clauses or ordinary noun phrases. In this paper, we investigate how different grammatical configurations affect language models' learning of ANCs and related constructions, and how these learning preferences compare with typological distributions in natural languages. We use a grammar-engineered method for synthetic corpus construction that combines shared semantic input from natural corpora with computational grammars. We construct 96 target languages varying in clause word order, noun-phrase word order, alignment, complement system, and ANC strategy. For each language, we train GPT-2-small models from scratch and evaluate them using targeted minimal pairs covering 34 grammatical phenomena. The results show typological parallels in basic clause configurations but divergences in complement systems and ANC strategies, with models also learning combinations rare or unattested in natural languages. This partial alignment suggests that natural language distributions may reflect both general learning pressures and functional demands not fully captured by model…

  PDF
• arXiv cs.LGAI safetyOct 15

  CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty

  Yuan-Chen Chang, Niklas Herbster, Gauthier Gidel, Tommaso Tosato

  Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest behaviour, such as outputting claims that contradict some knowledge or are not supported by what is accessible in context. We introduce Continuous Adversarial Training for Consistent Honesty (CATCH), inspired by a method originally developed to robustly refuse harmful queries. CATCH trains the model towards an honest answer and away from a dishonest one while maintaining the model's capabilities. We evaluate two architectures (Llama-3.3-70B-Instruct and Qwen3-3.6-27B). We show that trained with only hundreds of targets built from self-reporting scenarios, CATCH learns an honest behaviour that robustly generalizes and transfers across distinct benchmarks. It consistently reduces dishonesty under pressure on MASK, increases confessions in the multi-agent game of Among Us, and improves the discovery rates of the model's hidden behaviours in AuditBench. We show that CATCH outperforms prompting and supervised fine-tuning in improving honesty, and it is on par with state-of-the-art honesty activation steering. However,…

  AI70PDF
• arXiv cs.AITraining & fine-tuningOct 15

  EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search

  Hanane Nour Moussa, Doeun Lee, Sachin Kumar

  Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narrow the set of solutions the model can produce. Several approaches have attempted to address this behavior-sharpening effect, but they often optimize metrics that do not reflect the diversity of correct solutions. Ideally, we want a model that can produce multiple good solutions, not only a single reliable one. We propose EliteReplay, a post-training recipe that pairs GRPO with an "elite" archive built by quality-diversity search. Before training, we use the frozen base model to collect solutions that span distinct approaches; during training, GRPO is combined with a replay loss on this archive. The result is a post-trained model that improves accuracy while preserving more of the base model's solution diversity. On multiple text-to-SQL tasks, EliteReplay achieves a higher pass@128 than all baselines, producing up to 77% more distinct correct strategies than the strongest baselines. It preserves most of the base model's correct strategies, outperforming existing methods in strategy retention. This diversity translates into practical…

  AI70PDF
• arXiv cs.AIAgentsOct 15

  Improving Environment-Agnostic Agents: The Role of Scaffolding

  Sergey Rodionov

  Agents built on stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We investigate why this advantage persists and whether an environment-agnostic agent can be improved without environment-specific engineering. We evaluate a Codex-based agent in two nearly identical prompt variants on ARC-AGI-3, AGI Maze, and Terminal-Bench. Each variant is deployed with unchanged code, prompts, and general-purpose tools across environments, receiving environment-specific information as input. Changing only an instruction to encourage reporting difficulties and returning control for automatic continuation improves mean scores on both ARC-AGI-3 and AGI Maze, while Terminal-Bench shows small, mixed changes. Yet the general agent remains below an ARC-AGI-3-specific reference, including with GPT-5.6-sol. The reference prescribes organization and control rather than supplying new game rules or solutions. To investigate this gap, we transfer reset decisions to a scripted controller that follows a convention already given to the agent. This small change recovers part of the specialized agent's advantage. A…

  AI60PDF
• arXiv cs.LGOct 15

  Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems

  Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli

  We study rational synthesis for stochastic multi-agent systems with unknown dynamics, where each agent is equipped with its own probabilistic temporal objective specified using Probabilistic Linear Temporal Logic on Finite Traces ($\mathsf{PLTL}_f}$). We impose solution concepts (e.g., Nash equilibrium, subgame-perfect equilibrium) as constraints on the joint strategy profile, using payoffs derived from each agent's probability of satisfying its temporal objective. In particular, we formulate per-agent rational synthesis as finding a strategy profile -- if one exists -- such that (i) the designated agent's probabilistic temporal constraint is satisfied, and (ii) the profile represents a stable solution under a chosen solution concept. We give conditional convergence guarantees for tabular Nash-Q learning, certify satisfaction with simultaneous finite-sample confidence bounds, and assess strategic stability with approximate best-response checking. Our approach operates in a stochastic \emph{Multi-Agent Reinforcement Learning} (MARL) environment, where model-free learning algorithms attempt to attain extremal satisfaction probabilities for temporal objectives automatically compiled…

  AI20PDF
• arXiv cs.ROAgentsOct 15

  Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards

  Helena Merker, Nick Walker, Andreea Bobu

  Reward learning typically assumes the human's input covers everything that matters for the task. In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others. Prior work has shown how the robot can identify which features were poorly supervised directly from its teaching data. But the current solution is to ask the human to try again, putting the burden on someone who already struggled to convey those features. We propose shifting this burden to the robot. Our key insight is that the same information that tells the robot what it doesn't know can help it ask better questions. Preference queries offer a low-effort channel for resolving this uncertainty, but only if the robot knows where to direct them and the human knows what to attend to when answering. We act on this insight in two ways: we build an informed prior that targets preference queries at the features that need resolving, and we accompany each query with an explanation that focuses the human's attention on exactly those features. In simulation, the informed prior beats the standard active preference learning baseline by up to…

  AI60PDF
• arXiv cs.CVImage & video generationOct 15▲ 23

  Routing Policy Optimization for Online Diffusion Reinforcement Learning

  Qiuhong Shen, Yiding Yang, Yuxin Zhang, Xinwei Huang, Minxuan Lin +6

  Reinforcement learning can align visual generators with reward signals beyond their pretraining objectives, but existing score-function methods typically introduce stochasticity by perturbing the reverse denoising trajectory, leading to costly rollout-based optimization. We instead ask whether stochastic exploration can be introduced inside the generator while preserving its original sampler. Routing Policy Optimization (RPO) answers this question by turning attention routing into a stochastic exploration action. At a few selected denoising levels, each query block keeps its own block and samples further key blocks in proportion to the generator's native attention mass, or keeps dense attention. The sampled route perturbs the velocity of that transition, and a Gaussian likelihood around the dense velocity scores the perturbation with a score-function objective. RPO further uses a controlled two-rollout estimator: two rollouts share the same prompt, initial latent, routed denoising levels, and dense anchor layers, differing only in their sampled attention routes. Their reward difference provides an advantage signal for the routed transitions. Because the likelihood differentiates…

  AI60PDF
• arXiv cs.AIAgentsOct 15▲ 8

  LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents

  Qingni Wang, Changdae Oh, Yuzhe Yang, Sharon Li, Jiachen Yang +2

  Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails. Weak-to-strong escalation offers a middle ground where a weak agent acts by default and hands control to a strong one only when needed. The core challenge is deciding when to escalate, which requires an uncertainty signal cheap enough to check at every step. However, even after handoff, the strong agent can still get lost, but a black-box API that the strong agent is usually served exposes no internals to monitor. To this end, we propose LEASH, a training-free framework that unleashes the strong agent only when the weak agent's latent uncertainty signals it is needed, and keeps it on a leash afterward. LEASH has three layers: (1) initial task uncertainty for early routing, (2) step-level uncertainty for runtime escalation, and, after handoff, (3) a shadow observer for continued oversight of the strong black-box agent. Here, we use latent uncertainty as a fuel for all three layers. Specifically, we compare the weak model's hidden states with those from its past successful and failed trajectories, and a state that…

  AI80PDF
• arXiv cs.LGOct 15

  Progressive Misalignment Can Emerge from Benign Recursive Self-Distillation

  Karim Abdel Sadek, Federico Di Gennaro, Fanny Yang

  Training models on their own outputs has attracted widespread attention as a possible route to advance AI capabilities. One prominent approach is self-distillation, where a model is trained to match the token-level predictions it would have produced when given access to additional context, such as a cue, feedback, or instruction. However, the safety properties of this training procedure are poorly understood. In this paper, we present a surprising safety failure of recursive self-distillation, where each self-distilled model becomes the teacher for the next round of training. We observe that when a safe model is recursively self-distilled on its own (safe) generations while receiving an additional non-harmful cue, it becomes increasingly misaligned across a diverse set of harmful queries; we call this Progressive Misalignment. We show this failure mode in both the Qwen3 and Phi-4 model families on SORRY-Bench and StrongREJECT. Progressive misalignment also occurs in a more realistic setup, where the fixed cue is replaced by feedback from a simulated user with benign intent. Using a gradient-based method, we are also able to find benign prompts that lead to progressive…

  PDF
• arXiv cs.AIOct 15▲ 4

  Harness-Delta Attribution: Dissecting Gains From Harness Evolution

  Wenxuan Ding, Qin Lu, Changlong Yu, Sha Li, Shuowei Jin +3

  Harness evolution automatically optimizes the prompts, skills, tools, and orchestration code around a fixed-weight model, offering a way to improve agentic systems without updating model weights. The agent harness is iteratively optimized to achieve higher performance on the search set. But how much of this gain reflects benchmark-specific overfitting or additional inference-time compute, and how much may generalize beyond the search set? In this work, we introduce Harness-Delta Attribution (HDA), an evaluation protocol that dissects an evolution gain into artifact-driven overfitting, gains explained by test-time scaling, and the remainder, which gives an upper bound on residual generalizable improvement. We apply HDA to 11 executor models and three harness-evolution frameworks across math, coding, creativity, and agentic tasks. In 21 of these settings that show statistically significant search-set gains, we find that a large share of the improvement is explained by overfitting or test-time scaling. Specifically, among these 21 settings, overfitting and test-time scaling account for 54% and 14% of the gain on average; their combined share exceeds 50% in 14 settings. The residual…

  Code
• arXiv cs.CVMultimodalOct 15▲ 354

  MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

  Luozheng Qin, Yuhan Zhu, Changhai Zhou, Qian Qiao, Jun Gao +7

  Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation holds, how far an object is, or where to place it. Vision-language models (VLMs) produce these answers by free-form text generation, paying for autoregressive decoding and answer parsing even though the output space is compact: one of a few options, a scalar, or a 2D point. In light of this, we introduce MJev-Spatial, a System 1 multimodal decision model that tackles all three types of spatial understanding tasks within a unified classification framework. Specifically, MJev-Spatial treats each candidate as a class and scores it using the backbone's pretrained query and key projections, without adding parameters. The candidates are the given options for choice tasks, or value bins and image regions refined through coarse-to-fine classification for numerical and point prediction, respectively. At inference, each classification decision takes a single forward pass and generates no answer tokens. To train on heterogeneous spatial data efficiently, we supervise all coarse-to-fine stages jointly with teacher forcing in one…

  AI70Code

• Developer tooling2+100.0%
• Training & fine-tuning37+37.0%
• Federated learning49+25.6%
• AI safety25+13.6%
• Forecasting time84+6.3%
• Adversarial training51+4.1%
• Computer vision26+4.0%
• Quantum machine learning240.0%