Research

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

  Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in embodied control loops1 paper raises it · 0 address it

  High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

  Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

  Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

• Federated learning50+31.6%
• Agents530+2.1%
• Quantum machine learning240.0%
• Character recognition OCR170.0%
• Sensing communication150.0%
• Frontier LLMs448−7.4%
• Forecasting time78−11.4%
• Image segmentation184−11.5%

• arXiv cs.CLOct 19

  MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language Models

  Zhengao Li, Chuxu Zhang, Yushun Dong

  Knowledge acquisition from black-box large language models (LLMs) offers a practical approach to adapting smaller student models. However, many existing methods rely on predefined queries or student feedback to guide acquisition, leaving autonomous expansion of knowledge targets an important challenge. We propose \textbf{MapSteal}, a student-independent framework for structured recursive knowledge acquisition. Starting from a small set of initial roots, MapSteal represents acquisition targets using structured states and recursively expands them through teacher-proposed directions. Question realization, proposal admission, and deduplication constrain the acquisition process, while root-aware scheduling organizes exploration under a fixed QA budget. The resulting question--answer pairs are used to adapt student models without requiring student feedback during acquisition. Experiments with Qwen3.5 students at 2B, 4B, and 9B scales show competitive downstream performance across six medical and cybersecurity benchmarks. On the 4B medical evaluation, Full MapSteal improves average accuracy by 1.17 percentage points over a simplified recursive acquisition variant. Cross-domain…

  PDF
• arXiv cs.LGOct 19

  Zephyrus-R1: Agentic Reinforcement Learning for Weather Reporting

  Fengfei Yu, Marshall Fisher, Isadora White, Sumanth Varambally, Yasaman Jafari +11

  Reinforcement learning (RL) has emerged as a key method for training AI models in scientific applications, but RL remains difficult when outputs cannot easily be verified against a known ground-truth answer. Natural-language weather forecast reports are one such domain: they translate atmospheric data into assessments of weather evolution, hazards, and uncertainty for both the general public and key decision-makers. Unlike numerical weather-analysis questions, they admit many valid outputs, which limits deterministic verification. To address this, we develop Zephyrus-R1, a practical framework for RL on scientific weather forecast reporting. We focus on three key components of the agentic RL pipeline: reward design, curriculum learning, and an analysis of human-expert alignment. To encourage both report legibility and factual accuracy, we design a reward function that combines a meteorological rubric with bidirectional claim entailment, both evaluated against National Weather Service reference reports. Our framework optimizes this reward in a simulated tool-calling environment, enabling vision-language agents to gather and analyze forecast evidence across regions and lead times…

  PDF
• arXiv cs.CVOct 19

  Recurrent Vision Transformers for Event-Based Spacecraft Pose Estimation Under Slow Relative Motions

  Sofia McLeod, Mohsi Jawaid, Carl Seubert, Tat-Jun Chin

  Vision-based object pose estimation is vital for conducting spacecraft rendezvous and proximity operations (RPO). Recent research has demonstrated the robustness of event cameras against the harsh lighting conditions that often occur in orbit, thanks to the extremely high dynamic range of event sensors. However, event-based spacecraft pose estimation (EBSPE) suffers when the relative motion between the chaser and target is slow, since the event rate drops significantly, leading to data with low signal-to-noise ratio. Unfortunately, for safety reasons, real RPO trajectories often involve slow relative motions (e.g., down to 1 mm/s), and operating under low illumination exacerbates the problem. Addressing slow relative motions is thus crucial to raise the practicality of EBSPE. To this end, we propose using recurrent vision transformers (RVT) for EBSPE. The key idea is to exploit recurrent memory to capture longer-term information across sparse event streams, and to learn the temporal attention span from full trajectories rather than fixing the time window. We developed an RVT-based heatmap regressor to produce 2D-3D correspondences for pose estimation, which was validated on real…

  PDF
• arXiv cs.LGOct 19

  Weighted State Souping for Efficient Long-Context Retrieval

  William L. Tong, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Cengiz Pehlevan +1

  State space models (SSMs) combine fast inference and fixed state size with competitive language-modeling performance. Recently, state souping has been proposed as a procedure whereby an SSM independently encodes chunks of tokens like documents, tool definitions, or memory records. The resulting state encodings may be cached and recombined to cheaply construct a context for downstream queries. However, both state souping and vanilla SSMs deteriorate on long, crowded contexts, limiting their utility for long-horizon domains. To address this issue, we propose weighted state souping, a simple method that learns query-dependent weights for composing cached states. The resulting models improve long-context performance substantially across both single- and multi-hop document question answering, needle-in-a-haystack retrieval, variable tracking, and tool use. Our method can be further adapted into an efficient sparse variant, yielding near-constant encoding cost with respect to context length while preserving (and sometimes improving) performance. We also present simple theoretical arguments that illustrate why souping works and when it may fail, and discuss informally the advantages of…

  PDF
• arXiv cs.CVOct 19

  CheXFuse: Guided Differential Joint Attention Fusion for Robust Multimodal Chest X-Ray Classification in Data-Scarce Medical Settings

  Muntaqim Ahmed Raju, Priyanka Siddappa, Md Shifat Haider Al Amin, Ruizhe Ma, Md Ripon Ahammed

  A central challenge in multimodal learning is how to fuse modalities that differ substantially in predictive strength. When one modality provides a much stronger representation than another, indiscriminate cross-modal interaction can introduce weak, redundant, or unstable signals, limiting or even degrading performance relative to the strongest unimodal representation. To address this problem, we propose CheXFuse, a multimodal fusion framework based on Guided Differential Joint Attention (GuDJA). CheXFuse combines image and text token representations within a joint multimodal sequence, where learned token guidance emphasizes informative representations and differential attention reduces less useful attention responses. We evaluate CheXFuse on the Indiana University (IU) Chest X-ray dataset, using binary (normal vs. abnormal) classification as the downstream task. Experiments are conducted under both original-report and masked-report settings, with the latter serving as a controlled stress test under reduced textual informativeness. CheXFuse with GuDJA achieves the strongest mean overall performance across the evaluated baselines and ablations, reaching 95.73% accuracy, 95.79%…

  PDF
• arXiv cs.SEOct 19

  Better Specifications, Better Code: Fine-Tuning LLMs for Behavioral Contract Generation

  Brhane Team, Tiantian Yang, Nikta Akbarpour, Simone Bartucci, Francesco Calimeri +1

  Large language models (LLMs) demonstrate strong code-generation capabilities but often struggle with functional correctness due to implicit or ambiguous behavioral requirements. We present CG2, a contract-guided code generation framework that translates natural-language tasks into structured behavioral contracts specifying interfaces, preconditions, postconditions, and invariants. CG2 fine-tunes an LLM to generate these contracts and introduces an iterative semantic validation and repair process to identify and correct incomplete, inconsistent, or incorrect specifications before guiding an unchanged downstream code-generation model. We evaluate CG2 on 1,007 held-out tasks using five code LLMs: DeepSeek-Coder-V2-Lite-Instruct, Ministral-3-14B-Instruct-2512, Qwen2.5-Coder-14B-Instruct, Qwen2.5-Coder-32B-Instruct, and Qwen3.5-27B. Results show that CG2 consistently improves pass@1 over direct code generation by 1.49-3.27 percentage points (7.58%-22.45% relative improvement) and over contract guidance without fine-tuning by 1.19-2.38 percentage points (7.04%-14.65% relative improvement). Manual analysis further reveals that semantically correct contracts are associated with higher…

  PDF
• arXiv cs.LGOct 19

  Curriculum Learning Teaches LLMs Long-Horizon Implicit Reasoning, Up To A Limit

  Jimson Huang, Maxwell Nickell, Ruowang Zhang, Abulhair Saparov

  LLMs "reason" by externalizing intermediate steps as tokens through chain-of-thought (CoT), yet even frontier reasoning models hit abrupt performance cliffs on long-horizon tasks. Implicit reasoning (reasoning within a single forward pass) is useful during CoT generation, as the model can "search ahead" to decide the correct next move without explicit search. Models with weak implicit reasoning are more likely to commit to wrong paths and must attempt to recover via backtracking, while models with strong implicit reasoning identify the correct proof strategy directly, shortening the CoT. However, prior work shows LLMs struggle to reason implicitly beyond shallow depths, with no relief from scale. We investigate whether curriculum learning can extend this depth by fine-tuning on examples with progressively increasing vocabulary size and lookahead (the number of steps a model must search ahead to identify the correct next move). At matched compute, curriculum-trained models achieve lookaheads where no-curriculum training fails. Qwen3-0.6B reaches 98% accuracy on problems with lookahead up to 256 with curriculum, compared to 45% without. However, progress slows as fine-tuning…

  PDF
• arXiv cs.LGOct 19

  Safety Offset Learning: When Benign Fine-Tuning Misaligns LLMs

  Jesson Wang, Zhanhao Hu, Minghao Lin, Yuchen Wu, Aylin Caliskan +1

  Safety risks from fine-tuning are commonly characterized by the harmfulness of the training data:harmful fine-tuning is considered dangerous, while benign fine-tuning is often assumed to preservealignment. We argue that this view misses a more fundamental factor-the behavioral transition inducedby supervision. Harmful fine-tuning and safety-degrading benign fine-tuning can both be understoodas learning the same refusal-to-compliance transition, but on different data distributions. We studywhether such a transition learned on benign inputs can generalize to harmful requests. We constructbenign examples that an aligned model initially tends to refuse and pair them with their originalharmless responses, creating a discrepancy between the model's initial refusal and the supervisedanswer. Fine-tuning on these examples increases harmful compliance, but only when two conditionshold together: the discrepancy is large enough, and it cannot be resolved through a narrow surface-levelshortcut. With the induced discrepancy matched, varying only whether it is localized changes harmfulcompliance by an order of magnitude; raising the discrepancy does not help while a shortcut remainsavailable,…

  PDF
• arXiv cs.LGOct 19

  PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization

  Xinyi Chen, Jiahuan Pang, Titus Chima, Paul Weng, Wendong Wang

  Solubility depends on intermolecular interactions between solutes and solvents, and is central to drug discovery, chemical and materials process engineering. Its prediction requires out-of-distribution (OOD) generalization to unseen solutes, solvents, and solvent mixtures, where supervised methods suffer from data scarcity, and existing self-supervised methods do not explicitly learn chemically meaningful relations. Learning chemically meaningful relational information without labels can alleviate data scarcity and improve OOD generalization, but remains challenging. We introduce Prior Relational Information for Self-supervised Modeling (PRISM) and apply it to solubility OOD generalization. PRISM is a label-free pretraining framework that converts expert-defined chemical priors into relational teachers. For solubility prediction, it trains four encoders to preserve the population-level relational information from priors capturing hydrophobic, electrostatic, polarizability, and substructural effects, using Kullback-Leibler (KL) divergence to match distance-based neighborhood distributions during pretraining. Across scaffold, solute, and solvent OOD settings, PRISM matches or…

  PDF
• arXiv cs.LGOct 19

  Adversarial Post-Training of Foundation Models for High-Frequency Trading

  Alexandre Bismuth, Kang Li, Aramis Marti-Shahandeh, Valentin Mohl, Jakob Foerster +1

  While autoregressive foundation models trained on limit order book (LOB) data show state-of-the-art performance for market simulation, pre-training with cross-entropy neither penalizes the compounding of sampling errors over free-running rollouts nor targets desired market properties. We introduce a post-training method for LOB foundation models using a Wasserstein generative adversarial network (GAN) objective. A critic, trained online on rollouts through the true, non-differentiable matching engine, guides updates from evolution strategies over rank-4 LoRA perturbations of the pre-trained generator, under a KL trust region. For efficiency, we use EGGROLL (Evolution Guided GeneRal Optimisation via Low-rank Learning), a memory-efficient variant of evolution strategies. On a held-out panel, adversarial post-training improves LOB-Bench realism by 17.6% (WS-21) and 17.0% (Mean-$L_1$), while selection-matched random-perturbation and compute-matched continued-pre-training controls yield no improvement. Post-training is thus a necessary stage that more pre-training does not replace. Per-position divergence measurements show that it slows error accumulation over 500-message rollouts…

  PDF
• arXiv econ.GNOct 19

  When Better Opportunities Backfire: Service Worker Responses to Parallel AI Deployment in Customer Acquisition

  Xinyu Fu, Shulong Luo, Narayan Ramasubbu, Peng Shen, Xincheng Wang +1

  As AI voice agents get deployed in high-volume contact centers, firms can route low-intent leads to AI and allocate high-intent leads to human workers. Drawing on sequential search theory, we posit that AI-induced task allocation reshapes work, enriching opportunities facing human workers but also raising their reservation value for continuing with the lead in hand, making them less willing to persist. We study the effects of an AI voice-agent deployment at a Chinese online health-insurance brokerage using more than a half million customer outreach records surrounding the rollout. Adopting a regression-discontinuity-in-time design, we trace how worker behavior changes across the workday. Results show that the enrichment of human-facing opportunities concentrates early in the workday, raising the probability that a call is a high-intent lead by about 23 percentage points on the first three calls and fading to zero later. However, customer acquisition by human workers declines precisely where the enrichment is greatest, falling about 5 percentage points on the first three calls and flattening over the day. Consistent with the theorized reservation value mechanism, workers…

  PDF
• arXiv cs.SEOct 19

  Step-Aligned Script Generation with Verification and Recovery for Web Automation Testing

  Hridya Dhulipala, Xiaokai Rong, Aashish Yadavally, Tien N. Nguyen

  Automated generation of end-to-end web tests remains costly: developers must identify stable selectors, encode multi-step workflows, attach assertions, and maintain scripts as interfaces evolve. Recent LLM-based web agents can complete natural-language tasks in a live browser session, but task completion is not the same as producing a test-ware artifact - code that is executable, replay-able from a reset state, inspectable by developers, and tied to an oracle. We present TESSARA, an adaptive test-script generation framework that converts natural-language test intent into Playwright scripts consisting of executable interaction code, goal-state assertions, and step-level provenance linking each step to its generated code fragment, selector evidence, execution outcome, and repair history. TESSARA grounds each planned step via Step-Aligned Scripting (SAS), enabling fine-grained failure localization, selective regeneration of failing suffixes, and reversibility-aware backtracking that avoids undoing likely commit points (e.g., form submissions). A three-level verification pipeline (syntactic, execution, and semantic/oracle), detects and repairs malformed code, interaction failures,…

  PDF
• arXiv cs.LGOct 19

  Text Dominance in Paralinguistic Conflict: Tracing Suppression Through Audio LLM Circuits

  Ankur Banerjee, Vishnu Guntakala, Danity Pike, Advay Roongta, Kevin Yang +1

  Audio LLMs deployed in settings such as crisis hotlines and customer support are only useful beyond speech-to-text pipelines if they use acoustic cues rather than the transcript alone. We test whether they prioritise transcript content over paralinguistic cues (emotion, speaker identity, sarcasm) and trace the mechanism when they do. Across six audio LLMs under LISTEN-style conflict conditions, the mean text-dominance rate on mismatched text+audio items is 0.78 (0.86 excluding sarcasm). In the most text-dominant screened model, probing shows speaker identity remains linearly decodable at ceiling at the language model's input, so the failure is not perceptual. Back-patching, reported to repair lexical text dominance, has no measurable effect here; but it also fails on its own source task in our replication (n=300), so we treat its null as uninformative rather than as evidence of non-transfer. Attention knockout partially restores audio-grounded output by blocking the claim from propagating through intermediate tokens during open-ended generation, whereas blocking the answer position's direct connection to the conflicting claim has no effect. The claim's influence therefore travels…

  PDF
• arXiv cs.CLOct 19

  Cognitive Map in Large Language Models

  Albert Qin, Jonathan Cohen, Gautam Reddy

  It has long been proposed that animals construct cognitive maps to support flexible behavior in novel environments. We tested whether large language models form similar representations using relational reasoning tasks and causal "mosaic experiments" that manipulate internal activations in open-weight language models. Models beyond the ten-billion-parameter scale successfully inferred unstated relationships between entities and generalized to synthetic entity names. Across model and task families, models generated abstract representations of relational structure and combined them additively with representations of entity identity, binding entities to roles within that structure. Models stored observed relationships as pairwise links that they composed retrospectively when queried, rather than prospectively positioning each entity in a global coordinate system. Binding was mediated by a sparse, distributed set of key--value pairs; by perturbing these pairs, we implanted "false memories" that altered model behavior in predictable ways. Overall, our findings reveal an internal organization analogous to a cognitive map that explains how language models reason with limited information.

  PDF
• arXiv cs.CVOct 18

  ViMoLa: Discrete Motion Tokens for Language-Guided Video Generation

  Bishoy Galoaa, Sarah Ostadabbas

  Language-guided video generation often captures scene content while missing the requested motion. We present ViMoLa (Video Motion Language), which predicts a motion prior from language and injects it into a frozen image-to-video backbone. A spatial vector-quantized autoencoder compresses dense trajectories into 64 tokens from a 512-entry codebook; a 28M-parameter transformer predicts the tokens from text; and zero-gated cross-attention adapters condition every frozen Wan~2.2 DiT block through forward hooks. Trained on 462K videos from Something-Something~v2 and Kinetics-400, ViMoLa raises directional accuracy from 0.287 to 0.442 (chance 0.250), with similar measured generative quality. Across-prompt shuffled codes achieve 0.283, supporting the importance of prompt-matched token content. A low-rank adapter reaches 0.428 at 1.45% additional forward-pass FLOPs, and reusing the tokenizer and language model with newly trained CogVideoX adapters raises accuracy from 0.301 to 0.398. Control remains imperfect: oracle codes reach 0.531, compound-motion gains are smaller, and the adapter does not explicitly preserve token-to-patch assignments.

  PDF
• arXiv cs.LGOct 18

  Distributionally-Robust Policy Learning with Observational Data

  Debmalya Mandal

  Policy learning from observational data is fundamental to applications ranging from personalized medicine to welfare-program targeting, but standard approaches optimize empirical performance and may fail when the deployment distribution differs from the training distribution. We study \emph{distributionally-robust policy learning}: given observational data, we seek a policy $π\in Π$ that maximizes the worst-case policy value over an $f$-divergence ball of radius $ρ$ around the data-generating distribution. We propose an estimator built on cross-fitted doubly-robust scores for the conditional treatment effect, paired with a DRO solver that handles \texttt{KL}, $χ^2$, and \texttt{CVaR} ambiguity sets. We establish two convergence guarantees. First, the estimated policy attains the standard $\widetilde{O}(n^{-1/2})$ rate on its DRO regret, and inherits the doubly-robust property -- the rate continues to hold whenever either the outcome model or the propensity model is consistently estimated, even at slow nonparametric rates. We then propose a sample-splitting bias-correction algorithm derived from the Lagrangian dual, and show that under a Tsybakov-style margin condition on the…

  PDF
• arXiv cs.LGOct 18

  Divergence based Ranked Preference Alignment for LLMs

  Rajdeep Haldar, Yue Xing, Qifan Song

  Alignment of large language models typically relies on pairwise preference feedback, though ranked feedback can capture more comprehensive information across multiple responses within a single annotation. However, ranked-preference alignment is underexplored in practice compared to simpler pairwise approaches, potentially resulting in suboptimal behavior. Concurrently, recent research has conceptualized large language model alignment objectives as divergence estimators between aligned (preferred) and unaligned (less-preferred) response distributions, resulting in a family of objectives with an interpretable theoretical foundation and strong empirical performance. This work unifies these perspectives by introducing $f$-RPO, a $f$-divergence objective for ranked preference optimization that extends divergence-based alignment to ranked feedback and recovers pairwise preference alignment as a special case. Our theoretical analysis establishes rank-order consistency, showing that $f$-RPO preserves the underlying preference ordering at convergence. Empirical results indicate that total-variation and reverse-KL variants of the proposed objective consistently outperform ranked-alignment…

  PDF
• arXiv cs.CLOct 18

  Assertion and Belief: Moore's Paradox in Language Models

  Anshun Asher Zheng, Weili Cao, Fangcong Yin, David Beaver, Junyi Jessy Li

  Moore's paradox \citep{moore1942} concerns sentences such as ``It is raining, but I don't believe that it is,'' which may well be true yet cannot be sensibly asserted. The absurdity lies not in the content but in the act, since to assert is to vouch for one's own belief. This makes the paradox a test of whether language models take the speech act into account when computing meaning. We present the first test of Moore's paradox in LLMs, evaluating 12 models on a curated set of Moorean sentences in varied contexts. We find that models largely recognize the infelicity of Moorean sentences, and that the judgement is not tied to a memorized form and tracks the speech act. Using the Rational Speech Act framework (RSA; \citealt{goodmanfrank2016}), we then test whether these judgements arise from a listener reasoning about a speaker. We find the models' own listeners do not reason about their own speakers, and their reasoning traces suggest that they instead recall knowledge about the paradox and apply rules therein. The models thus appear to have learned the paradox as a fact about sentences, not as a requirement on speakers.

  PDF
• arXiv cs.LGOct 18

  CVTA: Cross-Variable Temporal Attention for Multivariate Irregular Time Series Prediction

  Ankitkumar Joshi, Milos Hauskrecht

  Irregularly sampled multivariate time series arise in many real-world domains such as healthcare, climate science, and large-scale monitoring systems. Characterized by asynchronous observations and heterogeneity across variables, such time series pose significant challenges for forecasting. In this work, we introduce Cross-Variable Temporal Attention (CVTA), a short-term, continuous-time forecasting framework that learns prediction functions from its compact, interpretable state summarizing recent temporal dynamics across variables. CVTA uses Variable-Conditioned Embeddings to project heterogeneous variables into variable-specific latent spaces, and applies temporal attention to capture cross-variable dependencies from this state. Furthermore, we demonstrate that CVTA can be integrated as an auxiliary module into existing state-of-the-art prediction models through a dynamic meta-decision model. Extensive experiments on multiple real-world benchmarks show that CVTA achieves strong short-term predictive accuracy, supports efficient online inference, improves existing prediction models when used as an auxiliary module, and learns attention patterns that align well with domain…

  PDF
• arXiv cs.CLOct 18

  Sharp Degree Bounds for Putinar Certificates in Terms of the Positivity Margin via Analytic Sums of Squares

  Yuxiang Zhao, Ting Gan

  We establish sharp degree bounds for Putinar sum-of-squares (SOS) certificates in terms of the positivity margin $δ$. For any fixed Archimedean quadratic module with prescribed generators and any fixed bound on the degree of the objective, we prove a uniform certificate-degree upper bound of $O(δ^{-1/2}\log^2(2/δ))$ for normalized polynomial objectives. We show that this bound is sharp by constructing a matching lower-bound example in three variables, thereby establishing that the dependence on $δ$ is optimal. These matching bounds also yield sharp worst-case convergence rates for the Lasserre hierarchy.

  PDF