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 learning51+37.8%
• Agents537+3.3%
• Quantum machine learning240.0%
• Character recognition OCR170.0%
• Sensing communication150.0%
• Frontier LLMs458−4.8%
• Image segmentation186−10.1%
• Voice AI104−10.3%

• arXiv cs.AIOct 19

  OrderGPT: Generation Order as a Learnable Modeling Choice

  Chenhe Yang, Yuhuan Lyu, Tianyang Hu

  Generative modeling of discrete data has two popular paradigms: autoregressive models such as GPT, which factorize a sequence in a left-to-right (L2R) order, and masked diffusion models, which are essentially any-order autoregressive modeling. Rather than competing methods, these are the two extreme points of a single axis -- the generation order. For structured discrete domains without a natural traversal, both extremes may be suboptimal, yet the intermediate choice -- a single well-adapted order -- remains largely unexplored. We introduce OrderGPT, which builds on Any-Order GPT to learn a task-level generation order without canonical-order supervision. Our key observation is that predicting variables from randomly sampled reveal prefixes produces recurring attention patterns in the backbone that provide a model-dependent signal of predictive dependencies. We aggregate this signal into a reciprocal dependency graph and use a spectral teacher to derive continuous generation priorities. A lightweight OrderMLP integrated into the GPT backbone learns to predict these priorities from attention, incorporating order learning into the architecture within a single training run. Training…

  PDF
• arXiv cs.AIOct 19

  Claim Laundering: When Agent Decision Models Trust Records Over Reality

  Tina Khezresmaeilzadeh, Seyedarmin Azizi, Erfan Baghaei Potraghloo, Mehdi Kamal, Massoud Pedram

  Agent decision models select actions in a single forward pass from inputs that combine environmental observations with the agent's own record of previous actions. When an action fails silently, these sources can conflict: the record reports success, but the environment shows that the step did not take effect. We ask which source determines the next decision. Across Android screen traces, ALFWorld, and WebShop, we construct paired states that independently vary the observation, the logged action, and an explicit success claim. In all 12 configurations of four decision models and three domains, records have a larger average effect on commitment decisions than observations; after claimed-but-failed steps, the models still stop, advance, or purchase in 53-100% of cases. Yet the relevant evidence is often represented internally: linear probes on intermediate hidden states distinguish successful from failed steps on held-out apps, tasks, and goals (AUROC 0.77-1.00), and activation patching reveals increasing influence from records in later layers. We use this signal in EVIGATE, an intermediate-layer veto that requires no additional forward pass and adds 0.04-2.0% serving latency. Under…

  PDF
• arXiv cs.ROOct 19

  Policy Search in Code Space for Multi-Agent Pathfinding

  Matthias Eder, Pantelis Emmanouil, Vivek Farias, Fabian Fischer, Adam Jozefiak +5

  Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With recent advances in autonomous coding agents, we show that policy search directly in code space offers a compelling third path that combines automated optimization with explicit interpretability. We investigate a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification. We conducted two case studies and found that this workflow robustly outperformed any manually engineered solutions. On a challenging map in the 2024 League of Robot Runners competition, a two-day search discovered a policy that exceeds the stronger locally reproduced competition entry by 35.0% on the densest instance and generalizes to unseen map instances. In simulated real-world warehouses with irregular lanes, continuous robot geometry, and asynchronous motion, a week-long search discovered an entirely new class of multi-agent pathfinding algorithm that outperforms a calibrated proprietary solution in…

  PDF
• arXiv cs.CLOct 19

  TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models

  Pume Tuchinda, Tinnakit Udsa, Peerat Limkonchotiwat

  Existing benchmarks for text-vision embedding models report aggregate scores that obscure whether performance comes from general capabilities, task-specific adaptation, or robustness to challenging tasks. We introduce TRACE, a Training-aware Robustness and Challenge Evaluation framework that reorganizes 168 tasks from various sources of datasets into three categories: General, Adaptability, and Challenge. Through controlled experiments on two text-vision embedding models, we show that combining general and adaptation data improves Adaptability performance by 7.67 and 7.09 points, respectively, while largely preserving General performance. However, Challenge performance remains below 5.0, with limited improvements from additional training data. Further analysis identifies multilingual and visual-document tasks as major weaknesses. Our findings demonstrate that data adaptation alone is insufficient to address these challenges, highlighting the need for methodological advances beyond data-centric improvements.

  PDF
• arXiv cs.LGOct 19

  CoASFL: Coupled Consistency Optimization for Asynchronous Split Federated Learning

  Junhao Cheng, Yunming Liao, Hongli Xu, Yang Xu, Zuan Xie

  Split Federated Learning (SFL) has emerged as a promising paradigm for training large-scale deep models on resource-constrained edge devices. Although asynchronous SFL alleviates the straggler bottleneck caused by system heterogeneity, it inevitably introduces two coupled dimensions of inconsistency: horizontal inconsistency across clients and vertical inconsistency between clients and the server. These inconsistencies, further exacerbated by statistical heterogeneity, result in biased activation representations, model divergence, and severe client drift. To address these challenges, we propose CoASFL, an inconsistency-aware asynchronous SFL framework that incorporates a dynamic activation merging mechanism and a consistency-aware model aggregation mechanism. Specifically, CoASFL constructs more consistent activation sequences from heterogeneous clients to alleviate horizontal inconsistency, and dynamically adjusts aggregation weights according to client participation frequencies and progress gaps to mitigate vertical inconsistency. By jointly coordinating activation-level and model-level consistency, CoASFL effectively suppresses inconsistency propagation during asynchronous…

  PDF
• arXiv cs.CLOct 19

  Speech LLMs That Breathe: Modeling Non-Verbal Vocalizations in Dialogue

  Heyang Liu, Lixin Zhang, Jiayi Huang, Ziyang Cheng, Yuhao Wang +4

  The user experience of speech interaction models has improved, benefiting from the modeling of paralinguistic attributes and advances in speech reconstruction paradigms. However, human communication follows extensive norms regarding non-verbal vocalizations (NVVs) spanning respiratory, affective, and discourse. The omission of these events imposes inherent limitations on the naturalness of current approaches. In this work, we cover 13 major types of NVVs and construct a natural dialogue dataset that conforms to human conversational norms through an automated synthesis pipeline. We enhance the ability of speech interaction models to generate contextually appropriate NVV events through multi-stage fine-tuning and NVV-aware GRPO (Group Relative Policy Optimization). Based on distinct modeling paradigms, we substantially improve the expressiveness of VocalNet and VITA-Qinyu in empathy interactions and role-play dialogues, and further discuss the architectural necessity for achieving high-quality natural speech generation.

  PDF
• arXiv cs.AIOct 19

  Global probabilistic forecasting of air pollution

  Ammar Kheder, Michael Boy, Zhi-song Liu

  Fine particulate matter (PM2.5) refers to particulate matter with an aerodynamic diameter of 2.5 micrometre or less. It comes from human activities, such as traffic and industry, and from wildfires, desert dust and gases emitted by vegetation. Short-term exposure to it accounts for about a million deaths a year. Operational forecasts run on grids tens of kilometres wide, which hide the pollution breathed by nearly two hundred million people a day. Machine learning has transformed weather forecasting, but data-driven forecasts of air pollution still blur extremes and lose skill as the air travels. Here we introduce Foehn, a generative model that learns from global kilometre-scale estimates of PM2.5 and computes where the air comes from. Over a year of retrospective forecasts, it outperforms the operational forecast at three stations in four and forecasts at the scale of this hidden exposure. Its ensembles are calibrated, and their mean detects local pollution extremes four days ahead as well as the operational forecast does one day ahead. Such forecasts could warn the millions whom coarse maps miss, once kilometre-scale data are available in real time.

  PDF
• arXiv cs.CLOct 19

  MITRA-lexicon: Lexica of attested translations from Sanskrit into English, Tibetan and Chinese

  Sebastian Nehrdich, Kengo Harimoto, Sven Sellmer, Oliver Hellwig

  The standard Sanskrit lexica are monumental and indispensable, but they cite their attestations as abbreviated references to editions, without links to the digitized texts now widely available and without a translation of the passage, and they naturally do not reflect translations made after them. To address these gaps, we present MITRA-lexicon, a family of corpus-grounded lexica based on span annotations of translation equivalents with Sanskrit as the pivot: Sanskrit-English, derived from the Mitrasamgraha corpus, as well as Sanskrit-Tibetan and Sanskrit-Chinese, derived from the MITRA-parallel corpus of Buddhist literature. In total, the resource comprises 2.18 million headword entries in six directional lexica. Headwords are lemmas and compounds from silver annotations that follow the Digital Corpus of Sanskrit (DCS). Senses are ranked by frequency, and each of the 10.4 million attestations includes its sentence pair, with character offsets of the word and its equivalent. We propose a multi-step pipeline based on grammatical annotation models, fine-tuned large language models, and a teacher-student setup to produce the alignments. We evaluate the lexica against reference…

  PDF
• arXiv cs.LGOct 19

  The KV-Surgeon: Compensation-Aware Offline KV-Cache Compaction

  Moritz Wagner, Christophe Roux, Max Zimmer, Sebastian Pokutta

  Offline compaction of the key--value cache (KV-cache) reduces the cost of repeatedly querying a fixed context by constructing a smaller cache once and reusing it subsequently. The central challenge of compaction is deciding which cache entries to delete and which to retain. Existing methods score each candidate for deletion on its own, with the rest of the cache being held fixed. However, softmax renormalization of the attention operation couples these decisions in a nonlinear manner: removing one entry changes the attention weights of every remaining one. In this work, we introduce KV-Surgeon, which uses calibration data to take interactions into account in a tractable way. We derive a quadratic surrogate that admits closed-form expressions for jointly making the optimal greedy removal decision as well as compensation within the remaining entries. On QuALITY, LongHealth, and Long Code Arena, and at every evaluated compaction ratio, KV-Surgeon substantially advances the cost--accuracy Pareto frontier of dense and mixture-of-experts models from 4B to 30B parameters. At $50\times$ compaction, KV-Surgeon improves question-answering accuracy by up to four points over attention…

  PDF
• arXiv cs.LGOct 19

  Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding

  Minoo Ahmadi, Seyedarmin Azizi, Mehdi Kamal, Massoud Pedram

  Inference-time sequential Monte Carlo (SMC) decoding can improve the reasoning accuracy of masked diffusion language models (diffusion LLMs) without post-training by resampling a population of partial generations according to a reward. Its effectiveness therefore depends on the resampling step, which must concentrate computation on promising candidates while retaining enough diversity to explore alternative reasoning paths. The reward can be internal, the decoder's own confidence on the committed prefix, or external, a process reward model scoring that prefix. Under either reward, multinomial resampling can disrupt this balance by duplicating high-weight particles and discarding lineages that may still reach a correct solution. The effective sample size (ESS) does not register this loss: multinomial resampling resets it to its maximum even as distinct lineages disappear. To retain such lineages, we introduce lineage-preserving SMC (LP-SMC), which combines Chopthin resampling with an input weight floor. Instead of equalizing weights, Chopthin bounds the ratio between the largest and smallest weights it returns and carries the unequal weights forward. The floor limits how far below…

  PDF
• arXiv cs.AIOct 19

  EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver

  Dastin Huang, Baran Nama, Salaheddin Alzubi

  EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact. The user starts a run by describing a benchmark and supplying a grader, which a benchmark adaptor turns into a benchmark-specific plugin. A solver attempts the tasks, and an evolver reads the solver's training rollouts and rewrites the skills at each epoch. We implement the evolver as one stateful coding agent with a bash tool for the whole run, unlike the two most common designs among the skill optimizers we surveyed: a sequence of single model calls, as in SkillOpt, and an agent that starts afresh each round, as in SkillBoost. We also measure how much the solver's rollouts vary from one attempt to the next, give the evolver several attempts per training task, and accept every epoch's skills instead of selecting among them on noisy scores. With fine-grained ground truth, EvoSkill v2's skills raised the held-out pass rate above the stronger of SkillOpt and SkillBoost by 7.7 percentage points on SpreadsheetBench v2 and by 5.4 on $τ^3$-bench banking. In both benchmarks and both feedback settings, EvoSkill v2's evolver cost less per percentage point of…

  PDF
• arXiv cs.AIOct 19

  TESS: LLM-guided Translation, Exploration, Simulation, and Search for Embodied Task Planning

  Peiran Xu, Yixiang Yang, Jinghan Li, Fei Li, Cao Sheng +2

  In this work we focus on the problem of embodied task planning, which requires an agent to accomplish a complex task by separating it into atomic actions. Recent studies have developed LLM-based methods to address this problem. However, the executability and correctness of the generated plans remain suboptimal in complex environments and tasks. On the other hand, classical search algorithms have the potential to solve the planning problems perfectly, yet they require fully observable environments, known state transitions and goal state, which are often unattainable in general task domains. Therefore, we propose to implement an LLM-guided search algorithm that makes the search process possible and efficient by incorporating LLMs' commonsense knowledge. Our method leverages LLMs to (1) translate natural language instructions into formatted goal conditions, (2) facilitate efficient exploration in partially observable environments, (3) implement a rule-based world simulator, and (4) prune the space of candidate actions to improve search efficiency. Experimental results on VirtualHome and ALFWorld demonstrate its superior performance.

  PDF
• arXiv cs.CVOct 19

  OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training

  Zixuan Chen, Depeng Wang, Hao Lin, Ke Xu, Ya Guo +3

  Omni-modal large language models can jointly understand video, audio, and text, yet they remain weak at temporal grounding, a capability essential for real-world audio-visual applications. To understand this limitation, we look beyond final predictions and examine the model's internal temporal evidence. We identify a temporal generation gap: the internal attention of the model localizes the target moment more accurately than the timestamps it generates. To close this gap, we propose TACG (Temporal Attention-Consistency Grounding), a post-training method that treats internal attention as a reliable temporal pivot and aligns it with both the model prediction and the ground-truth annotation through attention-consistency training. We further build a 580K-sample training dataset by reconstructing temporal QA from dense audio-visual annotations and organizing general omni-modal instruction data. Using TACG and this training dataset, we train OmniGround, a general-purpose omni-modal model with stronger temporal grounding capability, without injecting any additional temporal cues. OmniGround reaches state-of-the-art omni-modal temporal grounding, including 37.5 mIoU on LongVALE and 35.7…

  PDF
• arXiv cs.CVOct 19

  CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA

  Feiyang Hong, Yujie Wei, Bo Zhao, Xiu Su, Hongxun Yao +1

  Robot manipulation often depends on short-term cues - such as brief contacts, temporary occlusions, and intermediate object states - that are ambiguous in a single frame and can only be resolved by integrating observations over time. However, injecting historical information solely by enlarging the history window is computationally costly and frequently yields limited gains due to substantial redundancy and task-agnostic, inflexible sampling of observations. We propose CondenseVLA, a multi-frame VLA policy with a learnable decoder-side history condensation module for using short-term visual context in action decoding. Given a sequence of cached per-frame features from the VLM backbone, CondenseVLA distills observation history into a fixed set of slot tokens using learnable queries and multi-head cross-attention. Simple auxiliary regularization penalizes overlap among slot attention maps and decorrelates slot embeddings, encouraging complementary attention and reducing slot redundancy. Across the evaluated tasks, CondenseVLA improves Simpler-WidowX success from 58.7% to 69.8% (+11.1 percentage points), achieves 97.2% on LIBERO, and reaches 52.8% on real-world tasks. It achieves…

  PDF
• arXiv cs.CVOct 19

  MIRA: A Multimodal Illustrated Deep Research Agent for Controllable Reports

  Hongrui Wu, Kaiwen Tuo, Congcong Wang, Gen Li, Shuai Dong +5

  Deep research agents are increasingly capable of searching the open web and synthesizing evidence, yet they remain poorly suited to controllable report generation in multimodal deep research. This task requires agents to handle interleaved textual and visual inputs, gather multimodal evidence through multi-step web search, and deliver comprehensive illustrated reports under user-specified requirements. Existing systems face two limitations. During reasoning, they often underuse images discovered along the search trajectory; during generation, they tend to produce fixed-form answers with limited control over report granularity, multimodal composition, and evidence grounding. We introduce MIRA, a Multimodal Illustrated Deep Research Agent for controllable reports. MIRA integrates textual and visual evidence throughout research and writing. At its core, MIRA-Harness translates user requirements into generation contracts and connects four stages: evidence collection, report submission, feedback-driven revision, and final delivery. Building on this harness, MIRA-Data constructs high-quality multi-hop multimodal research trajectories, and we post-train foundation models to operate…

  PDF
• arXiv cs.LGOct 19

  UtilityBench: Measuring Language Model Utility When Errors Have Different Costs

  Qifeng Lei, Zhiyong Yang, Zitai Wang, Shilong Bao, Linchao Zhang +2

  As language models are increasingly deployed in real-world scenarios with important outcomes, the impact of their mistakes often extends far beyond what correctness can capture. In domains like medicine, a single error can lead to serious consequences and put patient safety at risk. However, mainstream evaluation protocols still treat all errors as equal, overlooking the spectrum of real-world costs. To address this, we propose a utility-based evaluation paradigm that explicitly incorporates the varying consequences of errors. Guided by this principle, we develop UtilityBench, a large-scale benchmark of 15,000 instances with verifiable answers, quantifying error severity using Best-Worst Scaling to elicit meaningful, data-driven cost estimates. These quantified utilities shape when a model should answer or abstain, guiding it to make decisions that align with the true importance of each scenario. As another merit, we introduce UtilityAUC, a metric that measures the area under the utility curve determined by a model's response ordering, thereby enabling utility preference alignment beyond error frequency. Our theoretical analysis demonstrates that UtilityAUC can distinguish…

  PDF
• arXiv cs.CVOct 19

  SAPO: Self-Supervised Attention Policy Optimization for Improving Temporal Video Grounding in Vision-Language Models

  Zixuan Chen, Depeng Wang, Wei Chen, Ke Xu, Ya Guo +3

  Video vision-language models (VLMs) have strong semantic understanding, yet remain unreliable at precise temporal grounding. Existing gains from explicitly aligning video frames with absolute time suggest that VLMs may already encode accurate temporal locations internally but lose precision when expressing them as timestamps. Our analysis across four VLMs and two grounding datasets confirms this hypothesis: attention intervals outperform predicted intervals on approximately 66% of valid examples. We term this discrepancy the temporal generation gap. Because precise temporal annotations are expensive, this finding motivates closing the gap to improve temporal grounding using only unlabeled video-query pairs. We propose Self-Supervised Attention Policy Optimization (SAPO), which uses internal temporal attention as self-supervision for Group Relative Policy Optimization and applies a ground-truth-free criterion to select high-value samples. SAPO consistently improves temporal grounding across multiple datasets and models spanning weak to strong initial grounding ability. Relative mIoU gains reach 33.7% on Qwen2.5-VL-3B and 5.4% on the strong Time-R1-7B. The improvements transfer…

  PDF
• arXiv cs.LGOct 19

  Maestro: Agentic Formal Proof Development by Coordination

  Haoyu Li, Zeren Shui, Yuhao Zhang, Ferhat Erata, Benjamin Mikek +2

  Lean is increasingly used to verify mathematical proofs and software produced by LLM agents, but writing formal proofs remains hard. Existing prover systems take a divide-and-conquer approach that recursively decomposes hard proof obligations into easier lemmas and splits again any lemma that resists proof. However, a lemma can resist proof for different reasons, including insufficient guidance, a false statement, or a flaw in the decomposition that produced it. Existing systems cannot tell these apart as a failed attempt reports little beyond its failure, and responses are confined to the failing node without considering the rest of the proof or revising the plan above it. The system may thus keep decomposing obligations along a flawed proof direction until the budget runs out, causing the whole proof attempt to fail. We introduce Maestro, a Lean prover harness that handles failures through global coordination. Provers report why they failed, not just that they failed, and a coordinator that sees the whole proof chooses an appropriate response, such as guiding a stuck prover, correcting a false lemma, or retracting a flawed subtree and replanning it. The same harness extends to…

  PDF
• arXiv cs.CLOct 19

  LEAPS: Long-context Evaluation of Adaptive Pattern Learning and State Tracking

  Howard Yen, Nitya Mani, Alex Renda, Christopher S. Hardin

  Long-context language models (LCLMs) power agents that act over long trajectories, from improving a codebase to running research experiments to forecasters that condition on lengthy histories. These applications draw on three distinct long-context capabilities: recall, where the answer is a fact present in the context; state tracking, where the outcome can be computed by performing a series of transformations to a specified state; and pattern learning, where the goal is to make a prediction by sampling from a distribution inferred from many observations. Existing benchmarks primarily focus on the first capability. In this work, we introduce LEAPS (Long-context Evaluation of Adaptive Pattern learning and State tracking), a collection of 12 novel datasets, spanning agentic workflows, behavioral modeling, and forecasting of market and world events. By construction, LEAPS is resistant to data contamination, extends to millions of input tokens, and uses reliable metrics. We evaluate 30 API and open models from 8K to 512K input tokens. LEAPS distinguishes models that perform near perfectly on recall tasks, finding that such models' state tracking and pattern learning abilities can vary…

  PDF
• arXiv cs.CVOct 19

  LEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear Leaps

  Haowei Zheng, Zhenyu Zhou, Jiawei Chen, Can Wang, Defang Chen

  Diffusion models primarily rely on general-purpose ODE-based numerical methods for training-free accelerated sampling, but performance degrades with coarse time discretization. In this paper, we propose optimal linear leaps (LEAP), a specialized method grounded in theoretical and empirical investigations of sampling trajectory geometry. Built upon low-dimensionality and cross-trajectory consistency, LEAP formulates a supervised least-squares optimization problem within the local trajectory subspace, achieving a precise approximation of future states without model evaluations. Extensive experiments demonstrate that LEAP outperforms previous methods across diverse modalities, including text-to-image (Stable Diffusion 3.5, FLUX.1-dev) and image-to-3D (TRELLIS.2) generation. Furthermore, LEAP can be seamlessly integrated into existing solver-based methods, offering a plug-and-play enhancement for modern diffusion models. Code is available at https://github.com/zju-pi/LEAP.

  PDF