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%
• Agents532+2.3%
• Quantum machine learning240.0%
• Character recognition OCR170.0%
• Sensing communication150.0%
• Frontier LLMs454−6.0%
• Voice AI104−9.6%
• 3D scene163−11.4%

• arXiv cs.CLOct 19

  Where RL Breaks: Localizing and Repairing Failures via Targeted Continued Pretraining

  Xinyi Wang, Danqi Chen

  Reinforcement learning with verifiable rewards (RLVR) is widely used to improve reasoning in language models, yet growing evidence suggests that it mostly sharpens what the base model can already do. This raises a practical question: when RL fails, what is the base model missing? We look inside the RL policy's own rollouts and find that failures are localized: whether a rollout fails is strongly predicted by a small set of characteristic n-grams, ranging from reflection phrases such as "let's recheck" to specific operations such as "the inverse of A". These failures persist throughout RL training, although they are not beyond the model's reach: other sampled answers to the same question are often correct. Building on this observation, we use the failure $n$-grams to retrieve text from the pretraining corpus and continue pretraining the base model on it before RL. The resulting corpus has only 35M tokens, 3--4 orders of magnitude smaller than typical mid-training. We evaluate this approach on OLMo2 and Qwen3 models trained with RL on (1) GSM8K; (2) a mixture of math, commonsense, and knowledge questions; and (3) general math and science reasoning. Despite its size, the corpus…

  PDF
• arXiv cs.CLOct 19

  Diffusion Language Models Change Speed Across Tasks and Languages

  Mohsen Fayyaz, Ali Modarressi, Daniel Israel, Lucas Bandarkar, Nanyun Peng

  Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passes to spend. Two outputs of the same token length can therefore vary a lot in cost. To understand the underlying factors of this cost variation, we analyze two diffusion models across 10 tasks. We find that the number of forward passes per token depends heavily on the task. Text copied or lightly edited from the input is cheap, while open-ended writing is costly. In DiffusionGemma, generating a token for story writing requires more than three times as many forward passes as for grammar correction. Two output properties explain much of this gap: how much of it is new relative to the input, and how rare its words are within the task. The same holds within a single response when thinking is involved. The final answer is cheap when it repeats the model's reasoning trace and costly when it adds something new. In multilingual generation, we find that highly tokenized languages also require more passes per token, adding to the cost they already pay with more tokens. Finally, cost tracks correctness: on the same math problem, wrong answers take more passes per token than…

  PDF
• arXiv cs.AIOct 19

  FrontierRefactor: Benchmarking Multi-Scale Performance-Oriented Codebase Refactoring

  Shijian Wang, Fanqing Meng, Jiajun Chen, Qiguang Chen, Linxin Song +6

  Autonomous codebase refactoring requires coding agents to restructure working software while strictly preserving externally observable behavior and prioritizing execution performance and compute efficiency over stylistic preference. Existing benchmarks: refactoring benchmarks assess functional correctness while overlooking runtime regressions, whereas code performance benchmarks target isolated micro-kernels that ignore codebase-scale complexity. We observe that refactoring scale is governed by the scope of the observable contract, the caller-visible interface fixing behavioral invariants while freeing private implementations for optimization. Building on this insight, we introduce FrontierRefactor, a benchmark of 60 qualified engineering tasks spanning four scales, from computational kernels to full repositories, across in-place optimization and cross-language rewriting. Evaluating frontier coding agents through a reference-free cascaded protocol across 1,080 execution runs reveals that correctness and speedup are largely decoupled: 41.2% of submissions satisfy functional equivalence yet fail to deliver verified performance improvements, with 19.3% suffering performance…

  PDF
• arXiv cs.CVOct 19

  Hihaze: One-Step Diffusion for High-Resolution Real-World Image Dehazing

  Zheng Chen, Yuchen Huang, Xiaoyang Liu, Jue Gong, Linghe Kong +1

  Diffusion models have recently achieved encouraging results in real-world image dehazing. However, restoring high-resolution images remains challenging due to spatially non-uniform haze and inconsistent predictions across local patches. To address these issues, we propose Hihaze, a one-step diffusion framework for high-resolution real-world dehazing. Hihaze adopts two haze-aware modulation modules: attentive skip compensation (ASC) and a spatial degradation adapter (SDA). ASC selectively transfers reliable encoder information to the variational autoencoder (VAE) decoder, preserving structural details while suppressing haze-degraded features. SDA extracts multi-scale spatial degradation representations and injects them into the U-Net to guide restoration according to local haze variations. Furthermore, we design a training-free global-guided patch fusion (GPF) method. It uses a global prediction to align patch appearance and downweight unreliable predictions, followed by structure-guided detail compensation. Notably, this training-free design also makes GPF a plug-and-play module for other dehazing models. Experiments across four real-world benchmarks show that Hihaze surpasses…

  PDF
• arXiv cs.AIOct 19

  When Retrieval Partially Conflicts with Skills: Understanding Procedural Hallucination in Language Models

  Guanqun Jiang, Pengfei Cao, Kang Liu, Jun Zhao

  Language models increasingly use skills that provide reusable instructions and procedures for task execution. After a relevant skill has been selected, the model may need to apply its governing procedure together with retrieved task context. When the retrieved context is useful but contains cues that violate the skill, the model must retain compatible information while rejecting the conflicting cues. We study failures in which the model adopts such cues and produces a retrieval-supported but skill-invalid answer, which we call procedural hallucination. We introduce SourceClash, a matched benchmark with 1,271 bundles and 6,355 prompts across ten procedural domains. Each bundle fixes the task, skill specification, and answer space while varying the relation between the skill and retrieval. Across nine models, valid-answer rates average 25.7% under conflicting retrieval, compared with 78.2% and 72.8% under two supportive retrieval settings. Mechanistic analysis of open-weight models shows that the answer-preference difference typically reaches its maximum shortly after generation begins. Residual replacement moves the model toward valid answers, while attention decomposition…

  PDF
• arXiv cs.SEOct 19

  From Finding to Fixing: How Useful is Fault Localization for Agentic Program Repair?

  Xinyu Shi, Zhou Yang, An Ran Chen

  Fault localization (FL) aims to identify code locations responsible for software failures and is commonly evaluated by how accurately it ranks known fault locations. Large language model (LLM) agents are changing program repair and are increasingly used to search and reason over repositories. Although recent LLM-based FL methods have improved localization accuracy, their impact on agentic repair remains unclear. To address this gap, we conduct a systematic empirical study of FL in agentic repair. We evaluate six recent FL methods on SWE-bench Verified and Defects4J with three LLMs under a common repair framework and analyze 16,248 repair trajectories. We also examine gold locations and bug-cause descriptions as forms of FL guidance across different repair contexts. The studied FL methods do not consistently improve repair success, and higher localization accuracy does not consistently lead to larger repair gains. Yet FL guides agents' early search and helps them reach relevant code sooner. Accurate locations can reduce repair token use by up to 39.2\%, but current FL methods often consume more tokens than they save during repair. Experiments with gold guidance suggest that FL has…

  PDF
• arXiv cs.SIOct 19

  Optimizing Marketing Budgets for Social Influence: A Generalized Fractional Incentives Framework

  Abhishek K. Umrawal, Akhil Bhimaraju, Eliot W. Robson, Lav R. Varshney

  Marketing managers routinely allocate limited budgets across individuals in social networks whose responsiveness and influence vary substantially. We study the problem of Budgeted Generalized Fractional Influence Maximization (BGFIM), which captures the allocation of continuous levels of marketing spend across users in the presence of heterogeneous response and network spillovers. In this framework, adoption probabilities are governed by user-specific response functions that capture both baseline propensity and marginal responsiveness, while incentive costs vary across users. We propose a scalable solution approach based on a discrete greedy procedure with provable approximation guarantees, enabling tractable optimization under realistic budget constraints. Our formulation generalizes prior influence maximization models by allowing heterogeneous response and cost structures, providing a more flexible representation of targeted marketing interventions. Using experiments on multiple large-scale networks, we show that continuous allocation strategies can outperform standard heuristics and improve influence outcomes under heterogeneous conditions, and we illustrate how the framework…

  PDF
• arXiv cs.AIOct 19

  When to Stop Asking: Factor Coverage Bias and LLM Determinability Judgments with Underspecified Information in Medicine

  Yusuke Watanabe, Yohei Kobashi, Taisei Tosaki, Takeshi Kojima, Yusuke Iwasawa +2

  Clinical decision-making often begins with underspecified information and requires not only gathering missing information but also knowing when to stop. This calls for judging determinability (whether the available information is sufficient for a decision) by considering whether missing information could change the conclusion, not simply the amount of available decision-relevant information. Reliance on this amount as a cue for determinability, which we term \textit{factor coverage bias}, could undermine the trustworthiness of large language models (LLMs) through premature conclusions or excessive information gathering, such as unnecessary invasive tests. Yet whether LLMs exhibit this bias remains insufficiently studied. To address this gap, we construct a controlled pairwise benchmark in which LLMs identify the determinable case within each determinable--undeterminable pair. We add a decision-relevant factor to either side while keeping each case's determinability unchanged, and similarly add irrelevant text to distinguish this bias from context-length effects. Adding a relevant factor made LLMs more likely to select the augmented case as determinable even when it remained…

  PDF
• arXiv cs.CLOct 19

  Modal Sense Disambiguation in Language Models: The Role of Context, Training Domain, and Input Frequency

  Ezgi Başar, Yevgen Matusevych, Annemarie van Dooren, Arianna Bisazza

  Modals such as may and must can take on different senses depending on discourse context, alternating between root interpretations (e.g., permission, obligation) and epistemic interpretations (e.g., knowledge, belief). While modals are known to be notoriously difficult for children to acquire, limited research exists on whether language models (LMs) can reliably distinguish between different modal senses. We evaluate seven LMs that vary in architecture, size, and training data type using vector-based similarity and surprisal measures across four datasets. Specifically, we investigate whether LMs can leverage contextual information to disambiguate modal senses and whether their performance reflects the distribution of modal senses in their training data. We show that larger LMs trained on diverse text successfully leverage additional contextual information when available. In the absence of context, they tend to favor the dominant sense based on corpus statistics. Smaller developmentally plausible LMs, including those trained on child-directed language (CDL), fail to show consistent sensitivity to modal sense distinctions and do not benefit from context to the same degree.

  PDF
• arXiv stat.MLOct 19

  Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting

  Songlin Du, Ling Luo, Uwe Aickelin

  Quantifying uncertainty in time series forecasting is particularly demanding because sequential data exhibit temporal dependence and are prone to distributional changes. Conformal inference has emerged as a powerful uncertainty quantification approach through the construction of prediction sets. Recent advances have introduced online conformal methods that adaptively adjust prediction thresholds through feedback mechanisms. However, the existing feedback mechanism typically relies solely on miscoverage indicators (actual feedback), whether the true label falls within the interval at each time step, while overlooking the empirical prediction threshold (estimated feedback) that is derived from the oracle conformal method. In this paper, we propose Dynamic Dual-feedback Conformal Inference (DDCI), which incorporates a dual-feedback mechanism consisting of actual feedback and estimated feedback. The former drives the primary adjustment of the intervals based on true observations, while the latter dampens excessive expansions or contractions by leveraging empirical thresholds from conformal inference during updates. By balancing these two signals, DDCI achieves more stable and…

  PDF
• arXiv cs.LGOct 19

  Is it RL or Data? A Controlled Comparison of GRPO and Rejection-Sampling Fine-Tuning

  Lakshya Chaudhry

  Bauer et al. (2026) showed that in low-data reinforcement learning with verifiable rewards, training GRPO on mixed-difficulty prompts gives up to 5x the sample efficiency of easy-only prompts. They did not test whether this benefit is specific to GRPO, or whether another post-training method given the same data would obtain it too. We test this on their procedural counting task with Qwen3-4B-Base and LoRA, comparing GRPO to rejection-sampling fine-tuning (RFT) on the same prompts, verifier and token cap. Six primary arms cross the two methods with three prompt sets (Easy, Mixed, and a Curated subset of prompts the base model sometimes solves, which makes GRPO's implicit filter explicit). We use three seeds per arm. Hypotheses and falsifiers were registered before training. To rule out a poorly tuned baseline, RFT receives a 27-run hyperparameter sweep, while GRPO uses Bauer et al.'s recipe unchanged. GRPO outperforms RFT at every prompt set: by 10.9 points on held-out test problems with curated prompts, and, in post hoc comparisons with matched rollout budgets, by 8.4 and 9.2 points on the easy and mixed prompts. On test the advantage survives the least favorable treatment of…

  PDF
• arXiv cs.LGOct 19

  Communication-Efficient Federated Domain Generalization in Edge Networks via Dynamic Prototype Regulation

  Yuankun Xia, Hui Wang, Ling Yuan, Ziyu Hong, Di Yin +1

  Federated learning (FL) is a distributed paradigm for Internet of Things (IoT) edge networks. However, deploying Vision-Language Models (VLMs) over wireless edge networks presents distinct challenges: large model parameters increase uplink transmission latency over bandwidth-constrained fading channels, and non-independent and identically distributed (Non-IID) data exacerbates client drift. Existing feature alignment solutions often introduce auxiliary computations that consume time slots allocated for wireless parameter transmission, increasing the likelihood of straggler dropouts under system delay constraints. To address these issues, we propose DPGR-GCAM, a communication-efficient federated domain generalization framework. By employing a dual-parameter-efficient fine-tuning (PEFT) architecture, we design a channel-aware tiered transmission mechanism that adaptively truncates payloads to maximize node survival rates under fading conditions. To mitigate client drift, we introduce the Gradient-Conflict Aware Modulation (GCAM) mechanism. GCAM operates within the low-dimensional feature manifold to dynamically resolve multi-objective optimization conflicts with minimal edge…

  PDF
• arXiv cs.CVOct 19

  Do We Need Learned Targets? Classical Gradients as Supervision for 2D Gaussian Initialization

  Kyungjune Baek

  Learning-based Gaussian image initializers can require costly supervision obtained by per-image optimization. We investigate whether the Pseudo-PPM targets used by Instant GaussianImage can be replaced by classical image gradients. Our framework uses normalized Sobel maps in two tracks. A training-free analytic initializer combines probability boosting, parallel grid-based sampling, and geometric processing, producing initial parameters in 0.32 seconds on average. A neural initializer is trained on DIV2K with online Sobel supervision, which removes offline target optimization and allows training to scale to 10,000 LSDIR images without additional preprocessing. Both tracks achieve competitive long-budget reconstruction on Kodak and DIV2K. Under domain shift, the DIV2K-trained neural initializer surpasses Instant-GI on Manga109 from 500 fitting iterations onward (by 1.40 dB at 5K iterations), and training on LSDIR increases this margin to 1.85 dB. On Kvasir-SEG, the training-free analytic initializer exceeds Instant-GI at every reported budget. A controlled pipeline-time comparison yields an estimated $4.9\times$ reduction for DIV2K. These results establish inexpensive analytic…

  PDF
• arXiv cs.LGOct 19

  Sector-Ring Linear Reservoirs: Sector-Wise Decay-Timescale Allocation With State Reuse Across Candidate Settings

  Yudai Ebato, Sou Nobukawa, Yusuke Sakemi, Takashi Kanamaru, Nina Sviridova +1

  In reservoir computing, performance depends on whether the fixed dynamics of the reservoir suit the task, and the appropriate memory length and frequency response differ across tasks. The reservoir settings are found by a search on each task, and driving the reservoir with the input and collecting its states for every candidate setting dominates the cost of the search. In a reservoir with a linear recurrence, the dynamics decompose into modes, one per eigenvalue, and the eigenvalue distribution becomes a design variable. We propose the Sector-Ring Linear Reservoir (SRLR), in which the eigenvalue angles are fixed at evenly spaced positions around a circle and one decay timescale, chosen from a few values, is assigned to each sector of consecutive angles. To keep the scale of each mode's state equal across candidates, the input weights are scaled using the power spectrum of the training input. To reduce the cost of the search, the states of the modes for each decay-timescale value are computed once and reused across candidates. On prediction and reconstruction benchmarks built from chaotic systems, the SRLR achieved, in all eight cases, a lower mean test error than a reference…

  PDF
• arXiv cs.CLOct 19

  Think Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition

  Qihao Wang, Hang Su, Fan Cui, Lichun Fan, Jian Luan +1

  Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A reliable system must therefore exploit a relevant candidate without allowing unsupported alternatives to override the acoustic evidence. We propose a context-steered reasoning framework that generates a short, audio-grounded caption before transcription. This task-specific representation lets the model assess candidate relevance before making a lexical decision. Supervised fine-tuning establishes the structured caption-to-transcription behavior, while targeted trajectory injection strengthens group relative policy optimization when difficult utterances yield only unsuccessful rollouts. Experiments across diverse context conditions show that the proposed method consistently improves both transcription quality and hotword recognition while remaining robust to irrelevant candidates.

  PDF
• arXiv stat.MLOct 19

  Fair Regression under Approximate Demographic Parity

  Weiwei Wang, Xianyang Zhang, Raymond K. W. Wong

  Exact demographic parity requires the same prediction distribution across sensitive groups. In regression, this can be too restrictive and reduce predictive accuracy. We instead bound every pairwise Wasserstein distance between group-specific prediction distributions by a chosen tolerance, allowing the groups to differ while keeping fairness tunable. On the real line, the prediction and constrained transport problems have the same infimum. If the transport problem attains this value and suitable Monge maps exist, a deterministic transport-form predictor realizes it. Under a standard one-dimensional condition, the problem becomes a bounded quantile optimization that is convex when the conditional expected loss is convex in prediction. Under squared loss with two positively weighted groups, the $W_1$, $W_2$, and $W_\infty$ constraints yield soft-thresholding, shrinkage, and clipping. Under the stated conditions, we establish rates for the known-cost plug-in estimator. When the cost is unavailable, we describe an observed-loss computational proxy. Synthetic and California 2018 ACS studies illustrate the tunable fairness-accuracy trade-off and distinguish calibration feasibility from…

  PDF
• arXiv physics.ao-phOct 19

  AirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality Forecasting

  Yiheng Wang, Kai Zheng, Yuetan Lin, Fanglu Fan, Chenliang Tao +3

  Accurate real-time forecasting of atmospheric pollutants is essential for reducing exposure risks and improving public health. Traditional numerical forecasting systems suffer from incomplete parameterizations, uncertain inputs, and high computational cost. Existing deep learning approaches improve efficiency, but often entangle meteorological and pollutant variables within unified forecasting frameworks, limiting flexibility and pollutant-specific representation learning. To address these challenges, we propose AirMPA, a decoupled autoregressive framework for meteorology-to-pollution forecasting. AirMPA predicts 13 atmospheric pollutants at 0.4° spatial resolution and 12-h temporal resolution using meteorological fields, emission priors, and historical pollutant concentrations. The model is built on an improved Swin-Transformer architecture with zonal release attention and dual-branch fusion, enabling more effective modeling of global transport continuity and heterogeneous pollutant dynamics. During training, AirMPA uses the fifth-generation atmospheric reanalysis from the European Centre for Medium-Range Weather Forecasts (ERA5) as meteorological forcing, while during inference…

  PDF
• arXiv cs.AIOct 19

  SAR: Learning Global Item-Space Matching and Geometry-Aware Placement Ranking for Buffered Online 3D Bin Packing

  Xinpeng Lei, Jin Zhang, Yizhe Yang, Yihong Duan, Fucheng Wan

  Online 3D bin packing with a bounded buffer requires irreversible item-selection and placement decisions under limited knowledge of future arrivals. Feasibility alone is insufficient, as feasible actions can produce different residual-space structures and subsequent packing opportunities. A central architectural question is how to allocate spatial reasoning between item selection and placement evaluation. We propose Spatial Affordance Retrieval (SAR), a novel learning-based framework that coordinates global item-space matching with geometry-aware placement ranking. A voxel-token spatial encoder represents 3D container occupancy, enabling a picker to match buffered items to the residual space without requiring item-specific placement proposals as inputs. After item selection, a loader ranks feasible rotation-position candidates using candidate geometry, local geometric features (LGF), and inter-candidate comparison, without directly accessing global spatial tokens. The feasible candidate set connects the two stages, which are jointly optimized under a shared long-horizon packing return. On the Random, JD, and SF datasets, the best SAR variants improve utilization over the…

  PDF
• arXiv cs.CLOct 19

  CoMem: Learning to Anticipate Failures from Retrieved Experience

  Yun Shen, Ming Shen, Tianjun Yao

  Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the same explanation for failure. Cross-task reflective memory addresses this in two forms: retrieved memory keeps past experience explicit and looks up related cases, which is specific but bounded by the bank, and parametric memory internalizes experience into parameters, which generalizes but is grounded in nothing beyond the task description. When both are used, existing agents combine them additively, feeding their outputs to the solver side by side, so retrieved experience never changes what the learned memory produces. We introduce CoMem (Compounding Memory), which makes retrieved experience an input to the learned memory itself, at training and at inference. The agent builds a bank of its own successful and failed reflections, learns from retrieved cases to write failure hypotheses, candidate explanations of how an attempt is likely to go wrong, and at test time reasons from newly retrieved cases to guide each attempt. Varying the retrieved cases gives the memory different perspectives, yielding reflective…

  PDF
• arXiv cs.AIOct 19

  Can LLM User-Proxies Stand In for Humans in Reliance Measurement? Replicating Rel-A.I. with Simulated Users

  Shuai Wang, Rui Hu

  Can language-model user proxies reproduce human reliance on an AI answer across contexts? Published simulated-user studies do not establish validity for this partial-answer decision, and Rel-A.I.'s released human record omits trial-level choices. We audit its 90 printed questions and 15 domain-by-marker reliance rates using sampled decisions and counterbalanced A/B probabilities from open models through 72B parameters. A matched crossover varies the printed agent specialty within each question, separating question content, label averages, and their interaction. Mistral Small's strong-marker math-minus-law label marginal is -0.4 percentage points, yet matching the agent label to the question domain raises reliance by 13.3 points on average across the five domains. The best A/B proxy has 22.5-point absolute-rate error and 8.3-point domain-effect error against the human table. A two-sample independent-binomial human replication has 3.5-point expected domain-effect error under the stated working model. The interaction is model dependent, and inference layout changes identical-prompt probabilities. This single-study audit does not establish proxy validity for human effect sizes or…

  PDF