TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3142Multimodal534Agents532Frontier LLMs468Inference & serving266Image segmentation181Graph learning1683D scene160Learning verifiable rewards150Voice AI93Classifier & causal discovery88Forecasting time78Flow matching75Teacher policy distillation55Machine learned interatomic53Adversarial training50All 23 fields

Open problems across fields

  • Compositionality in RAG pipelines1 paper raises it · 1 addresses it

    Combining individually strong RAG components often fails to improve overall performance, and gains may not transfer across retrieval quality and answer faithfulness.

    • Retrieval Augmented Generation Compositionalityraises · addresses
  • Request execution in streaming video generation1 paper raises it · 0 address it

    Models struggle to reliably follow incremental multimodal requests while maintaining state consistency and visual fidelity.

    • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
  • Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

    Evolving execution harnesses may demand behaviors the model has not learned or restrict existing capabilities.

    • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
  • Length generalization in state tracking1 paper raises it · 1 addresses it

    Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

    • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
  • Evidence-grounded evaluation for audio-visual reasoning1 paper raises it · 1 addresses it

    Existing benchmarks often allow models to answer correctly without analyzing necessary audio-visual evidence, weakening reliability.

    • EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoningraises · addresses

Named by an AI from these papers' abstracts.

Papers

  • arXiv cs.CLOct 15▲ 710

    PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

    Dingjie Song, Zhiling Yan, Ziqian Zhang, Yuxuan Zhang, Lichao Sun

    Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says. We introduce ReviewFact, a benchmark that labels such factual errors in review comments under one definition across NLP, machine learning, and the natural sciences, and that measures cost and latency alongside accuracy. A frontier LLM checks comments well but must read the whole paper for each check, while cheap decision models, which score whether a statement holds in a text, fall far short on whole comments that mix several implicit assertions. PremiseCheck is a framework that combines the two. An LLM rewrites each comment as explicit premises without reading the paper, and a decision model checks each premise against the paper. When each comment is checked on its own, PremiseCheck reaches accuracy comparable to GPT-5.5 across all three fields at about half its cost, and on NLP reviews at a quarter of its cost and less than half its latency.

    CodePDF
  • arXiv cs.AIOct 15

    Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents

    Mohamed Abouzahra

    Tool-using language agents must revise prepared actions when evidence changes or authority is revoked. Selective withdrawal means suspending affected actions, preserving supported work, and resuming only after sufficient repair. We study supervised fine-tuning in NAQD-Env, a synthetic environment with explicit dependencies and a deterministic reference policy. Four LoRA checkpoints of Qwen2.5-3B-Instruct compare an original curriculum with an enriched one, the latter under three system-prompt framings with identical views and targets. Three instruction-tuned baselines and all four checkpoints are evaluated under three inference prompts on fresh validation cases, held-out dependency families, and held-out structural combinations. Under the naqd prompt, SFT checkpoints reach decision agreement of 0.77-0.92 and withdrawal recall of 0.46-0.86, versus 0.45-0.63 and at most 0.06 for the baselines. Rule-level diagnostics qualify these gains. The original-curriculum checkpoint wrongly withdraws 26 of 34 actions with surviving alternative support; enriched checkpoints withdraw 0-1. Conversely, all SFT checkpoints narrow prohibited combinations less often than the 7B and 8B baselines, a…

    PDF
  • arXiv cs.CLOct 15

    ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews

    Zhaoqian Xue, Shaoze Zhou, Xuexin Li, Junting Mu, Haozheng Liu +8

    Systematic literature reviews follow the PRISMA process of screening scholarly works and extracting evidence from included studies. Deep research tools based on large language models (LLMs) can search and summarize the literature but do not record which studies are excluded or where extracted values come from. We develop a conversational multi-agent system called ReviewPilot that automates the PRISMA workflow from paper screening to information extraction. Researchers can tailor criteria and schemas through dialogue, and a project memory keeps their configurations and revisions. Each screening decision comes with its reason and each extracted value with its source. On epidemiological expert reviews, ReviewPilot outperforms a single-prompt LLM and AgentSLR across three LLMs, with screening macro F1 up to 0.776 and extraction F1 up to 0.788. Case studies in biomedicine and human-computer interaction show close agreement with human annotators, suggesting that ReviewPilot can transfer beyond epidemiology. Code is available at https://github.com/ZhaoqianXue/ReviewPilot.

    PDF
  • arXiv cs.AIOct 15

    Recursive Reward Improvement via Adversarial Meta-Prompt Evolution

    Wei Dai, Qianchu Liu, Guanghui Qin, Xing Han, Tristan Naumann +2

    Recursive Self-Improvement (RSI) has gained wide attention for its ability to work with limited data. In a proposer-solver loop, a proposer model writes training tasks and a solver model learns to solve them through reinforcement learning. Such loops have succeeded in mathematics and coding, where every answer can be checked automatically. Open-ended expert tasks, like clinical report generations, have no answer key, which makes simple question-answer generation not viable. Here the proposer must also write a rubric that lists the content an answer should include and the errors it should avoid. However, the unique challenge behind model-written rubric is the comprehensiveness of it. For naively generated rubric, solvers tend to exploit it, naming the expected topics without the substance behind them, which corrupts the learning process. To solve this problem, we introduce RRI, Recursive Reward Improvement, which uses a reward hacking adversary to supervise the reward. Before the solver trains on a generated task, an adversary writes an answer that games its rubric while being as useless as possible, the same model writes an honest answer without seeing the rubric, and up to two…

    PDF
  • arXiv cs.LGOct 15

    INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples

    Sara Rezaeimanesh, Chad Klochko, Kundan Thind, Mohammad Ghassemi

    Machine learning models for tabular prediction typically assume that training data are representative of the population on which they will be deployed. In practice, however, data are often collected based on convenience, availability, or cost, resulting in systematic sampling biases that can distort feature--target relationships and undermine real-world generalization. Existing tabular distribution-shift benchmarks primarily construct out-of-distribution (OOD) settings by partitioning observations across naturally occurring domains. While such partitions may induce changes in P(Y | X), the resulting shifts are neither explicitly controlled nor isolated, and the evaluation distributions themselves are often not representative of the broader target population. We introduce INCONVENIENT, a benchmark designed to study robustness to convenience-sample bias. Rather than relying on naturally occurring domain partitions, INCONVENIENT directly perturbs feature--target relationships in the training distribution while preserving the original population distribution as the deployment environment. This setting more closely reflects real-world scenarios in which models are developed from…

    PDF
  • arXiv stat.MLOct 15

    Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy

    Mohammad Afzali, Hassan Ashtiani, Sivan Sabato

    We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariate distributions that can be approximated by piece-wise polynomials. This gives the first sample-efficient LDP learners for several distribution classes, including mixtures of log-concave distributions, such as Gaussian mixture models (GMMs). These learners also provide agnostic guarantees and are computationally efficient. We also prove a lower bound for learning GMMs under LDP, improving on the standard pure-DP packing lower bounds of Bun et al. [BKSW19]. To obtain our general learning framework, we develop an efficient non-interactive LDP algorithm for synthetic data generation over large domains, which may be of independent interest. We then use it together with a deterministic adaptation of the non-private piecewise polynomial learner of Acharya et al. [ADLS17].

    PDF
  • arXiv cs.IROct 15

    Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval

    Yingtao Luo, Kangyi Zhao, Shiyi Du, Yubo Li

    Reasoning-conditioned embeddings can improve retrieval by progressively refining semantic constraints. However, additional reasoning may introduce over-generalized or semantically noisy abstractions that weaken retrieval specificity. Existing methods largely supervise reasoning through final retrieval outcomes, providing limited guidance over the refinement process itself. We propose AURA, a framework that directly supervises intermediate reasoning states according to how well they separate relevant documents from hard distractors. AURA further trains a lightweight utility estimator over prefix-conditioned embeddings to adapt reasoning depth at inference time. On the reasoning-intensive BRIGHT benchmark, AURA-4B achieves 34.7 average nDCG@10 while using 2.8 reasoning steps and 96 generated tokens per query. Under matched deployment conditions, adaptive stopping reduces latency from 4.6 to 0.76 seconds relative to full-trajectory reasoning. Results on MS MARCO further suggest that this specialization need not substantially degrade conventional in-domain retrieval.

    PDF
  • arXiv cs.MAOct 15

    SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems

    Abhinav Kumar, Rediet Abebe, Eugene Bagdasarian, Sahar Abdelnabi

    As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent incidents have already revealed unplanned coordination between agents, highlighting the safety implications of these interactions. Yet prior studies of agent negotiation often use stylized games and simulated bargaining, leaving open how these behaviors develop during sustained, long-horizon tasks. We propose SCARCE (Shared Compute ARena for Coding agEnts), a framework in which agents solve sequences of coding tasks under individual deadlines while negotiating access to a shared execution resource. This negotiation determines when and for how long they can inspect programs, compile code, and run tests. We find that agents spontaneously develop informal institutions: persistent rules and commitments grounded in reputation, reciprocity, and precedent. These arrangements, which we call institutional behaviors, carry across tasks and influence resource allocation, with agents sometimes forgoing immediate advantages to honor earlier agreements. We develop a 21-category taxonomy of negotiation strategies and emergent norms and use it to…

    PDF
  • arXiv math.OCOct 14

    On the Last-Iterate Convergence of Clipped Gradient Methods

    Zijian Liu

    In stochastic (strongly) convex optimization, establishing last-iterate convergence guarantees for first-order methods has recently garnered increasing attention, as this not only deepens the theoretical understanding of these algorithms but also aligns more closely with practice. Notably, people have demonstrated that one of the most famous, simple, and popular methods, Stochastic Gradient Descent ($\mathtt{SGD}$), provably achieves last-iterate convergence. However, the existing results may have limited applicability, since they typically rely on strong conditions on the gradient noise (e.g., an exponentially decaying tail) rather than the more realistic heavy-tailed noise. Unfortunately, when faced with heavy-tailed noise, $\mathtt{SGD}$ is known to exhibit undesirable behavior or even fail to converge. To address the challenge of heavy-tailed noise, people have proposed $\mathtt{Clipped}\text{-}\mathtt{SGD}$, an algorithm that combines $\mathtt{SGD}$ with a simple mechanism, gradient clipping. Although $\mathtt{Clipped}\text{-}\mathtt{SGD}$ performs well in practice, its last-iterate convergence property remains highly underexplored. In this work, we prove the first optimal…

    AI20PDF
  • arXiv cs.CLFrontier LLMsOct 14▲ 3

    Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

    Matteo He, William F. Shen, Alex Iacob, Andrej Jovanovic, Xinchi Qiu +1

    When does a language model acquire a capability? Developmental studies usually answer this by tracking when models start producing the correct token. But that prediction passes through the unembedding matrix, or readout, which is itself still being learned during pretraining. We show that a model's hidden states can encode task information before its own readout expresses it, so timelines read from outputs conflate what the model encodes with what its readout expresses. To track the readout directly, we introduce parameter-trajectory crosscoding, which fits one sparse dictionary to every token's readout row at every checkpoint. Unlike crosscoders on activations, it needs only checkpoint weights. We use it to locate a narrow early window, 0.4-1.1% of the way through Pythia's pretraining, in which the readout reorganizes and WordNet word categories become decodable from its rows. By then, linear probes on the hidden states already decode task information that the model's own outputs do not yet show. To test whether such gaps depend on how fast the readout learns, we pretrain small models from scratch that differ only in the readout's learning rate. We find that raising it makes the…

    AIEvals80Code
  • arXiv cs.SDOct 14

    From Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory

    Josef Pavlíček, Martin Pelikán

    Automatic melody harmonization is often evaluated through individual compositions or data-driven corpus models. This study examines whether an explainable harmonic decision model developed for individual songs can be applied to independently collected human annotations without changing its rules. We evaluate a frozen Explainable Melody Harmonizer (EMH) on selected HookTheory excerpts containing aligned melody and chord annotations. EMH generates chord sequences from melody alone using explicit criteria for melodic compatibility, harmonic function, persistence, cadence, meter-aware segmentation, and Viterbi-like optimization. Human chords are withheld during generation and used only for post-hoc comparison. Nineteen excerpts yielded 439 evaluable harmonic segments. Exact chord agreement reached 20.50%, chord-root agreement 31.66%, and harmonic-function agreement 47.62%, with functions assessed relative to the key inferred by EMH. Decision-level analysis identified 203 segments (46.24%) where the human chord lay outside the model's candidate vocabulary and 146 (33.26%) where it was available but not selected. These findings distinguish representational limitations from differences…

    PDF
  • arXiv stat.MLOct 14

    Acceleration and its Limits in Gaussian Variational Inference

    Jaesung R. Park, Uijeong Jang, Yifan Chen

    We study whether the classical momentum-based acceleration that improves the condition-number dependence of gradient descent from $κ$ to $\sqrtκ$ for strongly convex, smooth objectives extends to Gaussian variational inference (GVI) for strongly log-concave, log-smooth target distributions. With exact Gaussian expectations, a convex composite formulation of GVI yields the classical accelerated $\sqrtκ$ convergence rate. However, when only pointwise derivatives are available, we construct a family of strongly log-concave targets for which any randomized algorithm requires $κ^{1-o(1)}$ queries to achieve a fixed objective accuracy, even when the initial objective gap is bounded independently of $κ$. Thus curvature bounds alone cannot guarantee uniform accelerated total-query complexity. We then ask which additional structure permits acceleration and give positive examples: under a Hessian-Lipschitz assumption, variance-reduced stochastic methods yield accelerated guarantees when the Hessian variation is sufficiently small. Finally, experiments on real datasets show substantial empirical speedups from acceleration across a broad range of methods.

    AI10PDF
  • arXiv eess.IVOct 14

    Deep Learning for Forest Plantation Mapping in Godavari Districts of Andhra Pradesh, India

    Snehal More, Anuj Karpatne, Valerie A. Thomas, Randolph H. Wynne

    Small-area forest plantations play a vital role in the socioeconomic well-being of farmers in Southeast Asia. Most plantations are established on former agricultural land, often on land less suitable for agriculture. Plantations that are converted from natural forest have adverse impacts on biodiversity. Mapping small-area plantations is thus important to understand the dynamics of forest cover in Southeast Asia and to study the social, economic, and ecological effects of this important land cover and land use change. While the small size of forest plantations makes it difficult to detect them using moderate resolution satellite sensors, the problem is exacerbated by the high degree of mixing between plantations, surrounding vegetation, and other land covers, which often show variegated responses in satellite signals across space and time. In this paper, we study the problem of mapping small-area forest plantations in East and West Godavari districts of Andhra Pradesh, India using deep learning methods. Remotely sensed cloud-free data from the Harmonized Landsat Sentinel-2 S10 product were classified using a pixel-level neural network and training data labeled using a field-based…

    PDF
  • arXiv cs.AIAgentsOct 14

    Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight

    Sheldon Yu, Tong Yu, Nikki Lijing Kuang, Zhendong Chu, Zhenwei Tang +4

    When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from exactly the problems it most needs to learn. The failed reasoning can nevertheless suggest what to try next. We present Replay-Selected Hindsight Distillation (RSHD), which turns failed attempts into an additional, tested source of supervision during GRPO training. The policy writes a corrective note about each failed attempt without seeing a reference answer or solution, then re-solves the problem with the note in context. A note is admitted only if its replays succeed more often than the original group did, after screening for notes that state the answer, and an admitted replay is distilled into the plain-prompt policy. Because admission is decided by fresh successes rather than by the failed rollout itself, the procedure can recover supervision from groups in which every attempt failed, and it applies equally to failures in mixed groups. Only the policy is trained, the only judge is the outcome verifier, and deployment requires no notes or extra inference. Across model families and sizes and two training domains, RSHD…

    AI60PDF
  • arXiv cs.LGAgentsOct 14

    CausalEvo: Causal Skill Self-Evolution for Health LLM Agents

    Yuchen Zhang

    Large language model (LLM) agents for health can accumulate reusable textual skills from task feedback, such as calculation criteria, measurement time points, and formula units. Deciding which skills to retain is consequential: useful rules improve later answers, while faulty generalizations propagate errors. We propose CausalEvo, a method for causal skill self-evolution that estimates the relative effects of deliberately changed skill sets while holding the model weights, feedback cases, and rule count fixed. At each evolution step, a frozen LLM proposes candidate rules, which are pooled with the incumbent skills so that the current skill set remains a feasible choice. Paired skill replacements against shared background rules are scored on the same feedback cases; least squares converts the score differences into relative skill values, and the top-ranked rules are retained, favoring incumbents on ties. A decision-loss bound separates candidate support, approximation, and estimation errors. On six MedCalc-Bench-Verified tasks with 120 held-out cases, CausalEvo achieves 60.00% accuracy, compared with 55.83% for SkillOpt and 51.67% without skills. Across the recorded training…

    AI60PDF
  • arXiv cs.CVComputer visionOct 14

    Audio-Visual Dog Identification and Tracking in Real-World Videos

    Aryahvishwa Babu, Kingsley Jin, Lillian Wang, Tuan M. Dang, Theron S. Wang +3

    Identifying individual dogs from barks in real-world videos remains challenging and largely unexplored. Solving this problem would enable long-term behavioral analysis, veterinary monitoring, and animal welfare monitoring by attributing vocalizations and behaviors to the correct individual. Real-world videos are challenging because multiple dogs may bark simultaneously, become occluded, or move in and out of view. Prior studies show that canine vocalizations and visual appearance contain discriminative identity information, but these modalities have largely been studied independently. We present a multimodal dog-fingerprinting framework combining visual identification, multiple-object tracking, and canine vocal fingerprinting to associate bark events with individual dogs while maintaining persistent profiles. The framework synchronizes bark events with tracked dogs and updates profiles using visual appearance and vocal characteristics, enabling identification despite occlusion, overlapping vocalizations, and off-screen barking. We also introduce a benchmark of 46 real-world videos containing 213 manually annotated bark events. Our framework correctly localizes the active visible…

    AIMultimodal30PDF
  • arXiv cs.AIOct 14

    Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation

    Justin M. Cheney, Clement N. Nyirenda

    Deep Reinforcement Learning (DRL) offers learned job selection for High-Performance Computing (HPC), but performance against heuristics alone does not establish value beyond action masking. Six DRL treatments are compared: Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Q-Network (DQN), each with and without masking. Three heuristics and a seed-paired masked uniform random control provide baselines across ten seeds on two real Slurm (Simple Linux Utility for Resource Management) workload traces, one homogeneous and one heterogeneous, under a common non-parametric framework. All masked treatments complete evaluation, whereas unmasked treatments are truncated. On the homogeneous trace, no masked DRL treatment significantly improves average waiting time or average and maximum bounded slowdown over the control. On the heterogeneous trace, MaskablePPO improves all three metrics relative to the control. Its average waiting time is equivalent to that of the three heuristics within a 10% margin, and its maximum bounded slowdown is 22% lower than that of Last-Come, First-Served (LCFS). MaskablePPO has the leading average waiting-time rank among complete…

    AI10PDF
  • arXiv cs.CVComputer visionOct 14

    Mind the Tail: Data Selection Through Sparse Concepts

    Ziheng Zhang, Neha Hulkund, Colin Lee, Zheda Mai, Hui Shen +5

    Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocation strategies may produce varied downstream model behavior, especially for tail concepts supported by only a few samples. Discarding them can hurt test-time robustness, while overemphasizing samples lying on category boundaries may introduce unstable training signals. This work explicitly investigates this relationship across fine-grained, spurious-correlation, and general image classification, as well as multimodal pretraining. Specifically, we use sparse autoencoders (SAEs) to extract concept activations from individual images. During selection, we accumulate the dataset-level concept support for each added sample. Applying diminishing returns to this distribution down-weights well-represented concepts and shifts the focus to the distribution tail. We then incorporate local support to find samples that reliably strengthen under-supported concepts. Empirical results show consistent improvements over strong data selection baselines across all benchmarks. We also reveal the connection between concepts our method enhances and the…

    AI40PDF
  • arXiv cs.CLAgentsOct 14

    Can LLMs Anticipate Their Cruxes?

    David Reber, James Reber, Ari Holtzman, Victor Veitch

    To use language models to help us make decisions we would like to understand the rationale behind the language model's outputs. In principle, the language model provides its rationale as part of its text output. However, the sheer volume of text makes this hard to use in practice. In this paper, we are interested in extracting the cruxes that lead a model to recommend one action over another. We take a crux to be a sub-question that a model's rollouts disagree on, where changing its value may have altered the conclusion. A crux is therefore a property of the distribution of a model's rollouts, not of any one rollout. We consider three strategies of increasing computational cost. First, we just ask a model to identify, a priori, what the cruxes of a decision will be. Second, we have the model actually go through the process of generating a response and then extract the cruxes that arose in its reasoning. Finally, we generate many responses and extract the cruxes by comparing the reasoning across the rollouts. We make this last procedure computationally tractable with cheap calls to a reranker, an estimated 86 times less compute than a judge. We then conduct an extensive empirical…

    AIEvals60PDF
  • arXiv cs.LGOct 14

    Imperfect Is Perfect: Learned Column Prefilling for Branch-Price-and-Cut

    Haoran Liu, Yu Yang

    Column generation folklore warns that initial columns hurt: a warm start may bias the dual and slow the root of branch-price-and-cut. We show the opposite once the columns are imperfect in the right way. Preloading the support of the optimal root LP, the best columns one could know in advance, fails to finish on half of our hardest instances; a pool of ordinary routes that need not belong to any optimal solution, held outside the master and priced at the current smoothed dual, speeds the root up. Because the columns need not be optimal, producing them becomes a learning task: a neural edge scorer guides a constructive generator that builds the pool in seconds. A second network predicts the initial center of Wentges smoothing from the instance file, and with it the direction of the smoothed pricing queries; the solver's own updates run unchanged. With prefill and center in place, exact pricing dominates root pricing time, so we rebuild bucket-graph labeling around its dominance test for the GPU and certify on the CPU. Inside RouteOpt, the state-of-the-art exact solver for capacitated vehicle routing, the pipeline reaches the same certified root bound in 13.2% of vanilla RouteOpt's…

    AI10PDF
Load more
PDF

Rising research topics

  • Federated learning47+4.4%
  • Adversarial training50+4.2%
  • Anomaly detectors350.0%
  • Forecasting time78−2.5%
  • Machine learned interatomic53−3.6%
  • Agents532−6.7%
  • Frontier LLMs468−7.9%
  • Classifier & causal discovery88−10.2%