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 fields2650Multimodal461Agents444Frontier LLMs397Inference & serving228Image segmentation158Graph learning1453D scene138Learning verifiable rewards121Voice AI74Classifier & causal discovery72Forecasting time67Flow matching60Teacher policy distillation47Adversarial training44Machine learned interatomic40All 23 fields

Open problems across fields

  • Reliable request execution in streaming video generation1 paper raises it · 0 address it

    Models often fail to follow incremental user requests while maintaining state consistency in real-time video generation.

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

    Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.

    • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
  • End-to-end deep search in real-world web environments1 paper raises it · 1 addresses it

    Agents struggle to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

    • Deep Search in Real-World Web Environmentsraises · 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 exploit textual or unimodal shortcuts, failing to test true multi-modal reasoning.

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

Named by an AI from these papers' abstracts.

Papers

  • arXiv cs.AIOct 14

    EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents

    Qianhong Guo, Wei Xie, Xiaofang Cai, Shuoyoucheng Ma, Chengxin Hu +1

    Static benchmarks for large language model (LLM) agents face saturation and data contamination risks, motivating continual updates to evaluation tasks. However, aggregate scores and success rates offer limited insight into specific problem-solving bottlenecks and provide limited guidance for subsequent task design. We propose EvoProbe, an evaluation-driven benchmark evolution framework that integrates task generation, diagnostic evaluation, and feedback-driven regeneration into a closed loop. It combines verifiable subtask outcome scoring with evidence-supported multi-judge trajectory evaluation and distills phase-level bottlenecks, success patterns, and failure patterns into diagnostic feedback for generating new executable tasks. Across two rounds of cybersecurity experiments, evaluations of eight models on 66 tasks reveal phase-level performance differences and common failure patterns beyond aggregate scores. In a cross-round comparison with the Examiner model set and solver configuration held fixed, all eight models achieve lower Outcome scores on the updated tasks, with relative decreases of 11.8\% in mean Outcome and 40.0\% in mean Pass\textasciicircum{}3. These results…

    PDF
  • arXiv cs.AIOct 14▲ 4

    Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction

    Lingfei Qian, Yan Wang, Xueqing Peng, Polydoros Giannouris, Nadhem Zmandar +3

    Comparing financial disclosures across languages requires identifying shared accounting concepts and recovering all numerical facts that express them. Existing benchmarks evaluate aspects of these capabilities, but provide limited insight into whether both succeed on the same multilingual evidence. In particular, it remains unclear whether language models can recognize these concepts across languages and exhaustively recover their corresponding numerical evidence from the same contexts. We introduce MULTIFINGROUND, a benchmark designed to investigate this recognition-grounding gap in multilingual financial reports. Constructed from FY2025 disclosures of 90 issuers in English, French, and Greek, MULTIFINGROUND aligns independently authored reports through a shared accounting taxonomy and provides traceable fact-level annotations. The benchmark evaluates financial fact identification, concept recognition, exhaustive fact selection, and concept discrimination without candidate labels. Across 15 evaluated models, eight API and open-weight reference models achieve 97.3-99.4\% concept recognition accuracy, yet miss at least one target fact in 26.6-41.9\% of correctly recognized groups.…

    PDF
  • arXiv cs.LGOct 14

    Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving

    Dechen Xie, Mushuang Liu

    This paper presents a comprehensive comparison of four representative reinforcement learning (RL) methods in autonomous vehicle (AV) decision-making, including: Fitted Value Iteration (FVI), Rollout Classification Policy Iteration (RCPI), Deep Q-Network (DQN), and a discrete-action adaptation of Deep Deterministic Policy Gradient (D-DDPG). The four methods are applied to the same AV decision-making problem at an unsignalized intersection and are compared in terms of optimality and safety, training stability, and training and decision cost. RCPI is the closest to a reference solution and has the most stable training process. However, it is the least data-efficient. D-DDPG reaches the second-smallest gap to a reference solution with the highest data efficiency, but has the least training stability. DQN is the most stable model-free method but has the highest collision rate. FVI achieves a lower collision rate than DQN, but is less data-efficient and less stable. Based on these results, we provide suggestions for selecting a method according to whether a model is available, the budget for training, and whether stable training is required.

    PDF
  • arXiv cs.CLOct 14

    How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs

    Shuyuan Zheng, Yun-seo Lee, Xing Gao, Jialu Wu, Jiabao Hu +5

    Legal reasoning is a fundamental capability for large language models (LLMs) to complete legal AI tasks such as legal judgment prediction. In legal practice, this reasoning is shaped by legal philosophy: a judge's view of the nature and sources of law guides how legal materials are interpreted and applied, so judges working from the same statutes and precedents can reach different judgments. Existing research has largely overlooked whether LLMs can understand legal philosophy and apply it in legal reasoning, an ability we call \textit{legal-philosophical reasoning}. To fill this gap, we introduce LePhilBench, a benchmark for evaluating the legal-philosophical reasoning of LLMs that comprises two benchmarking tasks and a dataset. The two tasks evaluate how well LLMs understand legal philosophy and how well they apply it in legal reasoning, respectively. The dataset is manually and meticulously constructed. Its test set contains 220 U.S. Supreme Court opinions. A law professor designed fourteen annotation questions on legal philosophy, and three law-trained annotators with formal training in jurisprudence answered all fourteen questions for every opinion, yielding 9,240…

    PDF
  • arXiv cs.AIOct 14▲ 9

    Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach

    Jiarui Qin, Junjie Huang, Yunjia Xi, Di Yin, Yong Yu +3

    Agentic capabilities are increasingly important for modern LLMs, yet remain difficult to evaluate during pretraining. Existing approaches typically rely on static trajectory-derived tasks or likelihood-based proxies, which are lightweight but provide limited visibility into how base models behave in interactive environments. We introduce ASAP (Agent Scaffold Adaptation for Pretraining Evaluation), a lightweight framework for eliciting and evaluating agentic behavior from pretrained base models on end-to-end tasks. Rather than converting base models into chat-style agents, ASAP preserves the completion interface and adapts existing agent scaffolds through structured trajectory continuation, short reference prefixes, and minimal recovery mechanisms. Across software-engineering and deep-research benchmarks, ASAP yields discriminative end-to-end performance across base models and pretraining checkpoints. Beyond aggregate scores, ASAP exposes model-generated execution trajectories, enabling analysis of exploration, editing, testing, recovery, and task completion across training stages. These trajectories provide a behavioral view of how agent-relevant capabilities change during…

    PDF
  • arXiv cs.CVOct 14

    VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness

    Zihao Lin, Haoyu Dong, Haobo Xu, Chi-Chih Chang, Xuying Ning +8

    LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory. Recursive harness evolution can automate their design, but how it can reliably discover generalizable systems from limited, noisy, and repeatedly reused feedback remains unclear. We study this question in agentic video understanding, where rich multimodal evidence and coupled mechanisms make harness optimization challenging. We first introduce VHarness-BRSI, a recursive self-improvement framework that evolves video harnesses around a frozen vision-language model. Analyzing over 4,000 evolved candidates, we find it competitive with hand-engineered systems but identify three interconnected failure modes: validation overfitting, search-budget dilution, and the early-experience trap. We trace all three to a common root: the same imperfect validation evidence drives both harness revisions and the proposer's search strategy. We therefore propose VHarness-SRSI, an evidence-governed framework in which every search decision rests on evidence that is transferable, sufficient, and gathered before the search commits. It…

    PDF
  • arXiv cs.AIOct 14

    Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training

    Anshu Raina, Peyman Razaghi, Yuankai Chen, Cheng Yao, Yao Fu +5

    Configuring distributed LLM training across hundreds of GPUs requires jointly optimizing tensor, pipeline, expert, context, and data parallelism alongside micro-batch size, recomputation, sharding, and overlap, a combinatorial space where memory legality can hinge on a single byte of activation accounting. Today, teams navigate it through expensive multi-node trial and error, burning GPU-hours on crashes and suboptimal recipes. We present Primus Projection, which closes this loop with two coupled components. First, a hybrid projection engine that measures what it can and simulates what it cannot: GPU microbenchmarks on as few as a single device capture compute kernels and any in-scope communication; a sub-node downscale-measure-upscale workflow analytically restores out-of-scope collectives, FSDP overlap, and the full pipeline schedule at the multi-node target. A pure simulation mode runs entirely on CPU, enabling pre-silicon planning without any GPU. Second, the Primus Tuning Agent treats the projection engine as a fast scoring oracle (seconds per candidate instead of tens of minutes) and uses it to drive an intelligent search over the configuration space. A deterministic seed…

    PDF
  • arXiv cs.AIOct 14▲ 6

    AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety

    Chenxu Wang, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Cheng Jin +2

    Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. However, malicious content embedded in user queries, tool descriptions, or environment observations can manipulate their decisions and induce unsafe actions. Adversarial co-evolution has emerged as an effective approach to strengthening LLM safety, but existing work primarily focuses on language-level safety or indirect prompt injection in web tasks. In this paper, we introduce AgentSafeEvo, a co-evolutionary reinforcement learning framework for agent safety built on an attacker-defender game spanning diverse tasks and attack types. The attacker learns to construct adversarial agent tasks that expose weaknesses in the defender's tool use, while the defender learns to complete tasks safely under these attacks. We further introduce learnability-guided task weighting, which uses within-task defender-reward variability to adjust each task's contribution to attacker and defender updates. Extensive experiments on agent safety and general capability benchmarks demonstrate that our method improves adversarial robustness while maintaining general agent capabilities.

    PDF
  • arXiv cs.ROOct 14▲ 9

    From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents

    Yue Zhang, Han Lin, Zun Wang, Yidong Huang, Zaid Khan +1

    Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn. Existing environment-generation pipelines largely optimize generic properties such as realism, diversity, or task coverage, while different pretrained policies can fail for different environmental reasons. We therefore introduce WEDGE, a framework for weakness-guided navigation learning in which the failure modes of a pretrained agent guide the generation of training environments at each adaptation round. Given a pretrained policy, WEDGE uses an LLM to propose executable weakness features from contrasting successful and failed rollouts, automatically validates them on the diagnostic set, and selects the strongest validated weakness based on its success-rate gap. The validated weaknesses are then mapped to the environmental factors that control them. WEDGE varies these factors to construct environments in the difficulty regimes where the policy struggles, producing targeted training experience for adaptation. Across three navigation agents with different adaptation mechanisms, we find that policies exhibit distinct…

    Code
  • arXiv stat.MLOct 14

    Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields

    Jiankun Lei, Tian Qi

    Posterior inference for random fields from sparse observations presents two major challenges: accurately characterizing complex spatial uncertainty and preventing conditional sampling costs from growing substantially as the spatial grid is refined. To address these challenges, we propose latent annealed posterior sampling (LAPS). LAPS first maps the random field into a latent space with reduced dimensionality, while a coordinate decoder composed of Branch and Trunk networks enables field evaluation at arbitrary spatial locations. Flow matching is then used to learn the latent prior distribution. Based on this learned prior, posterior sampling is performed entirely in the latent space, with the observation likelihood incorporated progressively through an annealing procedure. To control local covariance inflation, we introduce a variance-preserving (VP) bridge that allocates a covariance budget between the transported latent state and a Gaussian perturbation. Numerical experiments demonstrate that LAPS accurately approximates posterior distributions, preserves distinct posterior modes, and reduces the dependence of conditional sampling costs on spatial resolution. Across two…

    PDF
  • arXiv cs.CVOct 14▲ 8

    WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding

    Chenxu Wang, Hangyi Kuang, Bo-Wen Yin, Yuxuan Li, Quan-Sheng Zeng +4

    MLLM-based detectors formulate vision-language grounding as autoregressive coordinate generation, yet in dense scenes, they often collapse into a box repetition loop, repeatedly emitting identical boxes until the decoding budget is exhausted. We trace this failure to historical-answer attention takeover: Under full-history autoregression, repeated coordinate tokens in the growing answer history attract disproportionate attention, crowding out the attention sinks needed to attend to new visual evidence. % To break this loop, in this paper, we propose \textbf{Compressed Window Auto-Regression} (WinAR). This new mechanism partitions a long answer sequence into consecutive generation windows and restricts full token-level autoregression to the current window only while compressing each previous window into a fixed set of latent tokens that condition subsequent decoding. This design reduces the repeated exposure to raw historical coordinates that triggers the attention takeover, yet preserves cross-window dependencies essential for coherent multi-object generation. On RSDense, which contains 200-2,000 objects per image, our model WinARDet improves RexOmni F1-score (IoU=0.5) from 32.16…

    Code
  • arXiv cs.PLOct 14

    Recursive Formation and First-Class Reuse of Compositional Capabilities

    Hang Lin

    We introduce FormCraft, a framework for representing acquired operations as first-class capabilities that can be recursively composed, directly invoked, and selectively retained in a persistent library through domain-specific verification. The framework separates capability well-formedness and public callability from later admission to persistent storage while preserving formation provenance and operational identity. We formalize recursive compositional closure over a uniform capability space and show that formed composites can be reused through the same public interface without re-forming their historical derivation. Experiments across continuous, discrete, propositional, and sequence domains demonstrate instance-independent reuse, independent checking, persistent acquisition, and reduced reuse-time search work under first-class exposure.

    PDF
  • arXiv cs.LGOct 14

    W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition

    Yogesh Prabhu, Loki Natarajan, Jingjing Zou

    A major challenge in wearable device activity recognition is the heterogeneity across datasets in sensor placement, channel count, sampling rate and subjects. Moreover, the motion patterns that distinguish activities often appear as subtle, scale-specific variations within otherwise similar waveforms. As a result, raw signals are often ambiguous, and models trained on them tend to rely on cues specific to a particular sensor setup or participant, which limits both cross-dataset transfer and generalization to unseen participants. Addressing this requires representations that preserve such activity-relevant, scale-specific variation. We introduce W-JEPA, a self-supervised framework that exploits the multiscale structure of inertial motion and leverages a joint-embedding predictive architecture, by organizing windows into a fixed grid of wavelet tokens indexed by scale, sensor axis, and time. These wavelet tokens help expose activity-specific detail within broadly similar raw signals, and serve as the units of masked latent prediction. W-JEPA predicts masked token representations supplied by an exponential-moving-average (EMA) target encoder. Because recovering a masked token…

    PDF
  • arXiv cs.CLOct 14

    ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models

    Zhaoyan Jia, Chengwei Zhou, Gourav Datta, Massoud Pedram

    Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open challenge. Any-order generation can suffer from entropy degradation, which narrows the reasoning paths available for exploration. Recent work mitigates this issue by applying standard GRPO with left-to-right generation. However, independently generating every rollout from the input prompt can leave alternative continuations from intermediate states underexplored, while trajectory-level advantages assign uniform credit to all tokens without distinguishing the contributions of individual reasoning segments. We propose ForkGRPO, an RL framework that couples efficient exploration with fine-grained segment-level credit assignment. It samples multiple continuations from high-entropy intermediate states along a reference trajectory, prioritizing textual boundaries and reusing shared prefixes. The continuations provide complementary learning signals: within-state group-relative advantages guide which continuations to reinforce, while Monte Carlo state-value differences indicate which reasoning segments improve expected outcomes. Among the…

    PDF
  • arXiv cs.CLOct 14

    Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers

    Josh Barua, Kyle Mahowald, William Rudman

    Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g., a "blind faith in text"--but why preferences vary across models, domains, and input conditions remains unclear. We develop a predictive account from a Bayesian perspective, positing that VLMs combine conditionally independent evidence from each modality with prior beliefs, subject to modality-specific biases. The resulting two-parameter cue combination model accurately predicts VLM preferences under unseen combinations of input degradation and transfers to new forms of unreliability without refitting. Separating evidence strength from integration bias explains how VLMs can follow text even while weighting visual evidence more heavily, reconciling reports of text and vision dominance under a single combination rule.

    PDF
  • arXiv cs.DCOct 14

    Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off

    Javad Mirzaei, Jeebak Mitra

    Large Language Model (LLM) serving systems must balance latency and throughput while efficiently utilizing distributed GPU resources. This challenge arises because inference consists of two fundamentally different phases: prefill, which determines time-to-first-token (TTFT), and decode, which determines inter-token latency (ITL). The use of tensor parallelism (TP), pipeline parallelism (PP), and hybrid configurations exposes different trade-offs between these latency dimensions, making the optimal parallelism configuration highly dependent on workload characteristics, latency requirements, and context length. Moreover, despite the widespread adoption of distributed inference, there is still limited understanding of how parallelism configurations should be selected under varying workload conditions and service-level objectives (SLO). In this paper, we develop a systematic framework for characterizing LLM inference parallelism via throughput-latency trade-offs, SLO-aware serving, and long-context scalability. We introduce the notion of parallelism operating regions by constructing TTFT-ITL feasible sets and Pareto frontiers across different workload compositions, thereby revealing…

    PDF
  • arXiv cond-mat.mtrl-sciOct 14

    ActMOF: Mapping Reticular Synthesis through Active Learning

    Hongrui Sheng, Shutian Liang, Reid A. Coyle, Shyam Chand Pal, Peter Walther +3

    Reticular chemistry allows metal-organic frameworks (MOFs) to be designed from their building units, yet their synthesis remains constrained by sparse experimental data, noisy crystallization outcomes, and the absence of benchmarks for comparing active-learning strategies. While data-driven approaches such as Bayesian optimization (BO) can improve synthesis success rates, selecting appropriate optimizers beforehand for mapping MOF crystallization landscapes remains largely empirical. Here we present ActMOF, an experiment-grounded benchmark for comparing search strategies in aluminum-carboxylate MOF synthesis. ActMOF is emulated from experimentally measured microwave syntheses with each encoded condition assigned a crystallinity index calculated based on diffraction peak intensity and full width at half-maximum. By benchmarking policies guided by Gaussian processes (GP), tree ensembles and large language models (LLM), ActMOF placed the GP family among the leading policies for active learning in sparse synthesis landscapes. It then demonstrated transferability by guiding the microwave synthesis of six reticularly related aluminum MOFs. All six campaigns gave crystalline products…

    PDF
  • arXiv cs.LGOct 14

    Train to Stitch: Topology-Preserving Regularization for Interoperable Representations

    Akshay Malhotra, Nicolas Zilberstein, Shahab Hamidi-Rad

    As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to be seamlessly combined with little or no direct communication between them. Take autoencoder-based data compression as an example: the ability to independently choose architectures and train encoder and decoder models, while still ensuring they work together, could fundamentally transform how such models are built, deployed, and updated. In this work, we introduce a novel approach that leverages topological regularization to align the latent spaces of two independently trained autoencoder models, entirely eliminating the need for coordination during training. We provide a conditional theoretical analysis showing how the structural agreement encouraged by our regularizer can translate into approximate geometric compatibility between independently learned representations. Reconstruction experiments validate this approach empirically, substantially narrowing the interoperability gap across multiple datasets.

    PDF
  • arXiv cs.CLOct 14

    KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?

    SungHo Kim, Eojin Jeon, SangKeun Lee

    Korean neologisms arise through diverse mechanisms, a demanding test of language models beyond lexical memorization. To enable systematic evaluation, we introduce NeoTrace, an automated, rerunnable framework that collects and dates neologisms across genres. Its 4,271 entries support KoAGE, a cutoff-aware benchmark with three acquisition and two generation tasks---the latter, to our knowledge, the first to compare model coinages with attested neologisms under their original materials and community context. Across 21 models, lexical recall diverges from contextual inference: in a five-model temporal analysis, models define only 13-30% of cutoff-year words, yet can infer meaning from one usage. However, structural understanding remains limited: even correct definitions barely improve formation analysis of pre-cutoff neologisms. Given word-building materials, single models often follow human formation mechanisms, whereas multi-agent coinage favors abbreviation and depends on interaction framing. KoAGE thus separates what models know, learn from use, and coin.

    PDF
  • arXiv cs.AIOct 14▲ 5

    SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning

    Dingyi Rong, Yue Shi, Chaofan Ma, Zongrui Wang, Jiezhang Cao +3

    Long-horizon agentic RL is constrained by the futures visited by the current policy. When rollouts fail to reach useful behaviors, improved credit assignment cannot provide supervision for states and actions that were never encountered. On-policy distillation (OPD) introduces teacher guidance on policy-induced states, and recent multi-turn variants improve how this guidance is scheduled, replayed, refined, or validated. However, they do not directly use the oracle-controlled future itself as the training trajectory. We introduce \textbf{State-Rooted Executable Rollout Optimization (SERO)}, which augments on-policy agentic RL with executable oracle continuations. SERO restores a state actually reached by the current policy and lets a training-only oracle continue interacting with the real environment, making the downstream observations and oracle actions themselves available for learning. It then applies \textbf{policy-reachability weighting}, which weights each oracle step by the frozen behavior policy's compatibility with the preceding oracle actions. This allows deeper supervision to become effective as the policy becomes more compatible with the oracle branch. The oracle loss…

    PDF
Load more
PDF
PDF

Rising research topics

  • Adversarial training44−10.2%
  • Federated learning40−11.1%
  • CAD models13−13.3%
  • Forecasting time67−15.2%
  • Anomaly detectors30−18.9%
  • Inference & serving228−23.5%
  • Frontier LLMs397−23.8%
  • 3D scene138−23.8%