跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1295新增论文
+1026其中 AI 相关
+111已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 16:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 16:24 — 2026-11-17 16:24(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 16:10库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,122 已收录论文20,967 AI 相关7,309 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 25,122 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v3arXiv:2601.20250

Fast Statistical Rates for Flow Matching without Curvature Assumptions

Hari Krishna Sahoo, Mudit Gaur, Vaneet Aggarwal

原文摘要

Flow-based generative models have emerged as an efficient alternative to diffusion models. We study the sample complexity of learning a target distribution in Wasserstein distance via flow matching, which learns a velocity field transporting a base distribution to the target. Under exact empirical risk minimization over a fixed network class and standard assumptions on the architecture and data distribution, we show that any squared-loss flow-matching variant including rectified flow with bounded derivatives achieves $\widetilde{O}(\varepsilon^{-2})$ sample complexity for the statistical term with the Wasserstein guarantee taking the form $W_2 \le K(\varepsilon + C\varepsilon_{app})$, where $\varepsilon_{app}$ is the approximation error of the network class. This improves upon existing $\widetilde{O}(\varepsilon^{-4})$ guarantees and does not require the Polyak--Lojasiewicz condition in the statistical analysis. Instead, we exploit a structural property of the squared-loss objective - it induces an approximate Bernstein condition that directly ties the variance of the excess loss to the excess risk up to additive approximation-error. This condition enables a localized Rademacher complexity analysis yielding fast $O(1/n)$ rates. The flow-matching schedule enters the leading statistical prefactor through the Lipschitz constant of the pointwise loss, which we characterize explicitly for standard schedules.

cs.LG · cs.AI · cs.IT · stat.ML

版本更新 · v2arXiv:2604.08711

Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup

Vrushank Ahire, Vivek Kurumanghat, Mudasir Ganaie, Lipika Kabiraj

原文摘要

The disintegration of liquid sheets into ligaments and droplets involves highly transient, multi-scale dynamics that are complex to quantify from high-speed shadowgraphy images. Identification of droplets, ligaments, and blobs formed by the breakup of a liquid sheet, and their tracking from frame to frame, is an essential part of spray analysis. Analysis of such processes poses a fundamental challenge for conventional multi-object tracking frameworks, which enforce strict one-to-one temporal associations and cannot represent one-to-many fragmentation events. We present a two-stage deep learning framework that detects droplets and ligaments and identifies their temporal relationships across successive frames, modeling ligament deformation, fragmentation, and parent-child lineage. In the first stage, a Faster R-CNN detector with a ResNet-50 backbone and Feature Pyramid Network classifies ligaments and droplets in recordings of two impinging Carbopol gel jets. A morphology-preserving synthetic data generation strategy enriches the training set without physically implausible configurations, achieving a held-out test F1 score of up to 0.872 across fourteen original-to-synthetic data configurations, with robustness tested on different atomization conditions and liquid compositions. In the second stage, a Transformer-augmented multilayer perceptron classifies inter-frame object associations into continuation, fragmentation (one-to-many), and non-association using physics-informed geometric features. Despite severe class imbalance, the model achieves 86.1% accuracy, 93.2% precision, and perfect recall (1.00) for fragmentation events on the held-out test set. Together, the two stages preserve parent-child lineage and enable extraction of breakup statistics, including fragment multiplicity and droplet size distributions, offering an automated analysis of the primary mode of atomization.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.08634

Benchmarking Machine Learning for Chaotic Three-Body Dynamics in Astrophysics

Sheng Wan, Pavan Vynatheya, Duo Xu, Li Kevin Wenliang, Ye Zhu

原文摘要

Machine learning (ML) and generative AI have recently made impressive progress in understanding physics. We explore a hierarchy of prediction problems stemming from chaotic three-body systems and benchmark existing ML approaches, including general-purpose prediction algorithms and those that build on top of foundational physics models. We first simulate the trajectories of triple systems near the critical boundary of stable/unstable initial conditions. We then design a hierarchy of learning tasks, focusing mainly on two broad problems: stability prediction and trajectory prediction. The former classifies whether a given triple system has diverged or not up to a specific horizon, while the latter predicts the exact trajectory, both given suitable input features. We benchmark a range of ML approaches, from simple regression methods to state-of-the-art foundational physics models, across these tasks, and compare them against astrophysical methods such as the Mardling-Aarseth stability criterion. Our experiments reveal a clear order of task difficulties in chaotic three-body dynamics: early dynamics enable strong stability prediction, while precise long-horizon trajectory forecasting remains difficult. Code and dataset are publicly available at https://github.com/Simonwan03/ThreeBodyMLBench.

cs.LG

版本更新 · v3arXiv:2607.02050

A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems

Yuval Ran-Milo, Angelos Assos, Elad Hazan

原文摘要

Motivated by the challenge of stabilizing a general unknown linear dynamical system (LDS) from observations, we study the natural prerequisite of online prediction. Our goal is to achieve sublinear regret with a memory footprint that adapts to the intrinsic complexity of the dynamics rather than the full hidden-state dimension. We focus on the practically central regime of systems with low instability complexity -- eigenvalues outside the real stable interval that do not decay rapidly, together with non-semisimple modes -- potentially embedded in an otherwise stable real spectrum of much higher dimension; we write $k$ for this count. This regime is the primary setting in which stabilization is plausible: we show that many systems with high instability complexity cannot be stabilized without exponentially large controls. Thus, prediction is meaningful for stabilization precisely when the instability complexity is small. Within this regime, we introduce a unified online algorithm that handles every LDS (including non-diagonalizable systems with complex or exploding modes) with a learnable parameter count of $\widetilde{O}(k)$. Finally, we prove a lower bound showing that $k$ is a valid complexity measure: any filter-based predictor needs at least $k$ filters. Experiments corroborate our theory: on a high-dimensional system, our predictor sharply outperforms prior methods at an equal parameter budget.

cs.LG · eess.SY

新论文 · v1arXiv:2611.08631

BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving

Qiren Wang, Mingyu Guo, Zixuan Wang, Weisong Shi

原文摘要

Camera-based driving models build a dense bird's-eye-view (BEV) grid and spend the same computation on every cell of it, although the vehicle crosses only a few of those cells within the planning horizon. We present BEVCast, a two-stage BEV whose resolution adapts to the predicted driving path. A coarse pass encodes the whole scene on a grid of 4.096 m cells. A heat head trained on the recorded path assigns a heat to every coarse cell and the cells with the highest heat are refined into 1.024 m cells under a fixed budget. The remaining cells keep their coarse resolution, so the trajectory head reads a mixed-resolution BEV that still covers the entire scene and needs neither an HD map nor a navigation command. Against a full grid of 1.024 m cells with the same architecture and training recipe, BEVCast at a 10% refinement budget encodes 28% of the BEV queries and needs 66% of the BEV encoder time at batch size 1. On nuScenes its mean displacement error is 1.078 m against 1.149 m and its drivable area violation rate is 1.46% against 2.29%. On NAVSIM navtest its mean displacement error is 0.577 m against 0.598 m and its extended predictive driver model score is 82.51 against 81.28. Next to published planners BEVCast reaches a comparable error on both benchmarks without a navigation command. The resolution of a driving BEV can therefore follow the task instead of the grid.

cs.CV

版本更新 · v4arXiv:2608.05466

Recursive Synthesis for Long-Horizon Terminal Tasks

Zhongzhi Li, Yucheng Shi, Zongxia Li, Ruhan Wang, Anhao Li, Jiaxi Li, Junyao Yang, Lei Ke 等 14 位作者

原文摘要

High-quality long-horizon training data for terminal agents is costly and difficult to scale, as manual authoring is expensive and direct LLM generation often produces inconsistent instructions, environments, solutions, and verifiers. We present Recursive Synthetic Terminal Tasks (RST), a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale. Starting from verified seed tasks, RST extends the reference solution, realigns the verifier and instruction to the new workflow, validates the result in a fresh sandbox, and reuses accepted tasks as seeds for subsequent rounds. Across fifteen recursive rounds, RST produces 37,484 synthesized terminal-agent tasks at roughly $0.05 per task. Task difficulty increases substantially over rounds: the median reference solution grows from 67 to 374 lines, the median number of executed commands grows from 40 to 244, and DeepSeek-V4-Pro pass@4 drops from 90% at R1 to 2.5% at R15. To demonstrate training utility, we collect rejection-sampled Qwen3.5 trajectories on the synthesized tasks and use them for supervised fine-tuning. Fine-tuning on these trajectories improves Qwen3.5-27B and Qwen3.5-122B-A10B by up to 10 points on Terminal-Bench 2, Terminal-Bench Hard, and Long-Horizon Terminal Bench, while agentic PPO lifts Qwen3.5-27B to 49.44%, 32.00%, and 22.07% on the three benchmarks, corresponding to relative gains of 20.0%, 41.2%, and 21.9% over the base model. Moreover, after 15 rounds, the recursion shows no ceiling: synthesis yield and validation rates remain stable as difficulty keeps climbing, indicating that the process can continue well beyond the scale reported here.

cs.AI · cs.LG

新论文 · v1arXiv:2611.10040

SPRING-5: Measuring Tool Documentation Repair for LLM Agents by Efficiency

Guan Zheng Huang

原文摘要

Methods that repair tool documentation automatically are mostly evaluated on task accuracy. We report a benchmark that scores them on cost. SPRING-5 is 20 tool families and 344 tasks, each with a deliberately degraded specification, a hand-written honest one, a deterministic backend and an answer key, scored on calls charged against the ideal call path. A wrong answer is charged the full call budget, so this cost index largely tracks the completion rate, and we report calls per correct task beside it, which carries no such charge. Over 2,644 baseline sessions, 54% of wrong answers arrive with no rejected call, no refusal and no retry. The benchmark carries three validity instruments. A build-time ceiling assertion requires the honest specification to reach the ideal path and fails systematically on only one family. A dud rule names the families a stronger model solves cold and catches four. A directly measured noise floor shows that two evaluations of a byte-identical specification differ by a 95% factor of 0.64 to 1.56, so about one comparison in eight crosses a conventional win threshold on noise alone, and the cheap way of estimating that floor is biased by which families happen to go unedited. Against these instruments, a schema-only method closes 1% of the baseline-to-ideal cost gap, an online self-evolution loop 13%, one batch rewrite over every training transcript 33%, and a variant given correctness labels 58%. The batch advantage over the loop is the evidence it reads: held to the loop's exposure it is no longer detectable. With five and ten tools in context the effect survives, the baseline cost does not change, and only machine-written descriptions sent calls to the wrong tool. On BFCL, 62% of held-out queries are already answered from the shipped documentation, which explains a pooled null there. Code, data and runs are released.

cs.SE · cs.AI · cs.CL

版本更新 · v2arXiv:2605.04039

Safety and accuracy diverge across deployment conditions in clinical large language models

Sebastian Wind, Tri-Thien Nguyen, Jeta Sopa, Mahshad Lotfinia, Sebastian Bickelhaup, Michael Uder, Harald Köstler, Gerhard Wellein 等 12 位作者

原文摘要

Clinical large language models (LLMs) are commonly scaled by increasing model size, context length, retrieval complexity, or inference-time compute, on the assumption that higher accuracy implies safer behavior. In medicine, where a few confident or evidence-contradicting errors can outweigh average performance, this assumption may be incomplete. We introduce Safety-Focused Evaluation of Scaling (SaFE-Scale) and instantiate it on RadSaFE-200, a 200-question text-based radiology multiple-choice benchmark with clinician-defined clean evidence, conflict evidence, and option-level labels for high-risk error, unsafe answer, and evidence contradiction. Thirty-four local LLMs were evaluated across six deployment conditions spanning closed-book, evidence-grounded, standard and agentic retrieval- augmented generation (RAG), and max-context prompting. Clean clinician-written evidence, used as an upper-bound, produced the strongest joint gain, raising mean accuracy from 73.5% to 94.1% and reducing high-risk error from 12.0% to 2.6% and dangerous overconfidence from 8.0% to 1.6%. Standard and agentic RAG, max-context prompting, and inference-time compute improved selected metrics but did not reproduce this safety profile. Clinically, consequential errors concentrated in a small subset of questions, and variance decomposition placed deployment condition above model family on every safety metric. Within this evaluation, clinical LLM safety did not track accuracy scaling but emerged as a deployment-level property.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2608.06630

The Sparsity Whisperer

Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit

原文摘要

Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We argue that this overlooks a key computation performed by particularly sparsity-sensitive neurons in the MLP up and gate projections: separating similar inputs into dissimilar outputs. This suggests that effective pruning should preserve not only activations, but also the differences between outputs more broadly. We introduce a family of difference-informed pruning methods built upon this principle. Wisp+ is a neuronwise, update-free method that prioritizes the input pairs each neuron separates most strongly relative to their distance. Wisp provides a more efficient layerwise alternative that scores weights using shared input-difference norms. Finally, Whisper extends global difference preservation to second-order reconstruction using a lightly regularized difference Hessian. Across Llama 2 and 3.1 models from 7B to 405B parameters, our second-order variant consistently improves over strong reconstruction-based baselines, while our update-free variants improve over activation-aware baselines, especially in constrained settings. The improvements over Wanda and SparseGPT extend to structured sparsity, downstream evaluations, and other model families. Augmenting stronger techniques such as RIA and ALPS with our difference-informed criteria yields further improvements, shifting the overall accuracy-runtime frontier outward at negligible additional cost. These results suggest that preserving output differences is a broadly useful and composable signal for post-training LLM sparsification.

cs.LG

版本更新 · v2arXiv:2606.13355

Real-Time Execution with Autoregressive Policies

Sangkyu Lee, Seohyeon Park, Tackgeun You, Avi Caciularu, Idan Szpektor, Hwasup Lim, Youngjae Yu

原文摘要

Real-time execution, enabled by asynchronous inference that ensures both smooth action trajectories and fast reactivity, is critical for realistic deployments of large-scale Vision-Language-Action models. However, recent work on real-time execution primarily focuses on variants of diffusion policies, even though it is more critical for autoregressive policies given their slower rollout speed in synchronous inference. In contrast, we demonstrate that autoregressive policies can achieve real-time execution by adjusting the tokenization horizon and applying constrained decoding, thereby guaranteeing strict latency bounds that enable multi-trajectory decoding to maximize performance. Across simulated and real-world environments, we find that the autoregressive policy consistently outperforms its equivalent-level flow-matching policy counterpart while achieving significantly improved task completion speeds from synchronous inference. Coupled with the inherent advantages of autoregressive policies, such as faster convergence and better generalizability in instruction-following, these results confirm that autoregressive policies can remain a competitive policy type supporting real-time execution.

cs.RO · cs.AI

版本更新 · v2arXiv:2603.23509

Internal Safety Collapse in LLMs and Coding Agents

Yutao Wu, Xiao Liu, Hanxun Huang, Xiang Zheng, Yige Li, Yifeng Gao, Cong Wang, Bo Li 等 10 位作者

原文摘要

LLMs and coding agents can now tackle complex, long-horizon tasks through advances in reinforcement learning, but stronger task-solving capabilities do not necessarily preserve safety alignment. Recent AI agent incidents involving reward hacking indicate how optimizing for task success can bring learned capabilities into conflict with safety alignment. In this work, we identify a critical failure mode that manifests this conflict, which we term Internal Safety Collapse (ISC). When completing otherwise benign coding tasks, AI agents can prioritize satisfying program requirements over safety constraints, generating large volumes of sensitive content, including unsafe outputs, as task data. To study this phenomenon, we introduce TVD (Task, Validator, Data), a framework for building controlled workflows that require sensitive content for completion. Through extensive experiments, we observe instances of highly harmful content that closely resemble outputs from early, unaligned LLMs in 2023. We further find that ISC can be effectively triggered even in highly capable LLMs such as Claude Fable 5. These results indicate that, despite substantial alignment efforts, frontier LLMs remain internally unsafe: safety alignment primarily reshapes surface behavior without eliminating the underlying knowledge that enables unsafe outputs. Our findings underscore the need for caution when deploying LLMs in high-stakes settings, such as scientific pipelines and autonomous agents. Content Warning: This paper contains examples of harmful content. Source code: https://github.com/wuyoscar/Internal-Safety-Collapse

cs.CL · cs.AI · cs.CR

版本更新 · v2arXiv:2611.00405

Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data

Erik Bauer, Jakob Thumm, Christopher Agia, Rohan Sinha, Chen Xu, Haruki Nishimura, Jeannette Bohg, Marco Pavone 等 9 位作者

原文摘要

Data flywheels promise continuous improvement via insights from deployment data. Understanding how the deployed model succeeds and fails can steer subsequent data collection towards patching failures and reinforcing successes. However, robot deployments create large volumes of high-dimensional rollout data, which is challenging to understand and confidently ground data collection decisions in. To make deployment data easier to analyze and act on, we propose behavior graphs, which compress policy rollouts into a single interpretable, directed graph. We construct the graphs by learning to identify similar behavior modes across rollouts, connecting the behaviors temporally, and finally linking them to outcomes. In a user study on three real-world tasks, where participants analyzed rollouts to choose a data collection strategy, 16 of 18 preferred behavior graphs to rollout videos, reaching comparable conclusions with 40.3% lower perceived temporal demand and 37.6% lower effort. Beyond interpretability for deployment data, behavior graphs are capable progress predictors: across 43 datasets, they improve the rank correlation between predicted progress and true temporal order by 22.9% and reduce mean absolute error by 53.5% relative to the strongest baseline. As the number of deployed robots grows, behavior graphs lend structure to high-dimensional policy rollouts and make deployment data easier to interpret and reason about.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.08627

Evasive subspaces, minimal rank-metric codes and subspace designs via auxiliary fields

Alessandro Giannoni

原文摘要

We extend the auxiliary-field method for scattered subspaces to evasive subspaces and subspace designs. For $1\le h\le k<hn$ and coprime $h,k+1$ with $n(k-h+1)\ge k+1$, we construct spanning $(h,k)$-evasive $\mathbb{F}_q$-subspaces of $\mathbb{F}_{q^n}^r$ of dimension $rn(k-h+1)/(k+1)$ in every sufficiently large admissible ambient dimension, with a threshold independent of $q$. When $k<n$, this dimension is maximum. The proof combines an intersection lemma, a rank-support density inequality, scalar orbit counting, and a profile preserved by direct sums. The coding consequences include, for every fixed odd extension degree $m\ge3$ and every sufficiently large $K$, minimal rank-metric codes of optimal length $2K$ with first two generalized weights $(m+1)/2$ and $m+1$. For these codes the stable profile is equivalent to minimality with the largest possible minimum distance; for even $m$ the analogous class consists of minimal MRD codes. More generally, for $1\leτ\le m-2$ and $\gcd(m,τ+1)=1$, we obtain nondegenerate $τ$-minimal codes of length $(τ+1)K$ for every sufficiently large $K$, uniformly in $q$. We also construct maximum $h$-designs whose number of members grows exponentially with the ambient dimension at fixed $q,n,h$, and the associated maximum sum-rank distance (MSRD) codes with a growing number of equal long blocks. In extension degree five, the ordinary and $2$-minimal constructions hold for every $q$ and every $K\ge32$ and $K\ge59$, respectively.

math.CO · cs.IT

新论文 · v1arXiv:2611.08626

LLM-Based Feature Extraction for Multi-Criteria Inventory Classification

Humza Akhtar, Rami Pinto

原文摘要

E-commerce supply chains generate large volumes of customer feedback and operational data that remain underutilized in inventory management. Traditional inventory classification techniques such as ABC analysis rely primarily on annual dollar usage, while multi-criteria inventory classification (MCIC) methods extend this but still depend on structured quantitative data and do not utilize unstructured information available in modern supply chains. This paper proposes an LLM-based feature extraction approach that transforms unstructured sources such as customer reviews into quantitative features using vector embeddings and LLM-generated evaluation criteria. The enriched feature set is incorporated into an MCIC framework based on the Hadi-Vencheh model. Experimental results show measurable reclassification effects when customer sentiment signals are included, demonstrating that integrating unstructured data into MCIC can enhance inventory prioritization.

cs.AI · cs.DB · cs.ET

版本更新 · v3arXiv:2602.13739

XIT: Exploration and Exploitation Informed Trees for Active Gas Distribution Mapping in Unknown Environments

Mal Fazliu, Matthew Coombes, Sen Wang, Cunjia Liu

原文摘要

Mobile robotic gas distribution mapping (GDM) provides critical situational awareness during emergency responses to hazardous gas releases. However, most systems still rely on teleoperation, limiting scalability and response speed. Autonomous active GDM is challenging in unknown and cluttered environments, because the robot must simultaneously explore traversable space, map the environment, and infer the gas distribution belief from sparse chemical measurements. We address this by formulating active GDM as a next-best-trajectory informative path planning (IPP) problem and develop XIT (Exploration and Exploitation Informed Trees), a sampling-based planner that grows a single shared tree toward multiple frontier goals, coupling exploration of unresolved regions with informative gas sampling en route. XIT draws a batch of samples from an Upper Confidence Bound (UCB) information field derived from the current gas posterior and expands the tree using a cost that trades off travel effort against information acquisition. To enable plume-aware exploration, we introduce the gas frontier concept, defined as unobserved regions adjacent to high gas concentrations, and propose the Wavefront Gas Frontier Detection (WGFD) algorithm for their identification. High-fidelity simulations demonstrate the benefits of XIT in terms of GDM quality and efficiency, and a scaled real-world experiment demonstrates its practicality. Although developed for active GDM, XIT is applicable to other robotic information-gathering tasks in unknown environments that face the exploration and exploitation trade-off.

cs.RO · eess.SY

版本更新 · v2arXiv:2609.31780

Panoptic Scene Program Diffusion Transformer

Chika Maduabuchi

原文摘要

Modern text-to-image models produce high-fidelity images but still struggle with compositional prompts that require instance identity, attribute ownership, counting, spatial ordering, and role-sensitive relations. We introduce Panoptic Scene Program Diffusion Transformer (PSP-DiT), a diffusion-transformer architecture that treats a panoptic scene program as a first-class latent variable rather than an external control signal or post-hoc parse. PSP-DiT jointly denoises image latents and scene-program latents through coupled transformer streams, while panoptic grounding and cycle-consistency objectives tie object instances, attributes, relations, and counts to visual support in the generated image. Under matched training and inference settings, PSP-DiT improves over a strong flat-text baseline across GenEval 2, SANEval-Simple, PSG-Score, and DetailMaster, with the largest gains on counting, attribute binding, role-sensitive relations, and long structured prompts. The method preserves image quality, adds modest inference overhead, and remains robust to imperfect scene programs.

cs.CV · cs.LG

新论文 · v1arXiv:2611.08615

s$^3$: Simple Scaling of Swarms via Cooperative Multi-agent RL

Kunal Jha, Gonçalo Faria, Shuyue Stella Li, Scott Geng, Faeze Brahman, Noah A. Smith, Yulia Tsvetkov, Max Kleiman-Weiner 等 9 位作者

原文摘要

Groups can achieve more than individuals in the same amount of time, but only if their members coordinate: they must decide who works on what and what to share. However, this organization in multi-agent systems today usually comes from arbitrary, static harnesses designed a priori without adapting to agent behaviors or task specifications. We ask whether agents can instead learn to organize themselves. We introduce s$^3$, the first multi-agent reinforcement learning method in which agents decide for themselves how long to work alone and when to share findings or read teammates' messages, with no predefined organization or roles. Our s$^3$ agents learn to take different approaches, read each other's work, exhibit emergent roles that complement each other in the swarm, and generalize to bigger teams. We study both coordination, where agents must combine private information, and parallel exploration, where sharing discoveries can make search more efficient. With matched training and inference budgets, s$^3$, swarms evaluated with twice as many agents as in training solve over 25$\times$ more coordination problems than the strongest baseline, and in exploration, communicating agents reduce repeated work by nearly 50% and outperform best-of-N by up to 9.4 percentage points. Rather than being designed in advance, s$^3$ enables organization to emerge from a shared goal. This opens the door to capable systems built from many models that learn to work together.

cs.MA · cs.AI

版本更新 · v2arXiv:2610.34487

A Multi-Domain Study on the Effectiveness of LLMs at Writing Property-Based Tests

M M Abid Naziri, Feiran Qin, Khush Patel, Marcelo d'Amorim

原文摘要

A property-based test (PBT) checks a property of a program on many generated inputs, but writing one takes a property, a generator of valid inputs, and an oracle. LLM-based PBT writers produce all three, yet they have been evaluated only on Python libraries. We study how two of them, Proptest-AI and Agentic-PBT, generalize to ten programs in five domains: deep learning libraries, databases, system software, compilers, and LLM serving engines. Most of these programs take text in their own language, such as queries, configurations, and programs. Agentic-PBT covers more branches than Proptest-AI on seven of the ten programs with Opus 5 and on all ten with GLM-5.3-Flash. Domain-specific fuzzers cover more of the compilers and of PostgreSQL and less of PyTorch than Agentic-PBT. We filed 180 bug reports, 44 of which duplicate reports that others filed after the models' knowledge cutoffs; maintainers have confirmed 65 of the others, in all five domains, and fixed 23. We draw lessons for building and evaluating such writers: low observability hurts them, and mature fuzzers paired with LLM-written properties could check that each feature behaves as documented.

cs.SE

新论文 · v1arXiv:2611.08613

NormGym: Evaluating Normative Competence through Social Interaction

Binze Li, Zihuan Zhang, Seokhyun Baek, Gillian K. Hadfield, Tianmin Shu

原文摘要

Normative competence, the ability to infer socially enforced expectations from interaction and adjust behavior accordingly, is essential for agents operating in unfamiliar human communities. Yet existing evaluations largely test whether agents can recognize or apply norms they may already know, rather than whether they can acquire previously unknown norms from social interaction. We introduce NormGym, an interactive benchmark for normative competence in which a newcomer must infer a hidden, arbitrary norm while pursuing its own task in a multi-agent community. Success requires distinguishing what is possible from what is permitted, inferring the norm from observed behavior and sanctions, and applying it in new situations. NormGym contains diverse norms and distinct environments, allowing systematic evaluation of current agents, including large language model (LLM) agents. We find that normative competence remains challenging: the strongest evaluated LLM achieves a joint task-and-compliance success rate of 55.3%. Our analysis reveals that models can sometimes revise their behavior following sanctions for their own actions, but struggle to use other agents' behavior and the sanctions they receive to infer the underlying norm. We further find that fine-tuning models may be insufficient to improve normative competence. These results suggest that current models lack a robust, transferable capability for acquiring normative knowledge through social interaction.

cs.AI

版本更新 · v2arXiv:2611.04678

Lower Bounds for Adaptive Relaxed Locally Decodable Codes via the Capped Horvitz--Thompson Estimator

Guy Goldberg, Tom Gur, Sidhant Saraogi

原文摘要

We prove a nearly optimal lower bound on the blocklength of general relaxed locally decodable codes (RLDCs), extending the result of [GGS26] to nonlinear encodings and adaptive decoders with two-sided error. Namely, we show that any $q$-query RLDC $C\colon \{0,1\}^k \to \{0,1\}^n$ must satisfy $n = k^{1+Ω(1/q)}$, closely matching the upper bound of $n = k^{1+O(1/q)}$ by Ben-Sasson, Goldreich, Harsha, Sudan, and Vadhan (STOC 2004). Our proof reduces showing RLDC lower bounds to estimating the output distribution of adaptive decoders. To this end, we introduce a capped Horvitz--Thompson estimator with uniformly bounded discrete derivatives on the $p$-biased cube. We establish its concentration of measure via self-bounding inequalities and control the downward bias induced by capping through a spreadness argument.

cs.CC · cs.IT

新论文 · v1arXiv:2611.08610

InstaGen: Group-Shared Importance Sampling for Fast Video Generation

Kislay Aditya Oj, Kumar Krishna Agrawal, Sri Surya Varma Datla, Aditya Desai

原文摘要

Diffusion Transformers (DiTs) are the dominant architecture for video generation, but their quadratic attention complexity results in substantial computational cost and latency. Permuted block-sparse attention (PBSA) offers a promising approach to reducing this cost by selectively computing blocks of a semantically permuted attention matrix. However, existing approaches typically select only the top few key blocks for each query block, following a top-$p$ paradigm. We find that top-$p$ selection can be highly sample inefficient in high-entropy attention regimes, which are common in video generation. In these regimes, we show that sampling can provide substantially better approximations under the same computational budget. More generally, we cast block selection as importance sampling, where the top-scoring keys form an exact set that is computed in full and the remaining keys are represented by a sample drawn in proportion to their estimated attention and reweighted by inverse sampling probability. Building on this formulation, we present InstaGen, which can be parameterized by any PBSA method: it replaces the method's block selection with an exact set plus a weighted sample. Each query cluster draws one sample shared by all its queries, so the sampled keys form blocks amenable to efficient GPU execution. In this paper, we take the SVG family of PBSA methods and show that, on Wan2.1-T2V-1.3B and Wan2.1-T2V-14B, InstaGen parameterized by SVG2 improves PSNR over SVG2 by 3.4 dB and 2 dB, respectively, at matched attention density, and by 1.6 dB and 2.2 dB at matched wall-clock time. On Wan2.1-T2V-14B, InstaGen also beats SVG-EAR by 1.1 dB PSNR at nearly the same density while running faster (1.65x against 1.48x over dense).

cs.CV

新论文 · v1arXiv:2611.08606

Just CaloCHILL: fast hadronic shower generation in a learned latent space

Henry Day-Hall, Frank Gaede, Gregor Kasieczka, Katja Krüger, Martina Mozzanica

原文摘要

Calorimeter showers are the most expensive part of detector simulation, and highly granular calorimeters, in which a single hadronic shower leaves thousands of energy deposits, make them more expensive still. We present CaloCHILL (Calorimeter Hits In Learned Latents), a generative model that does not produce these deposits one by one: instead it generates a compact summary of the shower in a learned latent space and expands it to full resolution only at the end. The complete shower, including the arrival time of every hit, is built in three stages: a flow-matching model first sets the number of hits and the earliest hit time in each calorimeter layer, a mean-flow model then generates the latent summary, and the decompressor of a variational autoencoder turns it into the full point cloud, giving every hit its position, energy and time. Sparse attention along the shower axis keeps this compression affordable for showers with thousands of hits. On positive-pion showers in the calorimeter of the International Large Detector, a proposed detector for the FCC-ee, CaloCHILL reproduces the main shower observables, including their time structure. This new model is 600 times faster than its predecessor, while improving on all accuracy metrics considered.

physics.ins-det · cs.LG · hep-ex · hep-ph · physics.data-an

新论文 · v1arXiv:2611.08486

生成式AI时代下,我们是否怀念那些精心制作图表的夜晚?对Teaser图与框架图的再思考

Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI

Xiaoqi Zhao, Youwei Pang, Kailai Zhou

AI 速读 基于摘要

作者通过对200篇论文中371幅动机图与框架图的视觉回顾和源约束修订实验,探讨生成式AI辅助科研图表设计时解释清晰度与视觉表达之间的权衡。

cs.CV

查看原文摘要

Scientific figures give research ideas a visual form through choices of abstraction, composition, and emphasis. Generative AI offers new ways to realize these choices, raising questions about explanatory clarity and purposeful visual expression. We examine these questions through a visual retrospective of 371 motivation and framework figures from 200 papers. The corpus comprises a quota-based main sample of 160 papers spanning four temporal periods and a separate purposive style-contrast sample of 40 papers. A single multimodal judge evaluates six dimensions of communication and design, with three repeated judgments per figure. We attempt source-constrained revisions of all 371 figures, of which 369 pass the recorded fidelity checks. Original-figure ratings show no uniform decline across periods. Revisions increase mean clarity ratings by 0.428 points and decrease aesthetic coherence ratings by 0.111 points on a five-point scale. Gains in the six-dimension average are larger for main-sample motivation figures than for frameworks. Case analyses show that added explanation can clarify comparisons while leaving typographic hierarchy and visual economy unresolved. These model-based findings support researcher-led design, with AI assisting exploration and authors retaining responsibility for explanatory purpose, composition, and scientific relationships. The accompanying atlas and evaluation records are available at https://ntu-ai4x.github.io/Rethinking_Figures/index_en.html.

新论文 · v1arXiv:2611.08485

接地推理在何处以及为何有用?

Where and Why is Grounded Reasoning Useful?

David Yan, Le Xue, Forrest Huang, Qiuyi Zhang, Dustin Tran, Andrew M. Dai, Yinfei Yang

AI 速读 基于摘要

作者通过思维链分析方法和消融实验,考察带坐标接地的推理在哪些视觉推理任务中真正带来收益,并提出需要不可描述视觉指代的 BrickVision 基准。

cs.CV

查看原文摘要

Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual reasoning problems. However, the benefits and limitations of grounded reasoning are understudied. We study where and why grounded reasoning is most useful. To do so, we introduce a chain-of-thought analysis method to measure how much a model uses its outputted grounding in its thinking trace and perform a detailed ablation study of a grounded reasoning training recipe. We find that grounded reasoning improves counting but shows no significant gain over baselines without coordinate grounding across a wide range of spatial reasoning and perception benchmarks. Using several synthetic tasks, we show that grounded reasoning is most useful when a task requires undescribable references, which are visual concepts that are difficult to describe in language. However, we observe that many existing visual reasoning benchmarks are solvable with only describable text references. To close this gap, we introduce BrickVision, a new benchmark that requires undescribable visual references to solve.

新论文 · v1arXiv:2611.08483

SwarmEvolve:用于进化发现与优化的潜在智能体集群

SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization

Qile Jiang, George Em Karniadakis

AI 速读 基于摘要

提出让数百个低成本智能体在潜在空间中集群推理并通过传递 KV 缓存共享信息的进化搜索框架,以加速数学与科学计算问题的程序搜索。

cs.AI · cs.NE

查看原文摘要

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a different angle. A novelty filter keeps the most distinct agent ideas by directly measuring the distances between the agents' hidden state vectors. Crossover of ideas happens naturally in latent space, as a summarizer agent receives the combined KV caches of all swarm members. On 21 problems in mathematical discovery and scientific computing, SwarmEvolve gets the highest average score and needs a median of only 3 to 8 minutes to reach the best scores that other state-of-the-art frameworks reach in 60 minutes. On several problems, SwarmEvolve with Qwen3 8B improves on the solutions that AlphaEvolve first found with frontier LLMs. Our work shows that agent swarms that communicate in latent space offer a fast, low-cost approach to program search for scientific problems.

新论文 · v1arXiv:2611.08578

HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields

Zuhao Liu, Melih Darcan, Zhengdi Yu, Riza Alp Guler, Tolga Birdal

原文摘要

We propose, HaNDF, object-conditional neural distance fields as data-driven priors for modeling the plausible hand-object configurations, in the product manifold of hand articulations. While recent unconditional generative priors showed success in modeling human pose, hands are versatile articulated bodies often found in interaction with other objects. This makes it crucial to develop a generative prior which can model the plausible hand poses conditioned on the object under interaction. To this end, our HaNDF proposes a geometry-aware, object-conditioned neural distance field, representing the plausible articulations in the zero-level set of a conditional field. We leverage tools from Riemannian geometry to (i) represent plausible hands in the zero level-set of an object-induced neural field, and (ii) project a given pose onto this field. Using HaNDF, we can also optimize for a plausible condition, determining the object under interaction. Our extensive evaluations demonstrate that our HaNDF provides a flexible and powerful prior for hand-object interaction, suitable for applications such as pose refinement, reconstruction under occlusion, and physically plausible manipulation synthesis.

cs.CV · cs.AI · cs.LG · cs.RO

版本更新 · v3arXiv:2604.13081

前向前向算法中优良性函数的选择性与形状设计

Selectivity and Shape in the Design of Forward-Forward Goodness Functions

Talha Ruzgar Akkus, Suayp Talha Kocabay, Kamer Ali Yuksel, Hassan Sawaf

AI 速读 基于摘要

系统研究前向前向(Forward-Forward)算法中优良性函数的选择性与活动形状如何影响逐层学习,并提出基于超额峰度的 burstiness 目标。

cs.LG · cs.AI · cs.NE

查看原文摘要

The Forward-Forward (FF) algorithm trains networks layer-by-layer using a local "goodness function," yet the choice of activity statistic remains an important design question. We systematically study how selectivity and activity shape affect FF learning, introducing selective goodness functions based on top-$k$ and entmax-weighted energy alongside shape-sensitive objectives based on normalized higher-order moments. In particular, we propose burstiness goodness, a parameter-free, scale-invariant excess-kurtosis objective that rewards heavy-tailed activity patterns. Our study examines goodness functions together with activation and label-injection choices across six small-image datasets, and uses controlled experiments to isolate their effects. In validation-tuned, five-seed Fashion-MNIST experiments with matched ReLU activation, standard label injection, and per-layer scoring, burstiness improves accuracy from $73.2\pm0.9\%$ to $88.6\pm0.4\%$ over sum-of-squares. On CIFAR-10, burstiness improves block-local ResNet-18 accuracy from $28.9\pm0.5\%$ to $46.8\pm2.5\%$ under the same separate per-block label pathway. These results show that activity-shape statistics can provide effective local learning signals across the tested settings. Code is available at https://github.com/suayptalha/ff-selectivity-shape.

新论文 · v1arXiv:2611.08478

Scientist World:为 AI 科学家构建可运行的研究世界

Scientist World: Grow a Research World for AI-Scientists

Taiming Lu, Sachin Konan, Zhuang Liu

AI 速读 基于摘要

作者提出将每篇论文转化为可执行环境,构建供 AI-Scientist 研究与训练的世界,并报告首批 1000 个已验证环境及初步评测与训练结果。

cs.AI · cs.CL · cs.LG

查看原文摘要

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an executable environment. Our autonomous pipeline extracts each paper's open-ended research question and reproduces its proposed method as the baseline; an AI-Scientist entering the environment is evaluated against what the human authors achieved. We release the first 1,000 verified environments. With the world as an evaluation, we found that frontier AI-Scientists can already surpass the human researchers 74% of the time. As a record of how AI does science, it contains 6,400 hours of research traces, with every idea, experiment, failure, and success. As a training ground, we are able to raise (+158%) a small model to match frontier models in research ideation. At last, AI-Scientists' own world has arrived, grown from and growing with science itself.

版本更新 · v3arXiv:2602.15219

多智能体家庭能源管理助手

Multi-Agent Home Energy Management Assistant

Wooyoung Jung

AI 速读 基于摘要

提出开源多智能体系统 HEMA,用大语言模型加36个领域工具支持多轮对话式家庭能源管理,并给出基于LLM模拟用户的评测框架。

cs.HC

查看原文摘要

Existing home energy management systems conceptualize occupants as passive recipients of energy information and control, which limits their ability to effectively support informed decision-making and sustained engagement. This paper presents Home Energy Management Assistant (HEMA), the first open-source, multi-agent system enabling sustained human-AI collaboration - multi-turn conversational interactions with preserved context - across diverse home energy management (HEM) tasks - from energy analysis and educational support to smart device control. HEMA combines large language model (LLM) reasoning capabilities with 36 purpose-built domain-specific tools through a three-layer architecture: a web-based conversational interface, a backend API server, and a multi-agent system. The system features three specialized agents - Analysis (energy consumption patterns and cost optimization), Knowledge (educational queries and rebate information), and Control (smart device management and scheduling) - coordinated through a self-consistency classifier that routes user queries using chain-of-thought reasoning. This architecture enables various energy analyses, adaptive explanations, and streamlined device control. HEMA also includes a comprehensive evaluation framework using an LLM-as-simulated-user methodology with 23 objective metrics across task performance, factual accuracy, interaction quality, and system efficiency, allowing systematic testing across diverse scenarios and user personas without requiring extensive human subject testing. Through demonstrations using real-world household energy consumption data, we show how HEMA supports informed decision-making and active engagement in HEM, highlighting its potential as a user-friendly, adaptable tool for residential deployment and as a research platform for HEM innovation.

版本更新 · v2arXiv:2610.31835

SAGE:临时交通管制下施工区通行路径预测的视觉-语言与几何混合框架

SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control

Jiaxi Liu, Keshu Wu, Weizhe Tang, Bofeng Cao, Sikai Chen, Xiaopeng Li, Steven T. Parker, Bin Ran

AI 速读 基于摘要

SAGE 将视觉语言模型(VLM)的轨迹作为对几何候选路径的偏好,在共享候选空间中分离路径构建、路径偏好与控制合规,以预测施工区临时交通管制下的通行路径。

cs.CV · cs.RO

查看原文摘要

Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path. Geometric predictors provide several plausible paths, yet selecting the one consistent with the temporary control remains difficult. We propose SAGE (Semantic-to-Action Grounded Execution), a read-decide-execute-check framework that separates path construction, path preference, and control compliance within a shared candidate space. The central idea is to use a vision-language model's (VLM's) trajectory as a preference over intact geometric candidates. A role-decoupled generator constructs the candidates, and rank fusion combines each candidate's geometric score with its agreement with the VLM trajectory. Supervision structured around the Manual on Uniform Traffic Control Devices (MUTCD) trains SAGE-VLM to state the lane status and hazard side before its passage decision and trajectory. The predicted hazard side enters image-space predicates derived from MUTCD provisions, which support a final intervention bounded in score and displacement. On 2,306 real-world ROADWork validation episodes, the candidates include a path within 10 px of the human demonstration in 87% of episodes, yet selection regret accounts for 53% of the geometric ranker's error. SAGE reduces average and final displacement errors by 8.3% and 12.0% relative to the ranker and hard-constraint violations by 37%. The trajectory opinion improves all four tested generator-selector combinations. SAGE is comparable to state-of-the-art VLM modules in accuracy, with a faster-responding VLM, and outperforms four other adapted driving VLMs in displacement error and safety measures. Project page: https://hhjj233.github.io/SAGE-page/.