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

+758新增论文
+578其中 AI 相关
+94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 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 05:50 — 2026-11-17 05:50(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 04:58库内论文最新更新时间:2026-11-14 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。

24,106 已收录论文20,158 AI 相关7,049 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 181 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)
新论文 · v1arXiv:2611.18562

在仿真中训练推理模型以原生使用真实机器人

Training Reasoning Models in Simulation to Natively Use Real Robots

Jiaming Tang, Zhuoyang Zhang, Junxian Guo, Fangzhou Zhao, Yilong Zhao, Zekai Li, Xingyang Li, Yuyang Zhao 等 11 位作者

AI 速读 基于摘要

作者报告,一个开放权重的27B推理模型可完全在仿真中通过强化学习(无需演示)学会原生操控真实机器人,并迁移到未见机器人与新指令。

cs.RO · cs.LG

查看原文摘要

Robot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5.2, whereas open-weight models remain substantially less capable. We show that an open-weight 27B reasoning model can be trained to use real robots natively through reinforcement learning, entirely in simulation and without demonstrations. Like a computer-use agent (CUA), the model observes the environment, reasons in a chain of thought, and generates the next end-effector pose, without any harness. We build a Post-training Engine for Agentic Robotics (PEAR) and use it to train the model on simulated robot tasks at scale with robot-use reinforcement learning (RURL), mirroring how frontier models acquire computer use. We find that the skills acquired in simulation generalize well beyond the training tasks: they transfer to an unseen robot, to the real world, and to novel instructions. After training on LIBERO and RoboDojo in simulation, the model succeeds in 60% of our trials on a real dual-arm robot, whereas the base model succeeds in none. On LIBERO, training raises the success rate from 1.6% to 74.4%, approaching GPT-6 Astra and GPT-6.1 Sol at maximum reasoning effort. Compared with $π_{0.5}$, a vision-language-action model fine-tuned on demonstrations, our model is substantially more robust to changes in the task itself. On LIBERO-Pro, $π_{0.5}$ succeeds in only 0.75% of episodes when assigned a new task in a familiar scene whereas our model succeeds in 57.4%. Finally, the model retains its general capabilities, with no measurable degradation on nine reasoning, coding and vision benchmarks. These results highlight robot-use reinforcement learning as a promising component of foundation-model post-training.

新论文 · v1arXiv:2611.18533

ModHarness-RL:将智能体强化学习中的脚手架重构为可学习且可演化的程序

ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL

Zelin He, Siyu Zhu, Jacob Helwig, Yujian Liu, Li An, Rohit Jain, Shiyu Chang, Alborz Geramifard

AI 速读 基于摘要

ModHarness-RL 将智能体强化学习中的脚手架(harness)重构为可从数据学习并随模型训练演化的程序,在 CodeSearch、ALFWorld 和 BIRD SQL 上多数设置中优于固定脚手架基线。

cs.AI · cs.CL · cs.LG

查看原文摘要

Agentic reinforcement learning (RL) increasingly relies on a harness, the scaffold around the model that decides what it sees of its own interaction and what guidance it receives. Most existing approaches train under a hand-written harness that stays fixed throughout. However, an effective harness depends on the domain, the data and the model, and keeps changing as the model trains. We introduce ModHarness-RL, which recasts the harness as programs that are learned from data and evolve as the model trains with RL. ModHarness-RL records the interaction as structured State, a set of typed blocks, and two core components of the harness are programs over these blocks, a Compression program that assembles the accumulated history into the model's context and a Steering program that supplies guidance when behavior deviates. During RL training, candidate programs are proposed from recent trajectories, verified by execution, and replayed over past trajectories, so the harness tracks how the model's behavior shifts. We study CodeSearch in depth and further analyze ALFWorld and BIRD SQL, with models from 1.5B to 8B. The proposed Compression and Steering mechanisms improve held-out performance over the fixed-harness baseline in most settings. These results suggest that a harness for agentic RL can be learned from the task's data and evolved with the model.

版本更新 · v3arXiv:2510.08697

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Terry Yue Zhuo, Xiaolong Jin, Hange Liu, Juyong Jiang, Tianyang Liu, Chen Gong, Bhupesh Bishnoi, Vaisakhi Mishra 等 40 位作者

原文摘要

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

cs.SE · cs.AI · cs.CL

版本更新 · v5arXiv:2406.15877

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Terry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan 等 33 位作者

原文摘要

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs.To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area.

cs.SE · cs.AI · cs.CL

版本更新 · v2arXiv:2401.00788

Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models

Terry Yue Zhuo, Armel Zebaze, Nitchakarn Suppattarachai, Leandro von Werra, Harm de Vries, Qian Liu, Niklas Muennighoff

原文摘要

The high cost of full-parameter fine-tuning (FFT) of Large Language Models (LLMs) has led to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear which methods provide the best cost-performance trade-off at different model scales. We introduce Astraios, a suite of 28 instruction-tuned OctoCoder models using 7 tuning methods and 4 model sizes up to 16 billion parameters. Through investigations across 5 tasks and 8 different datasets encompassing both code comprehension and code generation tasks, we find that FFT generally leads to the best downstream performance across all scales, and PEFT methods differ significantly in their efficacy based on the model scale. LoRA usually offers the most favorable trade-off between cost and performance. Further investigation into the effects of these methods on both model robustness and code security reveals that larger models tend to demonstrate reduced robustness and less security. At last, we explore the relationships among updated parameters, cross-entropy loss, and task performance. We find that the tuning effectiveness observed in small models generalizes well to larger models, and the validation loss in instruction tuning can be a reliable indicator of overall downstream performance.

cs.CL · cs.AI · cs.SE

版本更新 · v2arXiv:2609.23036

ResGraph: Cross-Model Graph-based Index Migration via Residual Reachability in ANN Search

Baoyuan Gu, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Haoyang Li, Haotian Li, Jingkuan Song 等 9 位作者

原文摘要

Approximate nearest neighbor search (ANNS) underpins large-scale vector retrieval in search, recommendation, and retrieval-augmented generation. Graph-based indexes have demonstrated state-of-the-art search performance for ANNS: they connect each corpus vector to a small set of nearby or navigationally useful vertices and answer queries by traversing the resulting graph. Because these edges are selected using construction-time distances, the graph index is tied to the embedding model; re-encoding a corpus with a new model may change distances and neighborhoods of the vectors, and reconstructing the graph for the new embedding vectors incurs substantial construction cost and delays deployment. When the embedding model changes, we observe a phenomenon in the old graph index that we call residual reachability: although derived from different models, the vectors describe the same underlying objects and often retain part of their similarity structure, which the old graph reflects as connectivity, leaving many exact new-model neighbors reachable within a few hops. Motivated by this observation, we develop ResGraph, an index-migration framework that exploits the residual reachability of the old graph index to construct the new graph index faster. ResGraph provides two migration paths. Res-Local performs parallel shallow expansion over the inherited graph index and screens second-hop candidates with packed position sign codes before exact evaluation. Res-Search uses hop-bounded beam traversal to explore beyond shallow expansion. Across eight text and image migrations, ResGraph attains up to 17.43 times speedup on constructing the new graph index than the fastest degree-matched reconstruction method while keeping competitive recalls.

cs.DB

版本更新 · v2arXiv:2610.31552

CAMGen: A Core Change-Aware Multi-View Framework for Commit Message Generation

Bo Xiong, Weisheng Chen, Zongen Ren, Yifeng Zhu, Xutian Li, Runbang Yan, Chong Wang, Peng Liang

原文摘要

Commit messages help developers understand code changes and support software maintenance. Recent approaches use repository context to improve commit message generation (CMG) with large language models (LLMs). However, existing CMG methods provide limited support for understanding how local edits affect functionality jointly implemented by multiple code entities. This functional understanding is essential for generating commit messages that explain the main change and its impact. To address this problem, we propose CAMGen, a core change-aware multi-view commit message generation framework that incorporates functional context into generation. CAMGen identifies core entities that represent the primary change intent. It then forms candidate functional units through repository-wide semantic clustering and uses those containing the core entities to construct a Functional Semantic View. This view supplies semantic context for interpreting the affected functionality. CAMGen also uses context provided by the Structural Dependency View and the Historical Exemplar View. The context from all three views is then provided to the LLM together with the code diff to guide CMG. Experimental results across three programming languages show that CAMGen outperforms representative CMG baselines, including LLM-based approaches, on most automatic evaluation metrics. Human evaluation further shows that CAMGen generates more complete commit messages with clearer explanations of change rationale and impact. These results demonstrate the value of functional context and complementary repository information for CMG.

cs.SE

新论文 · v1arXiv:2611.17776

Certified Improvements to Best-Known Thomson-Problem Configurations with a Search Pipeline Built with Large Language Model Agents

Hui Shao, Tao Wang, Xiaotian Liu, Yijie Peng

原文摘要

The Thomson problem asks for N unit charges on a sphere with minimum Coulomb energy; for large N the best configurations known are curated in the Cambridge Cluster Database, whose largest-N entries were set in October 2026. We report configurations for N = 912, 1382 and 2502 with energies 0.0036186, 0.0109730 and 0.0614033 below the database values, certified by exact integer arithmetic. All three are numerically strict local minima modulo rotations and keep the defect inventory and scar compositions of the database configurations; the database value for N = 912 had been reached by two different methods. Our search runs unconstrained replica-exchange basin hopping from the database configurations, with a shared pool of minima, recombination of improved regions after relabelling by geometry, and gradient-only polishing; replica-exchange basin hopping alone found the N = 912 and 1382 configurations, the former in one of five runs. We built and ran it with large language model agents (Claude, through a chat interface and the Claude Code agent), and we report every search, including those that failed. Two findings matter for others who search the database. Polishing alone lowers two entries by more than the threshold at which our pipeline reports a candidate, which produced two spurious records until candidates were compared with the polished database energies (the polished baseline). A local-relaxation speed-up passed its exactness test yet found nothing in a controlled comparison in which every arm with full relaxation went below the database value within 15 minutes. We distil three practices for computational discovery with large language model agents: calibrate the search code and verify candidates with code separate from the search, compare candidates with the polished baseline, and test design changes in controlled comparisons with pass criteria fixed in advance.

cs.AI

新论文 · v1arXiv:2611.17621

AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs

AI Training Platform Team, Bingwei Zhang, Jing Li, Amir Abdullin, Sihang Chen, Xin Chen, Liangjun Feng, Yingmeng Gao 等 27 位作者

原文摘要

Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to optimize existing implementations under input configurations drawn from real workloads. To address this requirement, we introduce AscendGYM, a benchmark whose initial suite comprises 48 kernels across three difficulty levels. Each kernel is paired with test cases whose data types and tensor shapes are collected from real-world training and inference tasks. Consequently, performance improvements on AscendGYM map directly to the corresponding workloads. In terms of usability, two evaluation modes are supported in AscendGYM: model evaluation and model-harness evaluation. The kernel optimization capabilities of both trained models and custom agents are allowed to be measured. It provides a complete execution environment that closely reproduces how Ascend kernels are invoked in practical pipelines. For model evaluation, it additionally includes a built-in harness equipped with search orchestration and experience accumulation. Finally, we propose a new metric, the Speedup-Token Score (STS), which quantifies performance gains relative to token cost. By jointly considering speedup and cost, STS enables the assessment of practical kernel optimization capability of a model or harness under an acceptable budget. AscendGYM is available at https://github.com/SLAI-AITP/AscendGYM.

cs.AI · cs.DC · cs.LG

新论文 · v1arXiv:2611.17044

[实验、分析与基准] LLMs 对关系数据库模式的理解与设计能力如何?

[Experiment, Analysis, and Benchmark] How well do LLMs comprehend and design relational database schemata?

Sriom Chakrabarti, Sean Bin Yang, Arijit Khan, Sebastian Link

AI 速读 基于摘要

提出 SchemaBridge 基准,评估 LLM 在 Text2Schema、Schema2Text 及模式往返转换中的保真度。

cs.DB

查看原文摘要

Large Language Models (LLMs) are increasingly used for database tasks, yet most work, such as Text2SQL, assumes that the relational schema already exists. We ask whether LLMs can design a schema from natural language requirements (Text2Schema), verbalize an existing schema (Schema2Text), and preserve its structure through a Schema-to-Text-to-Schema round trip. We present SchemaBridge, a benchmark of 902 schemata from three collections, stratified by size and constraint complexity, that scores fidelity separately for tables, attributes, domain (data types and nullability), entity, and referential integrity. Evaluating six open-weight and proprietary LLMs, we find that: (i) human-written requirements under-specify schemata, with no model exceeding 0.27 referential integrity F1; (ii) LLM-generated descriptions carry far more structure when explicitly asked to be complete, raising GPT-5.4-mini's referential F1 on SchemaBench from 0.228 to 0.909, even as BLEU, ROUGE-L, and BERTScore decrease; (iii) controlled experiments show that both constructor and describer choices influence round-trip fidelity under fixed settings; and (iv) masked schema experiments show that structural cues support recovery of keys and relationships, while joint data-type and nullability information is poorly retained through verbalization. Code and data are available at https://github.com/iamsriom/SchemaBridge

新论文 · v1arXiv:2611.16749

ORCA:Orthogonal Residual Consensus Alignment for Multi-View Clustering

Xiaojian Ding, Xian Li, Xiaoying Zhu, Lin Zhao, Kaixiang Wang

原文摘要

Deep multi-view clustering often suffers from redundant information accumulation during fusion and indiscriminate alignment across representation levels. We propose Orthogonal Residual Consensus Alignment (ORCA) to address these challenges. Its semantic incremental recurrent fusion module extracts cross-view orthogonal residuals as non-redundant increments and adaptively weights recurrent states through divergence-guided gating. Its consensus-calibrated hierarchical contrastive alignment module uses the global consensus to weight contrastive alignment of view-level, pairwise, and recurrent representations. Together, these modules balance view-specific structure with cross-view consistency. Experiments on five benchmarks against fifteen competing methods demonstrate ORCA's effectiveness, including a 5.25 percent accuracy improvement over the strongest baseline on 100leaves. Ablation studies validate both modules. Code is available at https://github.com/XiaojianDing/2026-NeurIPS-ORCA.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.24122

HAVANA: A Hierarchical Video-Action Model for Vision-Language Navigation

Dongzhihan Wang, Yi Du, Chen Wang, Xiuxian Li, Liang Xu

原文摘要

Vision-Language Navigation (VLN) requires long-horizon instruction-consistent planning and short-horizon path planning grounded in the currently observed geometry. Anticipating how future observations evolve along the instructed route provides predictive guidance beyond the current field of view, motivating video-action models (VAMs) that learn representations of future visual states. However, many existing VAMs couple future visual prediction with action generation during inference, despite their distinct temporal requirements: instruction-conditioned route guidance can be reused across multiple control steps, whereas local trajectories must continuously adapt to fresh observations. To bridge this gap, we introduce HAVANA, a dual-system VAM that decouples predictive reasoning from reactive local planning. A slow system produces a compact language-conditioned latent plan from observation history, while a fast system combines the latest plan with the current observation to generate local trajectories. Their asynchronous execution enables rapid adaptation without repeated future prediction, and no future video is generated during inference. Experiments on OmniNavBench demonstrate state-of-the-art navigation performance over prior baselines, while zero-shot real-world deployments further show robust generalization to unseen environments.

cs.CV · cs.RO

版本更新 · v2arXiv:2608.10932

CamChoreo: Benchmarking Temporally Grounded Compositional Camera Motion Understanding for Vision Language Models

Dazhao Du, Shiyan Du, Jian Liu, Yongjian Yu, Bohai Gu, Tao Han, Jie Zhang, Hualuo Liu 等 12 位作者

原文摘要

Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Existing camera motion evaluations typically assign labels to entire clips, overlooking within-shot changes and simultaneous movements. We therefore formulate camera motion understanding as temporally grounded, compositional recognition, requiring models to localize motion-consistent intervals and identify all active movements. We introduce CamChoreo, the first benchmark for this task, comprising 4,229 diverse single-shot clips with expert temporal annotations using 20 direction-aware labels. Nearly half of its segments contain compound camera motion. We also construct a separate training corpus of approximately 43K clips with the same annotation format. On CamChoreo, supervised fine-tuning (SFT) on this corpus achieves 62.1/64.1 micro F1 with 4B/8B backbones, outperforming advanced closed-source vision language models (VLMs). To complement the primarily semantic representations of VLM visual encoders with cross-frame geometry, we introduce CamInject, which injects features from a frozen 3D foundation model into the VLM. CamInject improves over SFT but requires running the costly 3D model at inference. We instead propose CamDistill, which distills the same geometric knowledge into lightweight camera tokens during training and removes the 3D model at inference. CamDistill improves micro F1 over same-data SFT by 5.4/3.7 points on 4B/8B backbones, closely approaching CamInject. CamDistill-8B also demonstrates strong zero-shot transfer on the external camera motion understanding benchmarks CameraBench and CameraMotionVQA. Together, these resources and CamDistill enable benchmarking and improving temporally grounded, compositional camera motion understanding.

cs.CV · cs.AI

版本更新 · v2arXiv:2606.27025

Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

Zhenhua Xu, Dongsheng Chen, Jian Li, Yitong Lin, Zhebo Wang, Jiafu Wu, Yizhang Jin, Chengjie Wang 等 10 位作者

原文摘要

Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. Explicit reasoning can help models deliberate before responding, but generic reasoning does not necessarily preserve character fidelity. We therefore propose Psy-CoT, a psychology-grounded chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps: Interaction Perception, Psychological Empathy, and Logical Construction, so that the model thinks dynamically from the profile rather than merely mimicking surface patterns. While structured reasoning provides a foundation, it alone is insufficient; reinforcement learning is essential to further align the model with character fidelity. However, we observe that under LLM-based reward models, both generic phrases that hack the reward model and genuinely role-specific phrases receive identical gradient signals. This hacking accumulates over training, misleading the model into treating both as equally optimal choices. To address this, we propose Role-Aware Policy Optimization (RAPO), which uses profile-induced entropy differences to weight gradients asymmetrically, amplifying role-specific tokens under positive advantage while attenuating them under negative advantage. Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods, and RAPO consistently surpasses GRPO across multiple model scales.

cs.CL

新论文 · v1arXiv:2611.16384

Beyond Compressing Everything: Contrastive Memory Learning for Selective Context Compression

Sikui Zhang, Haowei Liu, Ziyun Gan, Chunfeng Yuan, Guangze Gao, Nian Liu, Boyu Cai, Bo Li 等 12 位作者

原文摘要

As large language models (LLMs) advance toward increasingly long inputs, soft context compression offers a promising approach to efficient inference by converting long inputs into compact memory slots. Under limited memory budgets, effective context compression remains challenging because task-relevant evidence varies substantially across queries, ranging from localized evidence to multiple distant spans or information dispersed throughout the full document. Instead of compressing everything indiscriminately, we propose CoMem, a query-guided selective context compression framework that learns memory representations conditioned on both the document and the query. CoMem develops Contrastive Compressor Learning to achieve query-sensitive yet context-preserving memory representations. To inject a strong prior over query-dependent evidence distributions, we devise a same-context hard negative mining strategy by pairing a single document with multiple queries, requiring the compressor to selectively retain information according to each query's distinct evidence needs. To address the restricted information flow imposed by causal masking, we further enable bidirectional attention among memory slots. Experiments demonstrate that CoMem consistently outperforms existing context compression methods across compression ratios on question answering and RULER-NIAH benchmarks. Our code is available at https://github.com/scar-on/CoMem.

cs.CL · cs.AI

版本更新 · v3arXiv:2605.03327

TIDE: Token-Level Credit Assignment via Entropy-Gated Bounded Deviation

Qiaoman Zhang, Shunhua Min, Xiang He, Zhenghan Zhang, Yuting Zhang, Guangxian Li, Yunzhu Kuang, Rui Jiang 等 11 位作者

原文摘要

Reinforcement learning (RL) is central for aligning large language models (LLMs) with complex reasoning, yet the leading critic-free algorithm, Group Relative Policy Optimization (GRPO), broadcasts a single sequence-level advantage uniformly across long Chain-of-Thought (CoT) generations and constrains exploration with an unbounded Kullback-Leibler (KL) penalty, which dilutes token-level supervision and induces gradient instability and mode-seeking conservatism. We propose TIDE (Token-level Importance via Deviation and Entropy), a critic-free RL framework that reinterprets distribution deviation as a guiding signal rather than a rigid penalty. TIDE replaces the volatile reverse KL divergence with the bounded Hellinger distance, safely quantifying token-level exploration without risk of gradient explosion. To separate genuine reasoning breakthroughs from confident hallucinations, an entropy gating mechanism scales this deviation by the policy's predictive uncertainty, and the gated scores redistribute the sequence-level advantage across tokens. The resulting updates amplify exploratory steps while suppressing low-entropy deviations, without a value network and with negligible overhead. Across in-domain, held-out, and out-of-domain benchmarks, TIDE outperforms strong critic-free baselines: on the Qwen2.5-32B backbone it reaches 60.0% and 46.0% Avg@32 accuracy on AIME 2024 and AIME 2025, respectively, above competitive baselines such as DAPO. Token-level attribution, causal perturbation, and exploration analyses further support the interpretation that the entropy-gated deviation identifies pivotal reasoning steps rather than merely perturbing optimization dynamics.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.20345

Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models

Jinlin Lai, Charles C. Margossian, Daniel Sheldon

原文摘要

Latent Gaussian models (LGMs) are a popular class of Bayesian hierarchical models that include Gaussian processes, as well as certain spatial models and mixed-effect models. Efficient Bayesian inference of LGMs often requires marginalizing out the latent variables. For LGMs with a non-Gaussian likelihood, exact marginalization is not possible and a popular approach is to do approximate marginalization with an integrated Laplace approximation (ILA). Using ILA produces an approximate posterior which, in some settings, can differ significantly from the correct posterior, which impacts downstream applications. We propose an importance sampling scheme to correct the error introduced by ILA. By increasing the number of samples in importance sampling, the posterior with ILA converges to the correct posterior. This idea is realized with various techniques, including pseudo-marginalization, quasi-Monte Carlo and randomized quasi-Monte Carlo. We implement our methods in an automatic differentiation framework to support gradient-based algorithms when doing inference on the hyperparameters. For the latter, we specifically consider the use of Hamiltonian Monte Carlo. We demonstrate the benefits of reduced error in various applied models.

stat.ML · cs.LG

新论文 · v1arXiv:2611.16293

Rasoi: Visual Diffs for Evaluating Structural Changes Made by Coding Agents

Riya Sahni, Aryan Kaul, Anushka Bhatnagar, Xuanming Zhang, Vivian Liu, Reya Vir, Lydia B. Chilton

原文摘要

Coding agents let developers modify software rapidly through natural language. However, as agents take on larger changes, developers can lose track of how the codebase is evolving. These edits may look correct on the surface while restructuring the system in unexpected ways: duplicating logic, changing modules outside the requested scope, removing functionality developers meant to keep, or introducing architectural drift. We investigate how visual diffs can help developers understand and evaluate the structural changes that coding agents make. We present Rasoi, a design probe that maps how a codebase's architecture evolves after each agent-made edit, letting developers inspect which architectural elements and relationships were added, modified, or removed across multiple levels of abstraction. We deployed Rasoi in a week-long study with 12 developers working on their own codebases across varied technical domains. We found that visual diffs helped developers see whether changes stayed within scope, notice unexpected restructuring, and understand how modified parts related to the system as a whole. Our findings suggest that the value of oversight tools for coding agents lies less in making developers trust the agent and more in helping developers feel confident in their own evaluation of agent-made changes. We discuss implications for visual tools that support code comprehension and human oversight in AI-assisted software development.

cs.SE · cs.HC

新论文 · v1arXiv:2611.15952

Quasi-Cyclic Qudit Lifted Product Codes with Almost Linear Minimum Distance

Shantom K. Borah, Abhinav Vaishya, V. Lalitha, Asit Kumar Pradhan, Bane Vasic, Narayanan Rengaswamy

原文摘要

Quantum low-density parity-check (QLDPC) codes are a promising route to fault-tolerant quantum computation with low overhead, and qudits offer advantages over qubits including more efficient information representation, improved magic state distillation, and richer algebraic structure for code design. Asymptotically good QLDPC codes arise from the lifted product (LP) construction with non-abelian lifts, but cyclic lifts remain attractive in practice because the resulting quasi-cyclic codes have circulant structure that hardware decoders exploit, which matters especially for non-binary decoders with costly check node operations. We introduce a qudit generalization of the LP construction over cyclic group algebras, which extends hypergraph product and LP codes to arbitrary prime-power dimensions and yields quasi-cyclic qudit CSS codes for every stacking order. We bound encoding rates via a connection to additive codes, and show that in the fully stacked case, qudit LP codes built from lifted Tanner codes on expander graphs form families with $Θ(\log N)$ logical qudits and almost linear minimum distance $Θ(N/\log N)$, via a distance bound that holds for a general class of LP factors. We also study an additive decoder for general qudit codes and a linear merged-syndrome decoder for fully stacked codes. Monte Carlo simulations under a depolarizing channel with equal symbol error probability show that qudit codes achieve lower frame error rates than comparable qubit codes, and that the linear decoder gives further gains for fully stacked codes.

quant-ph · cs.IT

新论文 · v1arXiv:2611.15488

FloCOS: Predicting Compact Forward Occupancy Sets of Surrounding Vehicles via Conditional Flow Matching

Chuansheng Dong, Yinxiao Zhan, Zongdian Li, Peng Hou, Jin Wang, Jiayu Fan

原文摘要

Existing methods for predicting surrounding vehicles' forward occupancy may under-approximate the ground-truth occupancy, exposing the ego vehicle to collision risk, or produce overly conservative regions that unnecessarily restrict feasible space and cause planning failures. To address these issues, we propose FloCOS, a conditional flow-matching framework that predicts compact forward occupancy sets with high occupancy coverage. FloCOS represents the forward occupancy set as a time-varying union of half-space convex polygons parameterized by temporal basis coefficients. Conditional flow matching captures the conditional distribution of these coefficients to govern the temporal evolution of the convex components, trained under coverage and union-area losses that penalize missed occupancy and excess area. For downstream trajectory optimization, the predicted nonconvex union is directly incorporated into hyperplane-based collision-avoidance constraints. Evaluations on the Waymo Open Motion Dataset show that FloCOS generates compact forward occupancy sets with high coverage and achieves a higher interaction completion rate than evaluated baselines. Real-world vehicle experiments further confirm its ability to support collision-free planning in interactive scenarios.

cs.RO

版本更新 · v2arXiv:2512.07302

Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts

Mingning Guo, Mengwei Wu, Shaoxian Li, Haifeng Li, Chao Tao

原文摘要

UAV image perception with VLMs aims to identify and localize targets based on semantic and spatial task prompts. However, small, densely distributed objects and cluttered backgrounds hinder these tasks, particularly when concise prompts provide insufficient guidance. Although task-specific fine-tuning improves image-text alignment, it requires large-scale annotations and model-specific updates, increasing adaptation costs across models and tasks. To address this, we propose AerialVP, a task-adaptive, training-free agent that adapts VLMs through prompt enhancement rather than parameter optimization. AerialVP dynamically adapts its enhancement strategy to the original prompt's specificity, selectively incorporating image-derived semantics, spatial positions, and object relationships. These cues provide discriminative descriptions and spatial constraints, leveraging VLMs' pretrained alignment and reasoning capabilities to improve image-text alignment and reduce target ambiguity. Specifically, an LLM-based Task Engine coordinates modular tools for prompt analysis, visual information extraction, and prompt fusion. The enhanced prompt and original image are then provided to the unchanged backend VLM for prediction. This prompt-centric strategy enables training-free adaptation across diverse open-source and proprietary VLMs. For systematic evaluation, we introduce AerialSense, a unified benchmark covering Aerial Visual Grounding, Aerial Visual Reasoning, and Aerial Visual Question Answering across diverse UAV scenes and imaging conditions. Experiments demonstrate consistent improvements across all three tasks and evaluated VLMs. AerialVP also achieves competitive performance against LoRA-based instruction fine-tuning, validating prompt-centric adaptation. Our work is available at https://github.com/lostwolves/AerialVP.

cs.CV · cs.AI

新论文 · v1arXiv:2611.15241

KQML-Liver: Interpretable Hybrid Quantum Machine Learning with Kolmogorov-Arnold Networks for Liver Disease Classification

Nhat-Long Nguyen, Viet-Loi Dinh, Trong-Nghia Pham

原文摘要

Liver disease remains a major global health concern, highlighting the need for reliable and accessible early detection methods. Although recent advances in machine learning, deep learning and quantum machine learning (QML) have introduced promising diagnostic tools, many approaches suffer from limited interpretability and inflated performance caused by data leakage or overly simplistic evaluation protocols. These constraints reduce their reliability in real-world clinical practice. This paper proposes KQML-Liver, a hybrid framework that integrates QML with Kolmogorov-Arnold Networks (KANs) to enhance predictive performance and interpretability. The architecture combines parameterized quantum circuits for expressive feature representation with KAN-based functional mappings that capture nonlinear relationships in an interpretable manner. Evaluated on the Indian Liver Patient Dataset (ILPD) under a rigorous preprocessing protocol preventing data leakage, the proposed model achieves 82% classification accuracy and 100% recall, detecting all positive cases, outperforming existing baselines while providing improved transparency in clinical predictions. These results suggest that hybrid KAN-quantum architectures offer a promising direction for interpretable AI-assisted medical diagnosis.

cs.LG · cs.AI

版本更新 · v3arXiv:2606.09547

Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

Apratim Bhattacharyya, Shweta Mahajan, Sanjay Haresh, Rajeev Yasarla, Reza Pourreza, Litian Liu, Risheek Garrepalli, Roland Memisevic

原文摘要

Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos. This opens the door to the use of video (and multimodal) large language models (LLMs) as task guidance assistants. A crucial capability for the real-world success of a prospective task guidance assistant is it's ability to intervene proactively as soon as a mistake is apparent in order to guide the user. To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios. Extensive experiments show that Ego-MC-Bench is highly challenging for state-of-the-art video LLMs. We argue that a key reason is the limited availability of training data for fine-tuning models on this task. Although there exists a wide range of cooking video datasets, existing datasets lack examples of mistakes along with appropriately timed interventions. To help address this data limitation, we also introduce Ego-CoMist, a counterfactual synthetic dataset created by transforming non -interactive cooking videos into supervised training examples showing proactive interventions. We show that fine-tuning on Ego-CoMist yields performance gains especially for smaller and more efficient video LLMs that are well suited for delivering assistance on edge devices.

cs.CV · cs.LG

新论文 · v1arXiv:2611.14926

Understanding the Asymptotic Transience of Q-Learning via Distributional Expansion

Shengbo Wang

原文摘要

Q-learning has been empirically observed to exhibit substantial transient error. This transient remains uncaptured by the leading Gaussian limit because the central-limit normalization removes the smaller-scale displacement generated by the initial nonlinear evolution. On the other hand, worst-case finite-sample guarantees, while accounting for transient effects, can obscure the mechanisms responsible for the error on a particular problem instance. We develop a finer asymptotic analysis that gives an asymptotically exact characterization of this transient for a fixed instance. Specifically, for synchronous Q-learning in finite discounted Markov decision processes, we separate the last-iterate error into an optimal-policy temporal-difference (TD) component and a nonnegative displacement caused by maximization. The centered TD component has Gaussian fluctuations at scale $n^{-1/2}$, whereas the maximization transient is of order $n^{-1}$ and converges almost surely, after rescaling by $n$, to a random limit. This limit represents the propagated effect of maximization errors generated before the greedy policy stabilizes. We combine this characterization with an Edgeworth expansion of the TD component to identify the corrections to its Gaussian approximation, separating the effects of initialization, non-Gaussian TD fluctuations, and maximization. The results reveal how transient errors arise for individual Q-learning instances and how their effects persist below the central-limit scale.

math.OC · cs.LG · stat.ML

新论文 · v1arXiv:2611.14908

Hy ASR 3.0 Technical Report

Aoxiong Yin, Auden Li, Chao Huang, Chuanyang Hu, Eitan Wang, Ethan Zou, Fangming Feng, Guangyu Chen 等 63 位作者

原文摘要

We present Hy ASR 3.0, a large language model (LLM)-based automatic speech recognition (ASR) system that delivers strong recognition accuracy, supports flexible contextual conditioning, and maintains robust recognition performance across diverse speech conditions. Hy ASR 3.0 supports Mandarin Chinese, English and 13 Chinese dialect groups, including Cantonese. Among the evaluated systems, it achieves the lowest aggregate error rates on public Mandarin Chinese, English, and Cantonese benchmarks and the lowest error rates on the corresponding internal test sets, alongside first-tier dialect recognition performance. Beyond audio-only transcription, Hy ASR 3.0 supports multiple forms of external context, including hotword lists, question--answer dialogues, and summaries, enabling the use of task-relevant information during recognition. The model also leverages intra-utterance context to disambiguate homophonic and phonetically similar keywords using information from other parts of the same utterance, without requiring a separate contextual input. Evaluations demonstrate strong contextual recognition in both external-context and intra-utterance settings, as well as robust recognition of long-form speech, children's and older adults' speech, low-volume speech, and speech in noisy environments. This report describes the model architecture and training methodology and presents evaluations across recognition accuracy, context utilization, and robustness.

cs.CL · eess.AS

版本更新 · v2arXiv:2601.12716

CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning

Ke Xie, Xingyi Zhao, Yiwen Hu, Haotian Lin, Shuhan Yuan, Wen Li, Tian Xie

原文摘要

Cellular networks are critical infrastructure supporting billions of worldwide users and safety- and mission-critical services. Vulnerabilities in cellular networks can therefore cause service disruption, privacy breaches, and broad societal harm, motivating growing efforts to analyze 3GPP specifications that define required device and operator behavior. However, existing benchmarks for this domain share three systematic deficiencies: they rely on LLM-generated entries without expert verification, they do not require faithful interpretation of normative language, reasoning across cross-referenced clauses, and verifiable conclusions grounded in multimodal evidence such as tables and figures, and they do not evaluate security reasoning over end-to-end protocol behavior. To address these gaps, we present CellularS2-Bench, a staged benchmark. CellularS2-Bench covers core control-plane specifications, processing over 1,866 paragraphs, 22,033 sentences, 424 figures, and 248 tables. It comprises 13,851 questions and instances across three progressive stages, of which 10,269 (74.14%) are newly constructed from 3GPP specifications and 43 real-world vulnerabilities. Beyond newly constructed tasks, CellularS2-Bench integrates and corrects 3,582 (25.86%) instances from 7 prior datasets to broaden task coverage. To establish a reproducible baseline on CellularS2-Bench, we introduce CellularS2-ARI, a unified Adapt-Retrieve-Integrate framework for systematic understanding and specification-driven security analysis of 3GPP specifications. Together, they establish an accessible and reproducible foundation for quantifying progress in specification understanding and security reasoning in cellular network security.

cs.CR

版本更新 · v2arXiv:2610.22588

SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and Decision Models

Yuchao Wu, XingCheng Liang, Guanxian Li

原文摘要

Multi-hop retrieval must find passages that become useful only after intermediate evidence is retrieved. We present SAG2, an embedding-free retriever whose only persistent structure is a SQLite lexical index, built without an LLM. Where SAG and HippoRAG 2 rely on a generative LLM for graph extraction and selection, SAG2 uses a decision model. Given the question and a shared context of selected retrieved passages, the decision model scores whether each candidate supplies an answer-chain fact. Terms activated from the top-scoring passages retrieve unvisited passages through the lexical index, which holds a passage-term hypergraph implicitly. SAG2 reaches Recall@10 of 86.62%, 97.43%, and 99.00% on 1,000-question subsets of MuSiQue, 2WikiMultiHopQA, and HotpotQA, the highest among the compared systems. With a decision model priced at about a fifth of SAG's LLM, indexing and retrieval on MuSiQue cost USD 4.33 against USD 14.85 for SAG. On EnterpriseRAG-Bench, SAG2 reaches 81.12% document Recall@10. As the benchmark's nested corpus grows 447.5-fold, SAG2's Recall@5 lead over BM25 alone widens from 7.28 to 14.76 points, at a nearly constant model cost per question. Because indexing makes no model call, SAG2 suits corpora that change often or must be searchable as soon as they are indexed.

cs.CL

版本更新 · v2arXiv:2611.11551

扩散语言模型何时应重新审视其承诺?

When Should Diffusion Language Models Reconsider Their Commitments?

Haoyang Zheng, Yidong Ouyang, Blake Jianhang Chen, Tian Tan, Ziqian Lin, Liqian Peng, Alec Go, Guang Lin

AI 速读 基于摘要

提出 PURL 训练框架,将并行生成与选择性 token 修订统一起来,让掩码扩散模型在解码过程中决定何时、在哪里以及如何修改早期 token 承诺。

cs.CL · cs.AI · cs.LG

查看原文摘要

Masked Diffusion Models (MDMs) are well known for fast text generation via parallel decoding. However, independent parallel sampling can commit to inconsistent predictions, and less is known about how to selectively revise these early token commitments. In this work, we introduce $\underline{\mathrm{P}}$lanned $\underline{\mathrm{U}}$nmasking-and-$\underline{\mathrm{R}}$evision Joint $\underline{\mathrm{L}}$earning (PURL) for MDMs, a training-based framework that seamlessly unifies parallel generation with selective token revision. We derive a normalized joint transition whose likelihood factorizes into edit selection, unmask selection, and token prediction. These components are trained jointly on partially masked sequences constructed according to the model's own unmasking policy. During inference, all three decisions are supported by a single shared forward pass, enabling the model to decode masked tokens and revise noisy tokens. Across logic puzzles, mathematical reasoning, and code generation, PURL improves accuracy at matched unmask budgets, with relative gains up to 47.4% accuracy improvement and up to an $8\times$ reduction in scheduled decoding rounds. Beyond these gains, our analysis further reveals general principles of revisable decoding: token edits become more effective as context accumulates; early edits can steer unfinished trajectories, whereas later edits tend to remain localized; and effective edits therefore depend on both calibrating when to intervene and learning where and how to revise. Together, these suggest that effective parallel generation depends not on revising more tokens, but on making the right commitments revisable at the right time.

新论文 · v1arXiv:2611.14257

Elastic-WAM:面向高效机器人控制的自适应时空想象

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xiao, Mutian Xu 等 11 位作者

AI 速读 基于摘要

提出 Elastic-WAM,用统一时空细化需求场自适应分配世界模型的计算,在降低推理开销的同时提升机器人控制表现。

cs.RO · cs.CV

查看原文摘要

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we propose Elastic-WAM, which adaptively allocates world refinement computation across temporal denoising time and spatial future space. A unified spatiotemporal refinement demand field governs when to stop world refinement, how far to advance each denoising step, and which regions to refresh. We parameterize this field with a shared temporal basis and spatial amplitudes, and learn it through a three-stage action-grounded supervised procedure. At inference, the learned field guides recurrent sparse world refinement to improve task success while reducing inference overhead. Evaluations across diverse simulation benchmarks and real-world long-horizon manipulation demonstrate state-of-the-art control performance with reduced inference latency.

新论文 · v1arXiv:2611.13776

DisasterAgent: An Evidence-Driven Agent for Verifiable Disaster Report Generation From Remote Sensing Imagery

Zhijian Li, Jiawei Song, Chao Ren, Yidan Zhang, Peijin Wang, Xian Sun, Kun Fu

原文摘要

Remote sensing disaster assessment is moving from simple damage classification toward comprehensive report-level analysis. In this setting, responders need not only damage descriptions but also verifiable evidence to guide response and recovery. Recent vision-language models (VLMs) and tool-augmented agents offer strong multimodal reasoning and perception, but they struggle to provide the evidence required for high-stakes verification. To address these limitations, we propose DisasterAgent, an evidence-driven agent that uses a Perception-Augmentation-Generation workflow to generate verifiable disaster reports from bitemporal optical imagery. DisasterAgent first invokes a specialized vision expert toolkit in the perception phase to build a Spatiotemporal Perception Graph (STPG), serving as a structured memory to store and organize disaster-induced changes across space and time. Evidence-based Augmentation (EA) then extracts evidence from the STPG, attaching inline citations that form a closed evidence loop from each statement to the supporting visual evidence. Extensive experiments on the DisasterM3 and RSCC benchmarks demonstrate that DisasterAgent consistently outperforms general-domain VLMs, remote sensing-specialized models, and existing remote sensing agents. Notably, compared with the original model, it improves the average score for disaster report generation on DisasterM3 by 13.5\% and ST5-SCS on RSCC by 15.34\%, providing a more accurate and verifiable solution for disaster emergency response. The code will be available at https://github.com/ZhijianLi2003/DisasterAgent.

cs.CV · cs.AI