大模型推理能力

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries

Marius Dragoi, Ioana Pintilie, Florin Gogianu, Florin Brad

机构 * Bitdefender（Bitdefender公司） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 10 pages, 3 figures. v2 adds discussion of related work (G-Pass@k)

OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning

Zhenyu Bi, Meng Lu, Yang Li, Swastik Roy, Weijie Guan, Morteza Ziyadi, Xuan Wang

机构 * Virginia Tech（弗吉尼亚理工大学） ； College of William and Mary（威廉与玛丽学院） ； Amazon Alexa AI（亚马逊Alexa人工智能） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 8 pages for main content

Local Coherence or Global Validity? Investigating RLVR Traces in Math Domains

Soumya Rani Samineni, Durgesh Kalwar, Vardaan Gangal, Siddhant Bhambri, Subbarao Kambhampati

机构 * Arizona State University（亚利桑那州立大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 4 pages, 2 figures

CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections

Keuntae Kim, Eunhye Jeong, Sehyeon Lee, Seohee Yoon, Yong Suk Choi

机构 * Department of Computer Science（计算机科学系） ； Department of Artificial Intelligence（人工智能系） ； Department of Future Mobility（未来移动部门） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2025

Prompt-to-Primal Teaching

Euzeli dos Santos

专题命中 数学推理 ：reasoning(abstract)

Comments 9 pages, 5 figures

Evaluating Program Semantics Reasoning with Type Inference in System F

Yifeng He, Luning Yang, Christopher Castro Gaw Gonzalo, Hao Chen

机构 * University of California, Davis（加州大学戴维斯分校） ； University of Hong Kong（香港大学） 纠错

专题命中 代码与定理证明 ：reasoning(title,abstract)；test-time compute(abstract)；分类 cs.CL

Comments NeurIPS '25, package released at: https://github.com/SecurityLab-UCD/TF-Bench

Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning

Manvi Jha, Jiaxin Wan, Deming Chen

机构 * Electrical and Computer Engineering（电气与计算机工程系） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 代码与定理证明 ：verifier(abstract)；分类 cs.AI

ParaVul: A Parallel Large Language Model and Retrieval-Augmented Framework for Smart Contract Vulnerability Detection

Tenghui Huang, Jinbo Wen, Jiawen Kang, Siyong Chen, Zhengtao Li, Tao Zhang, Dongning Liu, Jiacheng Wang, Chengjun Cai, Yinqiu Liu, Dusit Niyato

机构 * School of Automation, Guangdong University of Technology（广东科技大學自動化學院） ； College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大學計算機科學與技術學院） ； School of Cyberspace Science and Technology, Beijing Jiaotong University（北京交通大學網絡空間科學與技術學院） ； School of Computer Science and Technology, Guangdong University of Technology（廣東科技大學計算機科學與技術學院） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大學計算與數據科學學院） 纠错

专题命中 代码与定理证明 ：chain-of-thought(abstract)；分类 cs.AI

AI4DiTraRe: Building the BFO-Compliant Chemotion Knowledge Graph

Ebrahim Norouzi, Nicole Jung, Anna M. Jacyszyn, Jörg Waitelonis, Harald Sack

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 12 pages, 7 figures. Camera-ready version. Accepted to the 5th International Workshop on Scientific Knowledge: Representation, Discovery, and Assessment; 2 November 2025 - Nara, Japan; co-located with The 24th International Semantic Web Conference, ISWC 2025. Published in CEUR proceedings Vol-4065, pages 45-56

Ontology-Enhanced Knowledge Graph Completion using Large Language Models

Wenbin Guo, Xin Wang, Jiaoyan Chen, Zhao Li, Zirui Chen

机构 * Tianjin University, College of Intelligence and Computing（天津大学智能与计算学院） ； University of Manchester, Department of Computer Science（曼彻斯特大学计算机科学系） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Interpretability Framework for LLMs in Undergraduate Calculus

Sagnik Dakshit, Sushmita Sinha Roy

机构 * University of Texas at Tyler（德克萨斯理工大学） ； Florida Gulf Coast University（佛罗里达盖恩斯维尔大学） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment

Jinwei Hu, Yi Dong, Shuang Ao, Zhuoyun Li, Boxuan Wang, Lokesh Singh, Guangliang Cheng, Sarvapali D. Ramchurn, Xiaowei Huang

专题命中 逻辑推理 ：reasoning(abstract)

Comments Updated manuscript of our previous version (arXiv:2502.01714). Under review

Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring

Shuxin Lin, Dhaval Patel, Christodoulos Constantinides

机构 * IBM Research（IBM研究院） 纠错

专题命中 规划推理 ：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2025

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning

Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan

专题命中 规划推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments We have come across a recent approach that has not been properly attributed at the time of submission and compared in a fair setting. Therefore, we would like to withdraw the paper to address these concerns

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

Yiran Guo, Lijie Xu, Jie Liu, Dan Ye, Shuang Qiu

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； City University of Hong Kong（香港城市大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at NeurIPS 2025

Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning

Trixia Simangan, Ahmed Nadeem Abbasi, Yipeng Hu, Shaheer U. Saeed

机构 * UCL Hawkes Institute \& Department of Medical Physics ； Biomedical Engineering, University College London, United Kingdom Aga Khan University Hospital, Pakistan Centre for Bioengineering \& School of Engineering ； Materials Science \& Digital Environment Research Institute, Queen Mary University of London, United Kingdom 纠错

专题命中 规划推理 ：planning(title,abstract)

Comments Accepted at MICAD (Medical Imaging and Computer-Aided Diagnosis) 2025

Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval

Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Wenjun Peng, Sen Li, Fuyu Lv

专题命中 规划推理 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

The Challenge of Achieving Attributability in Multilingual Table-to-Text Generation with Question-Answer Blueprints

Aden Haussmann

机构 * The University of Edinburgh（爱丁堡大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.CL、cs.AI、cs.LG

PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses

Emmanuel O. Badmus, Peng Sang, Dimitrios Stamoulis, Amritanshu Pandey

机构 * Dept. of Electrical and Biomedical Engineering, The University of Vermont（维珍尼亚大学电气与生物医学工程系） ； Dept. of Electrical and Computer Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校电气与计算机工程系） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.AI

Explaining Large Language Models with gSMILE

Zeinab Dehghani, Mohammed Naveed Akram, Koorosh Aslansefat, Adil Khan, Yiannis Papadopoulos

机构 * University of Hull（赫尔大学） ； Fraunhofer IESE（弗劳恩霍夫研究所） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Glyph: Scaling Context Windows via Visual-Text Compression

Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang

机构 * The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University（清华大学对话人工智能（CoAI）小组） ； Zhipu AI（智谱AI） ； The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程小组（KEG）） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

On AI Verification in Open RAN

Rahul Soundrarajan, Claudio Fiandrino, Michele Polese, Salvatore D'Oro, Leonardo Bonati, Tommaso Melodia

机构 * Tejas Networks ； IMDEA Networks Institute ； Northeastern University 纠错

专题命中 规划推理 ：verifier(abstract)；分类 cs.AI

LLM-Based Multi-Agent System for Simulating and Analyzing Marketing and Consumer Behavior

Man-Lin Chu, Lucian Terhorst, Kadin Reed, Tom Ni, Weiwei Chen, Rongyu Lin

机构 * School of Business（商学院） ； School of Computing and Engineering（计算与工程学院） ； Quinnipiac University（昆尼皮亚克大学） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

Comments Accepted for publication at IEEE International Conference on e-Business Engineering ICEBE 2025, November 10-12, Buraydah, Saudi Arabia. 8 pages, 5 figures

Attention-Guided Deep Adversarial Temporal Subspace Clustering (A-DATSC) Model for multivariate spatiotemporal data

Francis Ndikum Nji, Vandana Janeja, Jianwu Wang

机构 * University of Maryland, Baltimore County（马里兰大学巴尔的摩县） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Comments 9 pages, under review submitted to ICLR 2025

FlySearch: Exploring how vision-language models explore

Adam Pardyl, Dominik Matuszek, Mateusz Przebieracz, Marek Cygan, Bartosz Zieliński, Maciej Wołczyk

专题命中 规划推理 ：planning(abstract)；分类 cs.LG

Comments NeurIPS 2025 Datasets and Benchmarks track

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Yu Feng, Ben Zhou, Weidong Lin, Dan Roth

机构 * University of Pennsylvania（宾夕法尼亚大学） ； Arizona State University（亚利桑那州立大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL

Journal ref ICLR 2025 (Oral)

Prompting the Priorities: A First Look at Evaluating LLMs for Vulnerability Triage and Prioritization

Osama Al Haddad, Muhammad Ikram, Ejaz Ahmed, Young Lee

专题命中 规划推理 ：chain-of-thought(abstract)

Comments 19 pages, 8 figures

Evaluating LLM-Based Mobile App Recommendations: An Empirical Study

Quim Motger, Xavier Franch, Vincenzo Gervasi, Jordi Marco

专题命中 规划推理 ：reasoning(abstract)

Comments Under review

Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents

Guangfu Guo, Xiaoqian Lu, Yue Feng

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning

Hao Yan, Xingchen Liu, Hao Wang, Zhenbiao Cao, Handong Zheng, Liang Yin, Xinxing Su, Zihao Chen, Jihao Wu, Minghui Liao, Chao Weng, Wei Chen, Yuliang Liu, Xiang Bai

专题命中 视觉空间推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 13 pages, 4 figures