大模型推理能力

Numerical Sensitivity and Robustness: Exploring the Flaws of Mathematical Reasoning in Large Language Models

Zhishen Sun, Guang Dai, Ivor Tsang, Haishan Ye

机构 * Xi’an Jiaotong University（西安交通大学） ； SGIT AI Lab（SGIT人工智能实验室） ； A*STAR 纠错

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

MSCR: Exploring the Vulnerability of LLMs' Mathematical Reasoning Abilities Using Multi-Source Candidate Replacement

Zhishen Sun, Guang Dai, Haishan Ye

机构 * Xi’an Jiaotong University（西安交通大学） ； SGIT AI Lab（SGIT人工智能实验室） 纠错

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

CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning

Lauren Deason, Adam Bali, Ciprian Bejean, Diana Bolocan, James Crnkovich, Ioana Croitoru, Krishna Durai, Chase Midler, Calin Miron, David Molnar, Brad Moon, Bruno Ostarcevic, Alberto Peltea, Matt Rosenberg, Catalin Sandu, Arthur Saputkin, Sagar Shah, Daniel Stan, Ernest Szocs, Shengye Wan, Spencer Whitman, Sven Krasser, Joshua Saxe

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

PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints

Tangrui Li, Pei Wang, Hongzheng Wang Christian Hahm, Matteo Spatola, Justin Shi

机构 * Temple University（特拉华大学） 纠错

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

Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs

Anton Gusarov, Anastasia Volkova, Valentin Khrulkov, Andrey Kuznetsov, Evgenii Maslov, Ivan Oseledets

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

Comments Code to be released

Towards AI-Assisted Generation of Military Training Scenarios

Soham Hans, Volkan Ustun, Benjamin Nye, James Sterrett, Matthew Green

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

Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning

Haolun Wu, Zhenkun Li, Lingyao Li

专题命中 逻辑推理 ：reasoning(title,abstract)；logical reasoning(title)

Comments 20 pages, 6 figures

SemanticForge: Repository-Level Code Generation through Semantic Knowledge Graphs and Constraint Satisfaction

Wuyang Zhang, Chenkai Zhang, Zhen Luo, Jianming Ma, Wangming Yuan, Chuqiao Gu, Chenwei Feng

机构 * Department of Elec.&Comp. Science, University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校电子与计算机科学系） ； Department of Computer Sys. Engineering, Northeastern University（东北大学计算机系统工程系） ； Department of Computer Science, George Mason University（乔治·梅森大学计算机科学系） ； Department of Info. Networking Institude, Carnegie Mellon University（卡内基梅隆大学信息网络研究所） ； Department of Computer & Mathematical Sciences, Auckland University of Technology（奥克兰理工大学计算机与数学科学系） 纠错

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

Journal ref INNO-PRESS: Journal of Emerging Applied AI, 2025

PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning

Hieu Tran, Zonghai Yao, Nguyen Luong Tran, Zhichao Yang, Feiyun Ouyang, Shuo Han, Razieh Rahimi, Hong Yu

机构 * Center for Healthcare Organization and Implementation Research, VA Bedford Health Care（VA Bedford Health Care 医疗组织与实施研究中心） ； Manning College of Information and Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校信息与计算机科学学院） ； Miner School of Computer and Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校 Miner 信息与计算机科学学院） 纠错

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

Comments Proceedings of AAAI 2026

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces

Xueliang Zhao, Wei Wu, Jian Guan, Qintong Li, Lingpeng Kong

机构 * The University of Hong Kong（香港大学） ； Ant Group（蚂蚁集团） 纠错

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

Comments Accepted to NeurIPS 2025

ControlMed: Adding Reasoning Control to Medical Language Model

Sung-Min Lee, Siyoon Lee, Juyeon Kim, Kyoungmin Roh

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

Comments IJCNLP-AACL 2025

Knowledge-Guided Textual Reasoning for Explainable Video Anomaly Detection via LLMs

Hari Lee

机构 * Hari Lee 纠错

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

LLM-GROP: Visually Grounded Robot Task and Motion Planning with Large Language Models

Xiaohan Zhang, Yan Ding, Yohei Hayamizu, Zainab Altaweel, Yifeng Zhu, Yuke Zhu, Peter Stone, Chris Paxton, Shiqi Zhang

机构 * The State University of New York at Binghamton（纽约州立大学布林顿分校） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Sony AI（索尼人工智能） ； Hello Robot（Hello Robot公司） ； Shanghai AI Laboratory（上海人工智能实验室） ； OneStar Robotics（OneStar机器人） 纠错

专题命中 规划推理 ：planning(title,abstract)

Journal ref The International Journal of Robotics Research, 2025, Vol. 0(0), pp. 1-19

VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use

Zhehao Zhang, Ryan Rossi, Tong Yu, Franck Dernoncourt, Ruiyi Zhang, Jiuxiang Gu, Sungchul Kim, Xiang Chen, Zichao Wang, Nedim Lipka

机构 * Adobe 纠错

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

Comments AAAI 2026

A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services

Guanzhong Pan, Vishal Chodnekar, Abinas Roy, Haibo Wang

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

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

Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models

Supriti Vijay, Aman Priyanshu, Anu Vellore, Baturay Saglam, Amin Karbasi

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Foundation AI–Cisco Systems Inc.（Foundation AI–Cisco 系统公司） ； Yale University（耶鲁大学） 纠错

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

Comments 37 images, 7 figures, and 15 tables

From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory

Siyu Xia, Zekun Xu, Jiajun Chai, Wentian Fan, Yan Song, Xiaohan Wang, Guojun Yin, Wei Lin, Haifeng Zhang, Jun Wang

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Meituan（美团） ； Nanjing University of Posts and Telecommunications（南京邮电大学） ； AI Centre, Department of Computer Science, University College London（伦敦大学学院计算机科学系人工智能中心） 纠错

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

A Negotiation-Based Multi-Agent Reinforcement Learning Approach for Dynamic Scheduling of Reconfigurable Manufacturing Systems

Manonmani Sekar, Nasim Nezamoddini

机构 * Industrial and Systems Engineering Department, Oakland University（奥克兰大学工业与系统工程系） 纠错

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

Procedural Knowledge Improves Agentic LLM Workflows

Vincent Hsiao, Mark Roberts, Leslie Smith

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

Socialized Learning and Emergent Behaviors in Multi-Agent Systems based on Multimodal Large Language Models

Sureyya Akin, Shruti T. Tiwari, Ram Bhattacharya, Sagar A. Raman, Kiran Mohanty, Sita Krishnan

专题命中 规划推理 ：planning(abstract)

Comments We have identified critical issues in the code implementation that severely deviate from Algorithm 1, invalidating all experimental results and conclusions. Despite exhaustive efforts to correct these issues, we find they fundamentally undermine the paper's core claims. To uphold academic integrity and prevent misinformation, we are withdrawing this manuscript

Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views

Haida Feng, Hao Wei, Zewen Xu, Haolin Wang, Chade Li, Yihong Wu

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

The Path Not Taken: RLVR Provably Learns Off the Principals

Hanqing Zhu, Zhenyu Zhang, Hanxian Huang, DiJia Su, Zechun Liu, Jiawei Zhao, Igor Fedorov, Hamed Pirsiavash, Zhizhou Sha, Jinwon Lee, David Z. Pan, Zhangyang Wang, Yuandong Tian, Kai Sheng Tai

机构 * Meta AI ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

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

Comments Preliminary version accepted as a spotlight in NeurIPS 2025 Workshop on Efficient Reasoning

Test-time Diverse Reasoning by Riemannian Activation Steering

Ly Tran Ho Khanh, Dongxuan Zhu, Man-Chung Yue, Viet Anh Nguyen

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments 19 pages, 6 figures. Accepted for publication at AAAI 2026 (40th AAAI Conference on Artificial Intelligence)

Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning

Qianxi He, Qingyu Ren, Shanzhe Lei, Xuhong Wang, Yingchun Wang

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（上海数据科学关键实验室，计算机科学学院，复旦大学） 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.AI、cs.LG

AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress

Zhiheng Xi, Chenyang Liao, Guanyu Li, Yajie Yang, Wenxiang Chen, Zhihao Zhang, Binghai Wang, Senjie Jin, Yuhao Zhou, Jian Guan, Wei Wu, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * Fudan University（复旦大学） ； Ant Group（蚂蚁集团） 纠错

专题命中 测试时计算 ：reasoning(abstract)；test-time compute(abstract)；分类 cs.CL、cs.LG

Comments Preprint

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

Tianwen Lyu, Xiang Zhuang, Keyan Ding, Xinzhe Cao, Lei Liang, Wei Zhao, Qiang Zhang, Huajun Chen

机构 * The Polytechnic Institute, Zhejiang University（浙江大学Polytechnic学院） ； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University（浙江大学Hangzhou全球科技创新中心） ； University of Oxford（牛津大学） ； Ant Group（蚂蚁集团） ； University of Aberdeen（阿伯丁大学） ； ZJU-UIUC Institute, Zhejiang University（浙江大学UIUC研究院） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；CoT(title,abstract)；分类 cs.AI

Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance

Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song

机构 * TikTok Inc.（字节跳动公司） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments Camera Ready for EMNLP 2025

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Yihe Deng, Hritik Bansal, Fan Yin, Nanyun Peng, Wei Wang, Kai-Wei Chang

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments 23 pages, 11 figures, 8 tables

Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching

Songze Li, Zhiqiang Liu, Zhengke Gui, Huajun Chen, Wen Zhang

机构 * Zhejiang University（浙江大学） ； Ant Group（蚂蚁集团） ； ZJU-Ant Group Joint Lab of Knowledge Graph（浙江大学-蚂蚁集团知识图谱联合实验室） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.CL

Journal ref EMNLP 2025, pages 7683-7703

SAFENLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces

Ruiheng Liu, XiaoBing Chen, Jinyu Zhang, Qiongwen Zhang, Yu Zhang, Bailong Yang

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments AAAI 2026 Extended Version