大模型推理能力

Evolutionary System 2 Reasoning: An Empirical Proof

进化系统2推理：一个实证证明

Zeyuan Ma, Wenqi Huang, Guo-Huan Song, Hongshu Guo, Sijie Ma, Zhiguang Cao, Yue-Jiao Gong

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

AI总结 本文提出进化推理优化框架，通过进化策略提升LLM的推理能力，实验证实即使弱模型也能通过简单进化获得强大推理能力。

Addressing Logical Fallacies In Scientific Reasoning From Large Language Models: Towards a Dual-Inference Training Framework

解决大型语言模型在科学推理中的逻辑谬误：一种双推理训练框架

Peter B. Walker, Hannah Davidson, Aiden Foster, Matthew Lienert, Thomas Pardue, Dale Russell

机构 * Intelligenesis LLC ； Uniformed Services University（美国武装部队服务大学） 纠错

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

AI总结 本文提出一种双推理训练框架，旨在解决大型语言模型在科学推理中的逻辑谬误问题，通过整合肯定生成与反事实否定，提升模型的鲁棒性和可解释性。

Comments 12 pages, 5 tables

Distributed Agent Reasoning Across Independent Systems With Strict Data Locality

跨独立系统的分布式代理推理与严格数据本地性

Daniel Vaughan, Kateřina Vaughan

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

AI总结 本文提出了一种基于自然语言消息的分布式代理推理系统，通过伪匿名令牌和本地数据查询实现跨组织安全合作，验证了去中心化多代理系统的可行性。

Comments 27 pages, 6 figures

Towards Verified Code Reasoning by LLMs

Meghana Sistla, Gogul Balakrishnan, Pat Rondon, José Cambronero, Michele Tufano, Satish Chandra

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Google DeepMind（谷歌DeepMind） ； Google（谷歌） ； Meta Platforms（元平台） 纠错

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

Comments 43 pages

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

Reasoning with Exploration: An Entropy Perspective

Daixuan Cheng, Shaohan Huang, Xuekai Zhu, Bo Dai, Wayne Xin Zhao, Zhenliang Zhang, Furu Wei

机构 * RUC（北京理工大学） ； MSRA（微软研究院） ； SJTU（上海交通大学） ； BIGAI（北京人工智能研究院） 纠错

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

Comments AAAI 2026 Conference

APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning

Azim Ospanov, Farzan Farnia, Roozbeh Yousefzadeh

机构 * Huawei Hong Kong Research Center（华为香港研究中心） ； Department of Computer Science & Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系） 纠错

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

Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs

Shufan Wang, Xing Hu, Junkai Chen, Zhiyuan Pan, Xin Xia

机构 * Singapore Management University（新加坡国立管理学院） 纠错

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

Comments 13 pages, 4 figures

\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs

Jun Gao, Yun Peng, Xiaoxue Ren

机构 * Zhejiang University（浙江大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Language

Yuhao Zhang, Dingxin Hu, Tinghao Yu, Hao Liu, Yiting Liu

机构 * Tencent Hunyuan Team（腾讯文言团队） 纠错

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

Evaluating the Role of Verifiers in Test-Time Scaling for Legal Reasoning Tasks

Davide Romano, Jonathan Schwarz, Daniele Giofré

机构 * Thomson Reuters（汤姆森·路透） 纠错

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

Comments Accepted to EMNLP - NLLP Workshop

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards

Xuan Zhang, Ruixiao Li, Zhijian Zhou, Long Li, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi

机构 * Fudan University（复旦大学） ； Shanghai Innovation Institute（上海创新研究院） ； Tencent Youtu Lab（腾讯优图实验室） 纠错

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

Toward Causal-Visual Programming: Enhancing Agentic Reasoning in Low-Code Environments

Jiexi Xu, Jiaqi Liu, Lanruo Wang, Su Liu

机构 * School of Information \& Computer Science University of California, Irvine Irvine, CA, USA ； Independent Researcher ； University of Texas at Dallas Dallas, TX, USA ； Georgia Institute of Technology Atlanta, GA, USA 纠错

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

Comments 5 pages, 1 table

Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters

Jacqueline L. Mitchell, Brian Hyeongseok Kim, Chenyu Zhou, Chao Wang

机构 * University of Southern California（南加州大学） 纠错

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

MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning

Jugal Gajjar, Kamalasankari Subramaniakuppusamy, Noha El Kachach

机构 * Computer Science Department（计算机科学系） ； The George Washington University（乔治华盛顿大学） 纠错

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

Comments 6 pages, 4 figures, accepted for publication in IEEE 26th International Conference on Information Reuse and Integration (IRI 2025)

Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning

Alexander Beiser, David Penz, Nysret Musliu

机构 * Johannes Kepler University Linz（约翰内斯·开普勒大学林茨） 纠错

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

Comments To appear in the proceedings of The Second Workshop on Knowledge Graphs and Neurosymbolic AI (KG-NeSy) Co-located with SEMANTiCS 2025 Conference, Vienna, Austria - September 3rd, 2025

Reasoning with RAGged events: RAG-Enhanced Event Knowledge Base Construction and reasoning with proof-assistants

Stergios Chatzikyriakidis

机构 * Computational Linguistics and Language Technology lab（计算语言学与语言技术实验室） ； Department of Philology（文学系） ； University of Crete（克里特大学） 纠错

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

Leanabell-Prover: Posttraining Scaling in Formal Reasoning

Jingyuan Zhang, Qi Wang, Xingguang Ji, Yahui Liu, Yang Yue, Fuzheng Zhang, Di Zhang, Guorui Zhou, Kun Gai

机构 * Kuaishou Technology（快手科技） 纠错

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

Comments 23 pages, 6 figures

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving

Zhenwen Liang, Linfeng Song, Yang Li, Tao Yang, Feng Zhang, Haitao Mi, Dong Yu

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

Comments Work in progress

AI-Driven Scholarly Peer Review via Persistent Workflow Prompting, Meta-Prompting, and Meta-Reasoning

Evgeny Markhasin

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

Comments 23 pages, 37 pages (references and appendixes)

Clarifying Before Reasoning: A Coq Prover with Structural Context

Yanzhen Lu, Hanbin Yang, Xiaodie Wang, Ge Zhang, Biao Li, Chenxu Fu, Chao Li, Yang Yuan, Andrew Chi-Chih Yao

机构 * Shanghai Qizhi Institute（上海启智研究院） ； IIIS, Tsinghua University（清华大学信息科学技术研究院） 纠错

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

Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models

Chenrui Cao, Liangcheng Song, Zenan Li, Xinyi Le, Xian Zhang, Hui Xue, Fan Yang

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

Comments 31 pages. Associated code and results are available at https://github.com/microsoft/DSP-Plus

Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning

Yihong Tang, Kehai Chen, Muyun Yang, Zhengyu Niu, Jing Li, Tiejun Zhao, Min Zhang

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； Baidu Inc.（百度公司） 纠错

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

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs

Shiyao Cui, Qinglin Zhang, Xuan Ouyang, Renmiao Chen, Zhexin Zhang, Yida Lu, Hongning Wang, Han Qiu, Minlie Huang

机构 * The Conversational AI (CoAI) group, DCST, Tsinghua University China（清华大学人工智能对话组，国防科技大学，清华大学） 纠错

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

ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus

Etienne Guichard, Felix Reimers, Mia Kvalsund, Mikkel Lepperød, Stefano Nichele

机构 * University of Oslo（奥斯陆大学） ； Simula Research Laboratory（Simula研究实验室） ； Oslo Metropolitan University（奥斯陆 Metropolitan 大学） 纠错

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

Proof-of-TBI -- Fine-Tuned Vision Language Model Consortium and OpenAI-o3 Reasoning LLM-Based Medical Diagnosis Support System for Mild Traumatic Brain Injury (TBI) Prediction

Ross Gore, Eranga Bandara, Sachin Shetty, Alberto E. Musto, Pratip Rana, Ambrosio Valencia-Romero, Christopher Rhea, Lobat Tayebi, Heather Richter, Atmaram Yarlagadda, Donna Edmonds, Steven Wallace, Donna Broshek

机构 * Old Dominion University（旧 Dominion 大学） ； McDonald Army Health Center（麦克唐纳陆军医疗中心） ； BRAINBox Solutions（BRAINBox 解决方案） ； UVA Health（弗吉尼亚大学健康系统） 纠错

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

Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning

Haiming Wang, Mert Unsal, Xiaohan Lin, Mantas Baksys, Junqi Liu, Marco Dos Santos, Flood Sung, Marina Vinyes, Zhenzhe Ying, Zekai Zhu, Jianqiao Lu, Hugues de Saxcé, Bolton Bailey, Chendong Song, Chenjun Xiao, Dehao Zhang, Ebony Zhang, Frederick Pu, Han Zhu, Jiawei Liu, Jonas Bayer, Julien Michel, Longhui Yu, Léo Dreyfus-Schmidt, Lewis Tunstall, Luigi Pagani, Moreira Machado, Pauline Bourigault, Ran Wang, Stanislas Polu, Thibaut Barroyer, Wen-Ding Li, Yazhe Niu, Yann Fleureau, Yangyang Hu, Zhouliang Yu, Zihan Wang, Zhilin Yang, Zhengying Liu, Jia Li

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

Comments 22 pages

Proof Flow: Preliminary Study on Generative Flow Network Language Model Tuning for Formal Reasoning

Matthew Ho, Vincent Zhu, Xiaoyin Chen, Moksh Jain, Nikolay Malkin, Edwin Zhang

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

Social, Legal, Ethical, Empathetic, and Cultural Rules: Compilation and Reasoning (Extended Version)

Nicolas Troquard, Martina De Sanctis, Paola Inverardi, Patrizio Pelliccione, Gian Luca Scoccia

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

Comments In proceedings of the 38th Annual AAAI Conference on Artificial Intelligence

Reasoning Runtime Behavior of a Program with LLM: How Far Are We?

Junkai Chen, Zhiyuan Pan, Xing Hu, Zhenhao Li, Ge Li, Xin Xia

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

Comments Accepted by 47th IEEE/ACM International Conference on Software Engineering (ICSE 2025). Our REval leaderboard is available at https://r-eval.github.io