大模型推理能力

2209.07753 2023-05-26 cs.RO 50%

Code as Policies: Language Model Programs for Embodied Control

Jacky Liang, Wenlong Huang, Fei Xia, Peng Xu, Karol Hausman, Brian Ichter, Pete Florence, Andy Zeng

专题命中数学推理：reasoning(abstract)

2105.00434 2021-05-04 cs.RO cs.SY eess.SY 50%

Dynamic Routing for Traffic Flow through Multi-agent Systems

Jizhe Zhou, Qiwei Chen, Qin Li

专题命中数学推理：planning(abstract)

2008.07321 2020-08-18 cs.CY 50%

Expected Utilitarianism

Heather M. Roff

专题命中数学推理：reasoning(abstract)

1805.05374 2019-05-14 cs.RO cs.MA 50%

Generating Comfortable, Safe and Comprehensible Trajectories for Automated Vehicles in Mixed Traffic

Maximilian Naumann, Martin Lauer, Christoph Stiller

专题命中数学推理：planning(abstract)

Journal ref Proc. IEEE Intl. Conf. Intelligent Transportation Systems, pp. 575-582, Hawaii, USA, Nov 2018

1806.00139 2018-06-04 cs.CR 50%

Tokenized Data Markets

Bharath Ramsundar, Roger Chen, Alok Vasudev, Rob Robbins, Artur Gorokh

专题命中数学推理：reasoning(abstract)

1711.03391 2017-11-10 physics.geo-ph 50%

A simplified model based on self-organized criticality framework for the seismic assessment of urban areas

A. Greco, A. Pluchino, L. Barbarossa, I. Caliò, F. Martinico, A. Rapisarda

专题命中数学推理：planning(abstract)

Comments 12 pages, 6 figures

1502.03998 2017-03-13 math.OC 50%

Time-consistent stopping under decreasing impatience

Yu-Jui Huang, Adrien Nguyen-Huu

专题命中数学推理：reasoning(abstract)

1701.09112 2017-02-01 cs.MA 50%

Socio-Affective Agents as Models of Human Behaviour in the Networked Prisoner's Dilemma

Joshua D. A. Jung, Jesse Hoey

专题命中数学推理：reasoning(abstract)

Comments 12 pages

1603.05072 2016-03-17 cs.GT cs.FL cs.LO 50%

Reconciling Rationality and Stochasticity: Rich Behavioral Models in Two-Player Games

Mickael Randour

专题命中数学推理：planning(abstract)

Comments Accepted at GAMES 2016, the 5th World Congress of the Game Theory Society. High-level survey notably based on arXiv:1204.3283 and arXiv:1411.0835

1402.7252 2014-03-03 physics.ed-ph 50%

Integrated STEM in Elementary Grades Using Distributed Agent-based Computation

Pratim Sengupta, Gokul Krishnan, Mason Wright

专题命中数学推理：reasoning(abstract)

Comments Proceedings of the Sixth International Conference on Computer Supported Education (CSEDU 2014) (In Press)

1305.0904 2013-05-07 cs.SI cs.DL math.HO physics.soc-ph 50%

What does mathoverflow tell us about the production of mathematics?

Ursula Martin, Alison Pease

专题命中数学推理：reasoning(abstract)

Comments Appeared in SOHUMAN, 2nd International Workshop on Social Media for Crowdsourcing and Human Computation, at ACM Web Science 2013, May 1, 2013, Paris http://eipcm.org/sohuman2013/

quant-ph/9809033 2009-12-01 quant-ph 50%

A Combinatorial Bit Bang Leading to Quaternions

Michael Manthey

专题命中数学推理：planning(abstract)

Comments 23 pages, 4 figures

Journal ref Acta Polytechnica Scandinavica, No. 91 (1998). Farre, G.L. and Oksala, T. (eds.): Emergence, Complexity, Hierarchy, Organization - Selected and edited papers from the ECHO III conference. Finnish Academy of Technology. ISBN 952-5148-59-9, ISSN 1238-9803

2608.03291 2026-08-05 cs.LG cs.AI cs.CL 新提交 93%

The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

可察觉的轨迹：利用思维链动态检测大语言模型中的推理失败

Shashwat Sourav, Aishwarya Balwani

专题命中代码与定理证明：chain-of-thought(title,abstract)；CoT(summary_cn,abstract)；reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结本研究利用思维链动态特性，在不假设语言化CoT语义忠实性的情况下，检测大语言模型在布尔可满足性任务中的分布式推理失败，并通过针对性提示干预提升了Llama3-70B的准确率。

2504.14089 2025-09-16 cs.CL cs.AI cs.LG 91%

LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

Kang He, Kaushik Roy

机构 * Electrical and Computer Engineering, Purdue University（电子与计算机工程系，普渡大学）

专题命中代码与定理证明：reasoning(title,abstract)；logical reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments EMNLP 2025 Main Conference

2607.10480 2026-07-14 cs.CL 新提交 90%

When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation

当推理对法律起草造成阻碍时：专利权利要求生成中的语言表达瓶颈

Lekang Jiang, Wenjun Sun, Stephan Goetz

专题命中代码与定理证明：CoT(summary_cn,abstract)；reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL

AI总结研究专利权利要求生成中CoT提示是否有益，提出特定任务CoT方法并评估。结果显示推理增强提示可提升权利要求质量，且隐式CoT优于显式CoT，显式CoT会引入信息瓶颈，为法律任务和CoT应用提供新见解。

Comments Accepted to AI for Law Workshop @ ICML 2026

2503.03205 2025-05-28 cs.CL cs.AI 90%

MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving

Ruida Wang, Rui Pan, Yuxin Li, Jipeng Zhang, Yizhen Jia, Shizhe Diao, Renjie Pi, Junjie Hu, Tong Zhang

专题命中代码与定理证明：chain-of-thought(title,abstract)；reasoning(title)；CoT(abstract)；verifier(abstract)

2510.24940 2026-01-28 cs.CL 89%

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

SemCoT：通过语义对齐的隐式令牌加速链式推理

Yinhan He, Wendy Zheng, Yaochen Zhu, Zaiyi Zheng, Lin Su, Sriram Vasudevan, Qi Guo, Liangjie Hong, Jundong Li

机构 * University of Virginia（弗吉尼亚大学）； LinkedIn Inc.（领英公司）

专题命中代码与定理证明：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(abstract)；分类 cs.CL

AI总结 SemCoT通过语义对齐的隐式令牌优化，提升链式推理的效率与准确性。

2510.01069 2025-10-02 cs.AI 89%

Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning

Elija Perrier

机构 * Centre for Quantum Software and Information（量子软件与信息中心）； University of Technology Sydney（悉尼技术大学）

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

Comments Under review

2507.08649 2025-07-14 cs.AI 89%

Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning

Xingguang Ji, Yahui Liu, Qi Wang, Jingyuan Zhang, Yang Yue, Rui Shi, Chenxi Sun, Fuzheng Zhang, Guorui Zhou, Kun Gai

机构 * Kuaishou Technology（快手科技）

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

Comments 23 pages, 13 figures

2503.01632 2025-03-04 cs.AI 89%

CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution

Tianchi Ren, Haibo Hu, Jiacheng Zuo, Xinhong Chen, Jianping Wang, Chun Jason Xue, Jen-Ming Wu, Nan Guan

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

2603.21286 2026-04-07 cs.HC 89%

When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors

当链条断裂时：LLM推理错误的交互诊断

Shiwei Chen, Niruthikka Sritharan, Xiaolin Wen, Chenxi Zhang, Xingbo Wang, Yong Wang

专题命中代码与定理证明：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(abstract)

AI总结本文提出ReasonDiag系统，通过结合外部事实核查与符号逻辑验证，帮助用户高效识别和诊断LLM推理链条中的错误步骤及根本原因。

Comments Accepted to EuroVis 2026

2410.23402 2025-02-11 cs.SE 89%

VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning

Cuong Chi Le, Hoang-Chau Truong-Vinh, Huy Nhat Phan, Dung Duy Le, Tien N. Nguyen, Nghi D. Q. Bui

专题命中代码与定理证明：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(abstract)

Comments NAACL 2025

2309.08589 2023-11-09 cs.LG cs.AI cs.CL 89%

Chain-of-Thought Reasoning is a Policy Improvement Operator

Hugh Zhang, David C. Parkes

专题命中代码与定理证明：reasoning(title,abstract)；chain-of-thought(title,abstract)；分类 cs.CL、cs.AI、cs.LG

2505.16998 2025-05-23 cs.CL cs.AI 88%

Do Large Language Models Excel in Complex Logical Reasoning with Formal Language?

Jin Jiang, Jianing Wang, Yuchen Yan, Yang Liu, Jianhua Zhu, Mengdi Zhang, Xunliang Cai, Liangcai Gao

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

2501.19143 2026-05-01 cs.AI cs.CR cs.CV 88%

Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI

对抗性欺骗的模仿游戏：生成AI中的链式推理

Ching-Chun Chang, Fan-Yun Chen, Shih-Hong Gu, Kai Gao, Hanrui Wang, Isao Echizen

机构 * Information and Society Research Division, National Institute of Informatics（信息与社会研究部，国立信息研究所）； Department of Information Engineering and Computer Science, Feng Chia University（信息工程与计算机科学系，逢甲大学）

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

AI总结本文提出基于模仿游戏的对抗性欺骗防御框架，利用链式推理生成多模态代理，有效对抗生成AI中的演绎和归纳欺骗攻击。

Journal ref in IEEE Access, vol. 13, pp. 95085-95093, 2025

2507.02984 2025-07-29 cs.CL 88%

From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought

Wentao Tan, Qiong Cao, Yibing Zhan, Chao Xue, Changxing Ding

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

2403.13312 2024-03-21 cs.CL 88%

LeanReasoner: Boosting Complex Logical Reasoning with Lean

Dongwei Jiang, Marcio Fonseca, Shay B. Cohen

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

Comments Accepted to NAACL 2024 main conference

2608.04285 2026-08-06 cs.AI cs.LG 新提交 88%

The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning

神经符号AI的RAIL原则：推理（Reasoning）、保证（Assurances）、接口（Interfacing）与学习（Learning）

Agnese Chiatti, Michael Cochez, Cristina Cornelio, Sebastijan Dumancic, Artur d'Avila Garcez, Luis C. Lamb, Lia Morra, Mathias Niepert, Robert Peharz, Alberto Speranzon, Maarten Stol, Annette Ten Teije, Thiviyan Thanapalasingam, Frank Van Harmelen, Emile Van Krieken, Antonio Vergari, Benjie Wang

机构 * Politecnico di Milano（米兰理工大学）； ELLIS Institute Finland（芬兰ELLIS研究所）； Åbo Akademi University（奥博 Akademi 大学）； Samsung AI（三星人工智能研究院）； Delft University of Technology（代尔夫特理工大学）； Stony Brook University（石溪大学）； Politecnico di Torino（都灵理工大学）； University of Stuttgart（斯图加特大学）； Graz University of Technology（格拉茨工业大学）； Lockheed Martin, Advanced Technology Labs（洛克希德·马丁公司先进技术实验室）； BrainCreators（BrainCreators公司）； Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）； University of Amsterdam（阿姆斯特丹大学）； University of Edinburgh（爱丁堡大学）； UCLA（加利福尼亚大学洛杉矶分校）

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

AI总结该文提出神经符号AI的RAIL四项原则，可统一分析多类AI系统，助力工程师更科学地设计部署生产级AI，指导整合神经符号方法到下一代AI技术。

2402.03667 2025-01-28 cs.CL cs.AI 88%

Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning

Yanfang Zhang, Yiliu Sun, Yibing Zhan, Dapeng Tao, Dacheng Tao, Chen Gong

专题命中代码与定理证明：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；logical reasoning(abstract)

Comments Accepted by COLING 2025 conference

2606.15972 2026-06-16 cs.CL cs.AI cs.LG 新提交 88%

Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning

一次形式化，其余编辑：基于Lean的高效数学推理答案选择

Ji Feng, Zhouxing Shi

机构 * University of California, Riverside（加州大学河滨分校）

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

AI总结提出BASE流水线，通过形式化一个候选答案并编辑其余答案，减少自动形式化调用约5倍，同时提升选择准确性。

Comments 15 pages, 1 figure. Code available at https://github.com/ucr-rai/base-and-edit

1. 数学推理 3222 篇

Code as Policies: Language Model Programs for Embodied Control

Dynamic Routing for Traffic Flow through Multi-agent Systems

Expected Utilitarianism

Generating Comfortable, Safe and Comprehensible Trajectories for Automated Vehicles in Mixed Traffic

Tokenized Data Markets

A simplified model based on self-organized criticality framework for the seismic assessment of urban areas

Time-consistent stopping under decreasing impatience

Socio-Affective Agents as Models of Human Behaviour in the Networked Prisoner's Dilemma

Reconciling Rationality and Stochasticity: Rich Behavioral Models in Two-Player Games

Integrated STEM in Elementary Grades Using Distributed Agent-based Computation

What does mathoverflow tell us about the production of mathematics?

A Combinatorial Bit Bang Leading to Quaternions

2. 代码与定理证明 1127 篇

The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation

MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning

Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning

CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution

When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors

VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning

Chain-of-Thought Reasoning is a Policy Improvement Operator

Do Large Language Models Excel in Complex Logical Reasoning with Formal Language?

Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI

From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought

LeanReasoner: Boosting Complex Logical Reasoning with Lean

The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning

Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning

Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning