大模型推理能力

Prompt Decorators: A Declarative and Composable Syntax for Reasoning, Formatting, and Control in LLMs

Mostapha Kalami Heris

机构 * School of Engineering and Built Environment（工程与建筑环境学院） ； College of Business（商学院） ； Sheffield Hallam University（谢菲尔德哈姆大学） 纠错

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

Conjecturing: An Overlooked Step in Formal Mathematical Reasoning

Jasivan Alex Sivakumar, Philipp Borchert, Ronald Cardenas, Gerasimos Lampouras

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

Formal Reasoning for Intelligent QA Systems: A Case Study in the Educational Domain

Tuan Bui, An Nguyen, Phat Thai, Minh Hua, Ngan Pham L. N., Ngan Pham T. B., Dung Le, Long Nguyen, Thanh-Tung Tran, Thang Bui, Tho Quan

机构 * Ho Chi Minh City University of Technology (HCMUT) - VNU-HCM（胡志明市技术大学（HCMUT）- VNU-HCM） ； International University - VNU-HCM（国际大学 - VNU-HCM） 纠错

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

Comments Published at the 2nd ACM Workshop in AI-powered Question & Answering Systems (AIQAM '25), co-located with ACM Multimedia 2025

Journal ref Proceedings of the 2nd ACM Workshop in AI-powered Question and Answering Systems (AIQAM '25), October 27-28, 2025, Dublin, Ireland

Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

Valentin Quesnel, Damien Sileo

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

ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding

Sining Zhoubian, Dan Zhang, Jie Tang

机构 * The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程小组（KEG）、清华大学） 纠错

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

Comments 21 pages, 4 figures

Understanding Tool-Integrated Reasoning

Heng Lin, Zhongwen Xu

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

LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

Bingxi Zhao, Lin Geng Foo, Ping Hu, Christian Theobalt, Hossein Rahmani, Jun Liu

机构 * Beijing Jiaotong University（北京交通大学） ； Lancaster University（兰卡斯特大学） ； Max Planck Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克研究所（信息学）萨尔兰州信息学校区） ； University of Electronic Science and Technology of China（电子科技大学） 纠错

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

Comments 51 pages,10 figures,8 tables. Work in progress

Investigating the Robustness of Deductive Reasoning with Large Language Models

Fabian Hoppe, Filip Ilievski, Jan-Christoph Kalo

机构 * Vrije Universiteit Amsterdam（阿姆斯特丹自由大学） ； Universiteit van Amsterdam（阿姆斯特丹大学） 纠错

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

Comments to be published in ECAI 2025

Retrieval-augmented reasoning with lean language models

Ryan Sze-Yin Chan, Federico Nanni, Tomas Lazauskas, Rosie Wood, Penelope Yong, Lionel Tarassenko, Mark Girolami, James Geddes, Andrew Duncan

机构 * The Alan Turing Institute（艾伦·图灵研究所） ； University of Oxford（牛津大学） ； University of Cambridge（剑桥大学） ； Imperial College London（伦敦帝国学院） 纠错

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

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

Ziyin Zhang, Jiahao Xu, Zhiwei He, Tian Liang, Qiuzhi Liu, Yansi Li, Linfeng Song, Zhenwen Liang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu

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

How Do LLMs Perform Two-Hop Reasoning in Context?

Tianyu Guo, Hanlin Zhu, Ruiqi Zhang, Jiantao Jiao, Song Mei, Michael I. Jordan, Stuart Russell

机构 * Department of Statistics, UC Berkeley（统计学系，伯克利大学） ； Department of EECS, UC Berkeley（电子工程与计算机科学系，伯克利大学） 纠错

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

Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks

Debargha Ganguly, Vikash Singh, Sreehari Sankar, Biyao Zhang, Xuecen Zhang, Srinivasan Iyengar, Xiaotian Han, Amit Sharma, Shivkumar Kalyanaraman, Vipin Chaudhary

机构 * Case Western Reserve University（凯斯西储大学） ； Microsoft Corporation（微软公司） ； Microsoft Research（微软研究院） 纠错

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

Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning

Alexander Beiser, David Penz, Nysret Musliu

机构 * TU Wien, Vienna, Austria（维也纳技术大学） ； Johannes Kepler University Linz, Linz, Austria（林茨约翰尼斯·凯普勒大学） 纠错

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

Reasoning Models Can Be Effective Without Thinking

Wenjie Ma, Jingxuan He, Charlie Snell, Tyler Griggs, Sewon Min, Matei Zaharia

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

Comments 33 pages, 7 main figures, 2 tables

Evaluating the Generalization Capabilities of Large Language Models on Code Reasoning

Rem Yang, Julian Dai, Nikos Vasilakis, Martin Rinard

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

PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement

Xin Quan, Marco Valentino, Danilo S. Carvalho, Dhairya Dalal, André Freitas

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

Comments Demo paper. Work in progress

Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching

Nooshin Bahador

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

Comments 15 pages, 3 figures

Grounding Agent Reasoning in Image Schemas: A Neurosymbolic Approach to Embodied Cognition

François Olivier, Zied Bouraoui

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

PRISM: Perspective Reasoning for Integrated Synthesis and Mediation as a Multi-Perspective Framework for AI Alignment

Anthony Diamond

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

Comments 104 pages, 5 figures. Preprint on AI alignment presenting PRISM: a multi-perspective framework that organizes moral concerns into seven basis worldviews and uses Pareto-inspired synthesis to reconcile conflicting human values and specification gaming. Grounded in cognitive science and moral psychology

Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning

Marco Sälzer, Eric Alsmann, Martin Lange

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

Formal Mathematical Reasoning: A New Frontier in AI

Kaiyu Yang, Gabriel Poesia, Jingxuan He, Wenda Li, Kristin Lauter, Swarat Chaudhuri, Dawn Song

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

Confidence in the Reasoning of Large Language Models

Yudi Pawitan, Chris Holmes

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

From Data to Commonsense Reasoning: The Use of Large Language Models for Explainable AI

Stefanie Krause, Frieder Stolzenburg

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

Comments 19 pages

Can formal argumentative reasoning enhance LLMs performances?

Federico Castagna, Isabel Sassoon, Simon Parsons

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

Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions

Pouya Pezeshkpour, Eser Kandogan, Nikita Bhutani, Sajjadur Rahman, Tom Mitchell, Estevam Hruschka

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

Meta Semantics: Towards better natural language understanding and reasoning

Xiaolin Hu

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

Comments 10 pages, 8 figures, 2 tables

Interpretable Proof Generation via Iterative Backward Reasoning

Hanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu

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

Comments NAACL-HLT 2022 (Long), 14 pages (2 page references + 3 page appendix)

Report on the First Knowledge Graph Reasoning Challenge 2018 -- Toward the eXplainable AI System

Takahiro Kawamura, Shusaku Egami, Koutarou Tamura, Yasunori Hokazono, Takanori Ugai, Yusuke Koyanagi, Fumihito Nishino, Seiji Okajima, Katsuhiko Murakami, Kunihiko Takamatsu, Aoi Sugiura, Shun Shiramatsu, Shawn Zhang, Kouji Kozaki

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

Causal Reasoning from Meta-reinforcement Learning

Ishita Dasgupta, Jane Wang, Silvia Chiappa, Jovana Mitrovic, Pedro Ortega, David Raposo, Edward Hughes, Peter Battaglia, Matthew Botvinick, Zeb Kurth-Nelson

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

Solving Bongard Problems with a Visual Language and Pragmatic Reasoning

Stefan Depeweg, Constantin A. Rothkopf, Frank Jäkel

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