语言大模型 / LLM

Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text

Zhun Yang, Adam Ishay, Joohyung Lee

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments 32 pages, Findings of the Association for Computational Linguistics: ACL 2023, 5186-5219

AutoScrum: Automating Project Planning Using Large Language Models

Martin Schroder

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments 25 pages, 3 figures, demo: https://github.com/autoscrum/autoscrum

Large Language Models Can Be Easily Distracted by Irrelevant Context

Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed Chi, Nathanael Schärli, Denny Zhou

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments Published in ICML 2023

Teaching Small Language Models to Reason

Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, Aliaksei Severyn

专题命中 推理与问题求解 ：language model(title,abstract)；small language model(title)；large language model(abstract)；prompting(abstract)

Gorilla: Large Language Model Connected with Massive APIs

Shishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. Gonzalez

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Enhance Reasoning Ability of Visual-Language Models via Large Language Models

Yueting Yang, Xintong Zhang, Wenjuan Han

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Leveraging Large Language Models in Conversational Recommender Systems

Luke Friedman, Sameer Ahuja, David Allen, Zhenning Tan, Hakim Sidahmed, Changbo Long, Jun Xie, Gabriel Schubiner, Ajay Patel, Harsh Lara, Brian Chu, Zexi Chen, Manoj Tiwari

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.LG

Boosted Prompt Ensembles for Large Language Models

Silviu Pitis, Michael R. Zhang, Andrew Wang, Jimmy Ba

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.LG

How well do Large Language Models perform in Arithmetic tasks?

Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Rethinking with Retrieval: Faithful Large Language Model Inference

Hangfeng He, Hongming Zhang, Dan Roth

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Towards a Mathematics Formalisation Assistant using Large Language Models

Ayush Agrawal, Siddhartha Gadgil, Navin Goyal, Ashvni Narayanan, Anand Tadipatri

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Exploring Length Generalization in Large Language Models

Cem Anil, Yuhuai Wu, Anders Andreassen, Aitor Lewkowycz, Vedant Misra, Vinay Ramasesh, Ambrose Slone, Guy Gur-Ari, Ethan Dyer, Behnam Neyshabur

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Antonia Creswell, Murray Shanahan, Irina Higgins

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage

TPTU：基于大型语言模型的AI代理用于任务规划和工具使用

Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； SenseTime Research（商汤科技研究院） ； HKUST（香港科技大学） 纠错

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

AI总结 本文提出基于大型语言模型的AI代理框架，设计两种代理类型以提升任务规划和工具使用能力，并通过实验验证其在复杂任务中的有效性。

Comments Accepted in NeurIPS-2023 Workshop on Foundation Models for Decision Making

Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning

推理中继：评估大型语言模型在数学推理中的稳定性与可替换性

Leo Lu, Jonathan Zhang, Sean Chua, Spencer Kim, Kevin Zhu, Sean O'Brien, Vasu Sharma

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Binghamton University（宾夕法尼亚州立大学布林茅尔分校） ； University of Toronto（多伦多大学） ； UC Berkeley（加州大学伯克利分校） ； Algoverse 纠错

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.AI

AI总结 本研究探讨大型语言模型在数学推理中的稳定性与可替换性，通过评估不同模型间推理链的延续性，揭示推理过程的可靠性和一致性。

Comments NeurIPS 2025 Workshop on Socially Responsible and Trustworthy Foundation Models (ResponsibleFM)

Evaluating Large Language Models for Workload Mapping and Scheduling in Heterogeneous HPC Systems

Aasish Kumar Sharma, Julian Kunkel

机构 * Faculty of Mathematics and Computer Science, Georg-August-Universität Göttingen（数学与计算机科学学院，哥廷根乔治-奥古斯特大学） 纠错

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；分类 cs.AI

Comments 14 pages, 4 figures, 2 tables. Evaluation study on LLM-based reasoning for HPC scheduling. Published in Research in Academic Engineering Journal (RAEJ), 2025

Journal ref Robot Autom Eng J. 2025; 6(5): 555696

Towards Transparent Reasoning: What Drives Faithfulness in Large Language Models?

Teague McMillan, Gabriele Dominici, Martin Gjoreski, Marc Langheinrich

机构 * ETH Zurich（苏黎世联邦理工学院） ； Università della Svizzera italiana（瑞士意大利大学） 纠错

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

Enriching Ontologies with Disjointness Axioms using Large Language Models

Elias Crum, Antonio De Santis, Manon Ovide, Jiaxin Pan, Alessia Pisu, Nicolas Lazzari, Sebastian Rudolph

专题命中 推理与问题求解 ：language model(title,abstract)；large language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments Accepted at KBC-LM'24 workshop at ISWC 2024, https://ceur-ws.org/Vol-3853/paper1.pdf

Journal ref Proc. of 2nd Workshop on Knowledge Base Construction from Pre-Trained Language Models (KBC-LM 2024) co-located with ISWC 2024, Baltimore, USA, November 12, 2024

Re-Thinking Inverse Graphics With Large Language Models

Peter Kulits, Haiwen Feng, Weiyang Liu, Victoria Abrevaya, Michael J. Black

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；分类 cs.CL

Comments TMLR camera-ready; 31 pages; project page: https://ig-llm.is.tue.mpg.de/

Complex Logical Reasoning over Knowledge Graphs using Large Language Models

Nurendra Choudhary, Chandan K. Reddy

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；分类 cs.AI

Comments Code available at https://github.com/Akirato/LLM-KG-Reasoning

REST API Testing with Verified LLM-Inferred Dependencies and Response-Driven Refinement

基于经验证的LLM推断依赖关系与响应驱动优化的REST API测试

Tu Nguyen, Thanh Nguyen, Huy Nguyen, Viet Nguyen, Tien N. Nguyen, Vu Nguyen

专题命中 推理与问题求解 ：LLM(title,title_cn)

AI总结 本文提出APIPilot框架，通过执行验证LLM推断的REST API依赖关系，结合响应驱动优化，在16个真实API上实现高覆盖率与成功率，优于现有基线。

Comments Submitted to ICSE 2027

Logos: Certified Order-Sensitive SQL Rewrites with Mechanized Semantics and LLM Guidance

Logos：结合机械化语义与LLM指导的可验证顺序敏感型SQL重写

Jingyu Ke, Jingyang Li, Guoqiang Li

专题命中 推理与问题求解 ：LLM(title,title_cn)

AI总结 Logos是一款结合Rocq机械化语义与LLM指导的SQL重写验证工具，解决了现有工具的不足，在389个查询对的评估中解决率达86.9%，优于基线工具SQLSolver。

Comments 13 pages, 4 figures, and 3 tables

When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems

当真相被分散时：错误信息会破坏基于大语言模型（LLM）的多智能体系统中的集体事实恢复

Chenfei Yan, Zeyang Yue, Feifei Zhao, Erliang Lin, Lu Jia, Haibo Tong, Mingyang Lyu, Chengyi Sun, Yi Zeng

专题命中 推理与问题求解 ：LLM(title,title_cn)

AI总结 本研究提出Hi-Agreement评估框架，发现基于LLM的多智能体系统中，关键证据持有者的虚假证词会破坏集体事实恢复，使恢复率从72.50%降至14.17%，且虚假证据会持续传播。

LLM Ensemble Fault Classification for Automotive HiL Validation

面向汽车HiL验证的大语言模型集成故障分类

Hamza Ouarrad, Mohammad Abboush, Andreas Rausch

专题命中 推理与问题求解 ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)

AI总结 本文提出可解释多LLM集成框架，结合异构LLM输出提升汽车HiL验证故障分类性能，经多车型多场景评估，Top-3集成优于单模型及Top-5集成，实现更优诊断效果。

Comments 8 pages, 3 figures. Accepted at the 23rd Workshop on Model Driven Engineering, Verification and Validation (MoDeVVa 2026), co-located with MODELS 2026. Original submitted version

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

CARE：用于执行 shell 的语言模型代理的执行前命令验证

Yu Liu, Wenxiao Zhang, Zhiwei Yang, Zhongyi Zhang, Hanqi Feng, Xinyu Wang, Peng Qiu, Yanbing Liu, Barnabas Poczos, Jin B. Hong

专题命中 推理与问题求解 ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)

AI总结 研究 LLM 代理执行 shell 命令时的调度风险，提出 CARE 验证器，通过规范化命令、推导证据并结合 LLM 判断，实现命令级调解，降低调度边界风险，平衡良性恢复、误报负担、延迟和危害降低之间的关系。

Comments Accepted by ISSRE 2026

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning

CVPO：通过值方差自适应与动态课程学习增强大语言模型的强化学习推理能力

Ziqi Jia, Yalu Ouyang, Bo Pang, Panpan Li, Hangfei Xu, Shengzhao Wen, Shiyong Li, Yanpeng Wang

专题命中 推理与问题求解 ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结 针对LLM强化学习推理中反馈精度不足与问题难度漂移问题，提出CVPO方法，通过值方差自适应与动态课程学习优化，在数学任务上性能优于VAPO等基线。

Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks

通过辩论提升大语言模型性能：针对编码任务的多智能体辩论实证研究

Yong Jin Chun, Qihong Chen, Jiawei Li, Iftekhar Ahmed

专题命中 推理与问题求解 ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)

AI总结 本研究探究多智能体辩论（MAD）在软件工程四类编码任务上的有效性，适配NLP的MAD框架并提出两种变体，证实结构化辩论可提升LLM编码性能，凸显其协作协同效应。

Comments accepted to ACM Transactions on Software Engineering and Methodology (TOSEM)

CinemaTraj: Composing Atomic Camera Trajectories for 3D Scenes with LLM Agents

CinemaTraj：用LLM智能体为3D场景合成原子相机轨迹

Qianru Li, Xuyang Chen, Erkin Türköz, Lu Liu, Xuqin Wang, Liqiu Meng, Tao Wu, Yanfeng Zhang

机构 * Technical University of Munich（慕尼黑工业大学） ； Huawei Dresden Research Center（华为德累斯顿研究中心） 纠错

专题命中 推理与问题求解 ：LLM(title,title_cn)

AI总结 CinemaTraj是将LLM智能体与3D场景图结合的框架，可从自然语言生成带旁白的3D场景相机轨迹，在真实环境中优于现有方法。

Comments 17 pages, including 8-page main paper, references, and supplementary material; project page: https://cinematraj.github.io/

zkCraft: Prompt-Guided LLM as a Zero-Shot Mutation Pattern Oracle for TCCT-Powered ZK Fuzzing

zkCraft: 基于提示的LLM作为零知识电路模糊测试的零样本突变模式Oracle

Rong Fu, Jia Yee Tan, Ziyu Kong, Shuning Zhang, Xianda Li, Kun Liu, Youjin Wang, Simon Fong

专题命中 推理与问题求解 ：LLM(title,title_cn)

AI总结 zkCraft结合确定性R1CS感知本地化与证明承载搜索，通过编码候选约束编辑为Row-Vortex多项式，利用LLM驱动的突变模板检测语义不一致，降低误报并提升ZK电路开发的鲁棒性。

Comments 36 pages, 12 figures, 9 tables

ParaTutor: Coordinating Parent and Child Math Tutoring through Role Separated LLM Scaffolding

ParaTutor: 通过角色分离的实时脚手架界面实现LLM介导的亲子辅导

Lan Luo, Anqi Wang, Muzhi Zhou, Junhua Zhu, Jie Cai, Ao Yu, Hui Pan

专题命中 推理与问题求解 ：LLM(title,title_cn)

AI总结 针对亲子辅导中角色不对称问题，提出ParaTutor系统，通过为家长提供辅导指导、为孩子提供视觉基础，在实时互动中保持家长主导和孩子参与，实验表明优于通用LLM辅助。