大模型推理能力

Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention

Xinhan Di, JoyJiaoW

机构 * Independent, Researcher, China（中国独立研究者） 纠错

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

Comments 7 pages, 1 table, accepted by SIM ICML@2025 Workshop

Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

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

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation

Ziyao Wang, Guoheng Sun, Yexiao He, Zheyu Shen, Bowei Tian, Ang Li

机构 * University of Maryland, College Park（马里兰大学学院公园分校） 纠错

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

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

Rui Jiao, Yue Zhang, Jinku Li

机构 * School of Cyber Engineering, Xidian University（西安电子科技大学电子工程学院） ； School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院） 纠错

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

Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules

Yilun Liu, Yunpu Ma, Yuetian Lu, Shuo Chen, Zifeng Ding, Volker Tresp

机构 * Technical University of Munich（慕尼黑技术大学） ； Ludwig Maximilian University of Munich（慕尼黑路德维希-马克西米利安大学） ； University of Cambridge（剑桥大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；math reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This paper is a preprint under review. arXiv admin note: text overlap with arXiv:2411.08212

Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games

Yunhao Liang, Yuan Qu, Jingyuan Yang, Shaochong Lin, Zuo-Jun Max Shen

专题命中 数学推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

Juzheng Zhang, Jiacheng You, Ashwinee Panda, Tom Goldstein

机构 * University of Maryland（马里兰大学） ； Tsinghua University（清华大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments COLM 2025

Self-Evolving Critique Abilities in Large Language Models

Zhengyang Tang, Ziniu Li, Zhenyang Xiao, Tian Ding, Ruoyu Sun, Benyou Wang, Dayiheng Liu, Fei Huang, Tianyu Liu, Bowen Yu, Junyang Lin

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； Shenzhen International Center for Industrial and Applied Mathematics（深圳国际工业与应用数学中心） ； Qwen Team, Alibaba Inc.（阿里云通义团队） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by COLM 2025

Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs

Jack Chen, Fazhong Liu, Naruto Liu, Yuhan Luo, Erqu Qin, Harry Zheng, Tian Dong, Haojin Zhu, Yan Meng, Xiao Wang

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

MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification

Ming Pok Ng, Junqi Jiang, Gabriel Freedman, Antonio Rago, Francesca Toni

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

Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents

Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, Zheng Cai

专题命中 代码与定理证明 ：reasoning(abstract)

Comments Accepted at the NIPS ML4PS Workshop 2024. The journal version is in preparation. Code and data will be fully made public following the journal publication. We welcome any comments and feedback

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Jingyi Zhang, Jiaxing Huang, Huanjin Yao, Shunyu Liu, Xikun Zhang, Shijian Lu, Dacheng Tao

机构 * Nanyang Technological University（南洋理工大学） 纠错

专题命中 逻辑推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICCV 2025 Camera Ready

Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis

Dominic Simon, Rickard Ewetz

机构 * University of Florida（佛罗里达大学） 纠错

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

Comments 14 pages, 15 figures, pre-print of paper accepted to IJCAI 2025

How Far Are LLMs from Symbolic Planners? An NLP-Based Perspective

Ma'ayan Armony, Albert Meroño-Peñuela, Gerard Canal

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

Relation-Aware LNN-Transformer for Intersection-Centric Next-Step Prediction

Zhehong Ren, Tianluo Zhang, Yiheng Lu, Yushen Liang, Promethee Spathis

机构 * New York University Shanghai（纽约大学上海） 纠错

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

Comments 8 pages, 5 figures

AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers

Donghao Yang, Aolang Wu, Tianyi Zhang, Li Zhang, Fang Liu, Xiaoli Lian, Yuming Ren, Jiaji Tian, Xiaoyin Che

机构 * Beihang University, China（北京航空航天大学） ； Siemens AG（西门子股份公司） 纠错

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

Comments 12 pages, 3 figures. Replaces "A Multi-Agent Framework for Extensible Structured Text Generation in PLCs" with an updated AutoPLC framework and new experiments

Testing the Untestable? An Empirical Study on the Testing Process of LLM-Powered Software Systems

Cleyton Magalhaes, Italo Santos, Brody Stuart-Verner, Ronnie de Souza Santos

专题命中 逻辑推理 ：reasoning(abstract)

Exploring 3D Reasoning-Driven Planning: From Implicit Human Intentions to Route-Aware Activity Planning

Xueying Jiang, Wenhao Li, Xiaoqin Zhang, Ling Shao, Shijian Lu

专题命中 规划推理 ：reasoning(title,abstract)；planning(title,abstract)

Emergent Response Planning in LLMs

Zhichen Dong, Zhanhui Zhou, Zhixuan Liu, Chao Yang, Chaochao Lu

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

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

Comments Published at ICML 2025. Code available at: https://github.com/niconi19/Emergent-Response-Planning-in-LLMs

Journal ref Proceedings of the 42nd International Conference on Machine Learning (ICML 2025)

Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search

Mikhail Andronov, Natalia Andronova, Michael Wand, Jürgen Schmidhuber, Djork-Arné Clevert

机构 * SUPSI, IDSIA（SUPSI、IDSIA） ； Pfizer Research and Development（辉瑞研发） ； Institute for Digital Technologies for Personalized Healthcare（个性化医疗数字技术研究所） ； KAUST（王国立科技大学） ； Center for Generative AI（生成人工智能中心） 纠错

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

L3M+P: Lifelong Planning with Large Language Models

Krish Agarwal, Yuqian Jiang, Jiaheng Hu, Bo Liu, Peter Stone

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

A Multi-Agent Pokemon Tournament for Evaluating Strategic Reasoning of Large Language Models

Tadisetty Sai Yashwanth, Dhatri C

机构 * TuriLabs 纠错

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

Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks

Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami

机构 * University of Tokyo（东京大学） 纠错

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

Journal ref ICML 2025

When not to help: planning for lasting human-AI collaboration

Mark Steyvers, Lukas Mayer

专题命中 规划推理 ：planning(title)；reasoning(abstract)

An analysis of AI Decision under Risk: Prospect theory emerges in Large Language Models

Kenneth Payne

机构 * King’s College London（伦敦国王学院） 纠错

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

Comments 26 pages, 2 figures, 9 tables, 2 appendices

Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous Driving

Hunter Schofield, Mohammed Elmahgiubi, Kasra Rezaee, Jinjun Shan

机构 * Noah’s Ark Lab, Huawei Technologies Canada（华为技术加拿大分公司诺亚 Ark 实验室） ； York University, Toronto, Canada（多伦多大学） 纠错

专题命中 规划推理 ：planning(title)

Comments Accepted ICRA 2025

Distributed AI Agents for Cognitive Underwater Robot Autonomy

Markus Buchholz, Ignacio Carlucho, Michele Grimaldi, Yvan R. Petillot

机构 * School of Engineering & Physical Sciences, Heriot-Watt University（工程与物理科学学院，赫里奥特-瓦特大学） 纠错

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

A Survey on Agent Workflow -- Status and Future

Chaojia Yu, Zihan Cheng, Hanwen Cui, Yishuo Gao, Zexu Luo, Yijin Wang, Hangbin Zheng, Yong Zhao

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

Comments 12 pages, 3 figures, accepted to IEEE Conference, ICAIBD(International Conference of Artificial Intelligence and Big Data) 2025. This is the author's version, not the publisher's. See https://ieeexplore.ieee.org/document/11082076

Journal ref IEEE ICAIBD 2025, pp. 770-781

Eyes Will Shut: A Vision-Based Next GPS Location Prediction Model by Reinforcement Learning from Visual Map Feed Back

Ruixing Zhang, Yang Zhang, Tongyu Zhu, Leilei Sun, Weifeng Lv

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Pre-Tactical Flight-Delay and Turnaround Forecasting with Synthetic Aviation Data

Abdulmajid Murad, Massimiliano Ruocco

机构 * Department of Software Engineering, Safety and Security（软件工程与安全系） ； SINTEF Digital（SINTEF数字研究院） ； Norwegian University of Science and Technology（挪威科技大学） 纠错

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

Comments Preprint. Under review