大模型推理能力

LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters

Klaudia Bałazy, Mohammadreza Banaei, Karl Aberer, Jacek Tabor

机构 * Jagiellonian University（雅盖隆大学） ； EPFL（苏黎世联邦理工学院） 纠错

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

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Shuaijie She, Yu Bao, Yu Lu, Lu Xu, Tao Li, Wenhao Zhu, Shujian Huang, Shanbo Cheng, Lu Lu, Yuxuan Wang

机构 * Nanjing University（南京大学） 纠错

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

Comments 18 pages, 4 figures,

Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving

Xinji Mai, Haotian Xu, Zhong-Zhi Li, Xing W, Weinong Wang, Jian Hu, Yingying Zhang, Wenqiang Zhang

机构 * Fudan University（复旦大学） ； Xiaohongshu（小红书） ； East China Normal University（华东师范大学） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

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

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders

Cliff O'Reilly, Ernesto Jimenez-Ruiz, Tillman Weyde

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

LeanGeo: Formalizing Competitional Geometry problems in Lean

Chendong Song, Zihan Wang, Frederick Pu, Haiming Wang, Xiaohan Lin, Junqi Liu, Jia Li, Zhengying Liu

机构 * Moonshot AI ； Numina ； Peking University（北京大学） ； University of Toronto（多伦多大学） 纠错

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

Comments 28 pages

Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement

Hong Su

机构 * School of Computer Science, Chengdu University of Information Technology（计算机科学学院，成都信息科技学院） 纠错

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

Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models

Wuyang Zhang, Yexin Tian, Xiandong Meng, Mengjie Wang, Junliang Du

专题命中 逻辑推理 ：reasoning(title,abstract)；分类 cs.CL

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference

Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban

机构 * Texas A\&M University, College Station, TX., USA（德克萨斯大学） ； Hamad Bin Khalifa University, Doha, Qatar（哈马德·本·卡伊夫大学） 纠错

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

Comments Under review

Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model

Siheng Xiong, Ali Payani, Yuan Yang, Faramarz Fekri

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Cisco Research（思科研究） 纠错

专题命中 规划推理 ：reasoning(title,abstract)；planning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments ACL25 (main)

Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination

João Vitor de Carvalho Silva, Douglas G. Macharet

机构 * Computer Vision and Robotics Laboratory (VeRLab), Department of Computer Science, Universidade Federal de Minas Gerais（计算机视觉与机器人实验室（VeRLab）、计算机科学系、巴西联邦大学矿务格里斯大学） 纠错

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

LaViPlan : Language-Guided Visual Path Planning with RLVR

Hayeon Oh

机构 * Electronics and Telecommunications Research Institute（电子通信研究院） 纠错

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

Comments Accepted to the 2nd ICCV 2025 Workshop on the Challenge of Out-of-Label Hazards in Autonomous Driving (13 pages, 6 figures)

DeepRetro: Retrosynthetic Pathway Discovery using Iterative LLM Reasoning

Shreyas Vinaya Sathyanarayana, Sharanabasava D. Hiremath, Rahil Shah, Rishikesh Panda, Rahul Jana, Riya Singh, Rida Irfan, Ashwin Murali, Bharath Ramsundar

机构 * Deep Forest Sciences（深林科学） 纠错

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

Comments 64 pages,

Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs

Luca Annese, Sabrina Patania, Silvia Serino, Tom Foulsham, Silvia Rossi, Azzurra Ruggeri, Dimitri Ognibene

机构 * University of Milan-Bicocca（米兰-比科卡大学） ； University of Essex（埃塞克斯大学） ； University of Naples Federico II（那不勒斯费德里科二世大学） ； TUM School of Social Sciences and Technology（技术与社会科学学院） 纠错

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

Comments Accepted at ICSR25

New Insights into Automatic Treatment Planning for Cancer Radiotherapy Using Explainable Artificial Intelligence

Md Mainul Abrar, Xun Jia, Yujie Chi

机构 * Department of Physics, The University of Texas at Arlington（德克萨斯大学阿灵顿分校物理系） ； Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University（约翰霍普金斯大学放射肿瘤学与分子放射科学系） 纠错

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

Comments 19 pages, 7 figures, 1 table, Oral presentation at the conference 'American Association of Physicists in Medicine 2025, 67th Annual Meeting and Exhibition'

Congestion Mitigation Path Planning for Large-Scale Multi-Agent Navigation in Dense Environments

Takuro Kato, Keisuke Okumura, Yoko Sasaki, Naoya Yokomachi

专题命中 规划推理 ：planning(title,abstract)

Comments Published in IEEE Robotics and Automation Letters (RA-L), 2025. Supplementary videos are accessible via IEEE Xplore

Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 10, pp. 9742-9749, 2025

TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Prompting

Jiaming Leng, Yunying Bi, Chuan Qin, Bing Yin, Yanyong Zhang, Chao Wang

机构 * University of Science and Technology of China（科学技术大学） ； Computer Network Information Center, Chinese Academy of Sciences.（中国科学院计算机网络信息中心） 纠错

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

DEXTER-LLM: Dynamic and Explainable Coordination of Multi-Robot Systems in Unknown Environments via Large Language Models

Yuxiao Zhu, Junfeng Chen, Xintong Zhang, Meng Guo, Zhongkui Li

机构 * College of Engineering, Peking University（北京大学工程学院） ； Division of Natural and Applied Sciences, Duke Kunshan University（杜克昆山大学自然科学与应用科学系） 纠错

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

Comments submitted to IROS 2025

SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing

Jing Chen, Zhiheng Yang, Yixian Shen, Jie Liu, Adam Belloum, Chrysa Papagainni, Paola Grosso

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

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

Comments The code is available at https://github.com/SurveyGens/SurveyGen-I , 20 pages, 16 figures

Towards Agent-based Test Support Systems: An Unsupervised Environment Design Approach

Collins O. Ogbodo, Timothy J. Rogers, Mattia Dal Borgo, David J. Wagg

机构 * Dynamic Research Group（动态研究组） ； School of Mechanical, Aerospace and Civil Engineering（机械、航空航天与土木工程学院） ； University of Sheffield（谢菲尔德大学） ； Siemens Digital Industries Software NV（西门子数字工业软件公司） ； The Alan Turing Institute（艾伦·图灵研究所） 纠错

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

Comments 17 pages, 11 figures; currently under peer review

TCFNet: Bidirectional face-bone transformation via a Transformer-based coarse-to-fine point movement network

Runshi Zhang, Bimeng Jie, Yang He, Junchen Wang

机构 * School of Mechanical Engineering and Automation, Beihang University（北京航空航天大学机械工程及自动化学院） ； Peking University School and Hospital of Stomatology（北京大学口腔医学院） 纠错

专题命中 规划推理 ：planning(abstract)

Comments 17 pages, 11 figures

Journal ref Medical Image Analysis 2025

SLAM-based Safe Indoor Exploration Strategy

Omar Mostafa, Nikolaos Evangeliou, Anthony Tzes

机构 * Center for Artificial Intelligence \& Robotics (CAIR) New York University Abu Dhabi (NYUAD) United Arab Emirates ； Robotics \& Intelligent Systems Control Lab NYUAD United Arab Emirates 纠错

专题命中 规划推理 ：planning(abstract)

Comments 5 pages, 8 figures. Published in the 2025 11th International Conference on Automation, Robotics, and Applications (ICARA)

Journal ref 2025 11th International Conference on Automation, Robotics, and Applications (ICARA), pp. 375-379

CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning

Jeonghyo Song, Kimin Yun, DaeUng Jo, Jinyoung Kim, Youngjoon Yoo

机构 * Department of Artificial Intelligence, Chung-Ang University（Chung-Ang大学人工智能系） ； Visual Intelligence Lab., ETRI（ETRI视觉智能实验室） ； University of Science and Technology (UST)（科技大学（UST）） ； School of Electronics Engineering, Kyungpook National University（Kyungpook国立大学电子工程学院） 纠错

专题命中 视觉空间推理 ：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(title,abstract)

Comments 6 pages, 3 figures. Accepted at IEEE International Conference on Advanced Visual and Signal-Based Systems 2025

MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

Ziyang Luo, Zhiqi Shen, Wenzhuo Yang, Zirui Zhao, Prathyusha Jwalapuram, Amrita Saha, Doyen Sahoo, Silvio Savarese, Caiming Xiong, Junnan Li

机构 * Salesforce AI Research（Salesforce人工智能研究） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Website: https://mcp-universe.github.io

Tooth-Diffusion: Guided 3D CBCT Synthesis with Fine-Grained Tooth Conditioning

Said Djafar Said, Torkan Gholamalizadeh, Mostafa Mehdipour Ghazi

机构 * Pioneer Centre for AI, Department of Computer Science, University of Copenhagen Research（先锋人工智能中心、计算机科学系、哥本哈根大学研究） 纠错

专题命中 视觉空间推理 ：planning(abstract)；分类 cs.AI

Comments MICCAI 2025 Workshop on Oral and Dental Image Analysis (ODIN)

3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds

Fan-Yun Sun, Shengguang Wu, Christian Jacobsen, Thomas Yim, Haoming Zou, Alex Zook, Shangru Li, Yu-Hsin Chou, Ethem Can, Xunlei Wu, Clemens Eppner, Valts Blukis, Jonathan Tremblay, Jiajun Wu, Stan Birchfield, Nick Haber

机构 * Stanford University（斯坦福大学） ； Nvidia Research（英伟达研究） 纠错

专题命中 视觉空间推理 ：reasoning(abstract)

Comments project website: https://ai.stanford.edu/~sunfanyun/3d-generalist/

It Takes Two: A Peer-Prediction Solution for Blockchain Verifier's Dilemma

Zishuo Zhao, Xi Chen, Yuan Zhou

专题命中 测试时计算 ：verifier(title,abstract)

Comments 63 pages

MultiFuzz: A Dense Retrieval-based Multi-Agent System for Network Protocol Fuzzing

Youssef Maklad, Fares Wael, Ali Hamdi, Wael Elsersy, Khaled Shaban

机构 * Dept. of Computer Science, Qatar University, Doha, Qatar（计算机科学系，卡塔尔大学，多哈） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources

Alisia Lupidi, Carlos Gemmell, Nicola Cancedda, Jane Dwivedi-Yu, Jason Weston, Jakob Foerster, Roberta Raileanu, Maria Lomeli

机构 * Meta Superintelligence labs（Meta超智能实验室） ； University of Oxford（牛津大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.AI

A Multi-Agent Approach to Neurological Clinical Reasoning

Moran Sorka, Alon Gorenshtein, Dvir Aran, Shahar Shelly

专题命中 推理评测 ：reasoning(title,abstract)；logical reasoning(abstract)；分类 cs.AI

JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics

Simindokht Jahangard, Mehrzad Mohammadi, Yi Shen, Zhixi Cai, Hamid Rezatofighi

专题命中 推理评测 ：reasoning(title,abstract)