大模型推理能力

From Extraction to Synthesis: Entangled Heuristics for Agent-Augmented Strategic Reasoning

Renato Ghisellini, Remo Pareschi, Marco Pedroni, Giovanni Battista Raggi

机构 * Institute for Generative Strategy（生成战略研究所） ； Stake Lab, University of Molise（莫利塞大学Stake实验室） 纠错

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

Comments Peer-reviewed full paper accepted through a double-blind review process at the HAR 2025 conference (https://har-conf.eu/). The official version will appear in a volume of the Lecture Notes in Computer Science (LNCS) series

ClarifAI: Enhancing AI Interpretability and Transparency through Case-Based Reasoning and Ontology-Driven Approach for Improved Decision-Making

Srikanth Vemula

机构 * Human-Centric eXplainable Intelligence Lab (hcXiL) Computer Science Department(CSCI), Saint John's University (CSBSJU)（以人为本的可解释智能实验室（hcXiL）计算机科学系，圣约翰大学） 纠错

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

Reinforced Imitative Trajectory Planning for Urban Automated Driving

Di Zeng, Ling Zheng, Xiantong Yang, Yinong Li

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

Comments 21 pages, 9 figures

LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing

Quanyan Zhu

机构 * Department of Electrical and Computer Engineering, New York University（电气与计算机工程系，纽约大学） 纠错

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

Synthesizing world models for bilevel planning

Zergham Ahmed, Joshua B. Tenenbaum, Christopher J. Bates, Samuel J. Gershman

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

Comments Accepted to TMLR

Reasoning and Behavioral Equilibria in LLM-Nash Games: From Mindsets to Actions

Quanyan Zhu

机构 * Department of Electrical ； Computer Engineering, New York University, Brooklyn, NY, USA 纠错

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

Application of LLMs to Multi-Robot Path Planning and Task Allocation

Ashish Kumar

机构 * Ashish Kumar（独立研究者） 纠错

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

Can LLMs Play Ô Ăn Quan Game? A Study of Multi-Step Planning and Decision Making

Sang Quang Nguyen, Kiet Van Nguyen, Vinh-Tiep Nguyen, Thanh Duc Ngo, Ngan Luu-Thuy Nguyen, Duy-Dinh Le

机构 * University of Information Technology Ho Chi Minh City Vietnam（越南胡志明市信息科技大学） ； Vietnam National University Ho Chi Minh City Vietnam（越南国家大学胡志明市分校） 纠错

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

Comments Accepted paper at MAPR 2025

LineRetriever: Planning-Aware Observation Reduction for Web Agents

Imene Kerboua, Sahar Omidi Shayegan, Megh Thakkar, Xing Han Lù, Massimo Caccia, Véronique Eglin, Alexandre Aussem, Jérémy Espinas, Alexandre Lacoste

机构 * INSA Lyon（里昂国立应用科学学院） ； Esker（Esker公司） ； ServiceNow Research（ServiceNow研究） ； Mila AI Institute（Mila人工智能研究所） ； McGill University（麦吉尔大学） ； Université Claude Bernard Lyon 1（里昂第一大学） ； LIRIS（LIRIS实验室） 纠错

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

Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning

Xiang Zhuang, Bin Wu, Jiyu Cui, Kehua Feng, Xiaotong Li, Huabin Xing, Keyan Ding, Qiang Zhang, Huajun Chen

机构 * Zhejiang University（浙江大学） ； ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙大杭州国际科创中心） ； University College London（伦敦大学学院） 纠错

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

Comments ACL 2025 Main

Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards

Alexander Gambashidze, Konstantin Sobolev, Andrey Kuznetsov, Ivan Oseledets

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

Comments We are withdrawing this paper because the main contributions and methodology have significantly changed after further research and experimental updates. The current version no longer reflects our results and main contribution / topic

Gazal-R1: Achieving State-of-the-Art Medical Reasoning with Parameter-Efficient Two-Stage Training

Ahmed M. Adly, Mostafa Samy, Amr Fawzy

机构 * TachyHealth 纠错

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

Large-Scale Multirobot Coverage Path Planning on Grids With Path Deconfliction

Jingtao Tang, Zining Mao, Hang Ma

机构 * School of Computing Science, Simon Fraser University（计算科学学院，西蒙弗雷泽大学） 纠错

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

Comments accepted to T-RO

Journal ref IEEE Transactions on Robotics, vol. 41, pp. 3348-3367, 2025

Case-based Reasoning Augmented Large Language Model Framework for Decision Making in Realistic Safety-Critical Driving Scenarios

Wenbin Gan, Minh-Son Dao, Koji Zettsu

机构 * Big Data Integration Research Center, National Institute of Information and Communications Technology (NICT), Tokyo, Japan（大数据整合研究室，日本信息通信技术研究所（NICT），东京） 纠错

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

Comments 12 pages, 10 figures, under-review conference

Do LLMs Know When to Flip a Coin? Strategic Randomization through Reasoning and Experience

Lingyu Yang

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

An intelligent tutor for planning in large partially observable environments

Lovis Heindrich, Saksham Consul, Falk Lieder

机构 * Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） ； Department of Psychology, UCLA（大学心理学系） 纠错

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

Planning of Heuristics: Strategic Planning on Large Language Models with Monte Carlo Tree Search for Automating Heuristic Optimization

Hui Wang, Xufeng Zhang, Chaoxu Mu

机构 * School of Artificial Intelligence, Anhui University, Hefei, Anhui, China（人工智能学院，安徽大学，合肥，安徽，中国） ； Pengcheng Laboratory, Shenzhen, Guangdong, China（鹏城实验室，深圳，广东，中国） 纠错

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

Comments 17 pages, 8 figures

Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling

Jinghan Li, Zhicheng Sun, Yadong Mu

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

Comments ICML 2025

Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning

Ayana Niwa, Masahiro Kaneko, Kentaro Inui

机构 * MBZUAI ； Tohoku University（东北大学） ； RIKEN（日本理化学研究所） 纠错

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

Comments Accepted at ACL2025 Findings (long)

DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation

Zhixuan Liang, Yao Mu, Yixiao Wang, Tianxing Chen, Wenqi Shao, Wei Zhan, Masayoshi Tomizuka, Ping Luo, Mingyu Ding

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

Comments Accepted by CVPR 2025. Camera ready version. Previous DexDiffuser. Project page: https://dexdiffuser.github.io/

Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials

Thorben Prein, Elton Pan, Janik Jehkul, Steffen Weinmann, Elsa A. Olivetti, Jennifer L. M. Rupp

机构 * Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA（材料科学与工程系，麻省理工学院，剑桥，马萨诸塞州，美国） 纠错

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

Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning

Junzhi Chen, Juhao Liang, Benyou Wang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） 纠错

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

Journal ref Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning

Mohammadamin Moradi, Runyu Jiang, Yingzi Liu, Malvern Madondo, Tianming Wu, James J. Sohn, Xiaofeng Yang, Yasmin Hasan, Zhen Tian

机构 * Department of Radiation & Cellular Oncology, University of Chicago（芝加哥大学辐射与细胞肿瘤学系） ； Department of Physics, University of Chicago（芝加哥大学物理系） ； Department of Radiation Oncology, Emory University（埃默里大学放射肿瘤学系） 纠错

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

Comments 12 pages, 2 figures, 3 tables

Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation

Shizhe Chen, Ricardo Garcia, Paul Pacaud, Cordelia Schmid

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

Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning

Ji Young Byun, Young-Jin Park, Navid Azizan, Rama Chellappa

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges

Jintao Liang, Gang Su, Huifeng Lin, You Wu, Rui Zhao, Ziyue Li

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； University of Georgia（佐治亚大学） ； South China University of Technology（华南理工大学） ； Technical University of Munich, University of Cologne（慕尼黑技术大学、科隆大学） ； SenseTime Research（商汤科技研究院） ； Qingyuan Research Institute, Shanghai Jiaotong University（青原研究院，上海交通大学） 纠错

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

Automatic Treatment Planning using Reinforcement Learning for High-dose-rate Prostate Brachytherapy

Tonghe Wang, Yining Feng, Xiaofeng Yang

机构 * Department of Medical Physics, Memorial Sloan Kettering Cancer Center（医学物理系，纪念斯隆-凯特琳癌症中心） ； Department of Radiation Oncology and Winship Cancer Institute, Emory University（放射肿瘤学系和Winship癌症研究所，埃默里大学） ； Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University School of Medicine（Wallace H. Coulter生物医学工程系，佐治亚理工学院和埃默里大学医学院） ； Department of Biomedical Informatics, Emory University（生物医学信息学系，埃默里大学） 纠错

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

BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models

Zhiting Fan, Ruizhe Chen, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室） 纠错

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

Comments ACL 2025 findings

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation

Keyu Zhao, Fengli Xu, Yong Li

机构 * Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学） 纠错

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

Integrating AI Planning Semantics into SysML System Models for Automated PDDL File Generation

Hamied Nabizada, Tom Jeleniewski, Lasse Beers, Maximilian Weigand, Felix Gehlhoff, Alexander Fay

机构 * Institute of Automation Technology（自动化技术研究所） ； Helmut Schmidt University（海姆·施密特大学） ； Ruhr University（鲁尔大学） 纠错

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