大模型推理能力

LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory

Jingru Jia, Zehua Yuan, Junhao Pan, Paul E. McNamara, Deming Chen

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments Accepted by NeurIPS 2025

Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code

Augusto B. Corrêa, André G. Pereira, Jendrik Seipp

机构 * University of Oxford（牛津大学） ； Federal University of Rio Grande do Sul（里约格兰德杜斯阿勒斯联邦大学） ； Linköping University（_linköping大学） 纠错

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

Comments Accepted to NeurIPS 2025

Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search

Haoran Sun, Yankai Jiang, Wenjie Lou, Yujie Zhang, Wenjie Li, Lilong Wang, Mianxin Liu, Lei Liu, Xiaosong Wang

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Fudan University（复旦大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning

Guoxin Wang, Jun Zhao, Xinyi Liu, Yanbo Liu, Xuyang Cao, Chao Li, Zhuoyun Liu, Qintian Sun, Fangru Zhou, Haoqiang Xing, Zhenhong Yang

机构 * JDH Algo（京东健康算法） 纠错

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

A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search

Austin R. Ellis-Mohr, Anuj K. Nayak, Lav R. Varshney

机构 * University of Illinois Urbana-Champaign, Urbana, IL, USA（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning

Rebekah A. Gelpí, Eric Xue, William A. Cunningham

机构 * Department of Psychology, University of Toronto（多伦多大学心理学系） ； Vector Institute（向量研究所） ； Schwartz Reisman Institute of Technology & Society, University of Toronto（多伦多大学科技与社会研究所） ； Department of Computer Science, University of Toronto（多伦多大学计算机科学系） 纠错

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

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models

Peijie Liu, Fengli Xu, Yong Li

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

Comments 20 pages, 6 figures, 13 tables(Accept by ICML2025)

Large Language Models for Planning: A Comprehensive and Systematic Survey

Pengfei Cao, Tianyi Men, Wencan Liu, Jingwen Zhang, Xuzhao Li, Xixun Lin, Dianbo Sui, Yanan Cao, Kang Liu, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA, and School of Artificial Intelligence, University of Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室、中国科学院自动化研究所和中国科学院大学人工智能学院） ； Harbin Institute of Technology（哈尔滨工业大学） ； Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Automation, Beijing Institute of Technology（北京理工大学自动化学院） 纠错

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

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Chenwei Lou, Zewei Sun, Xinnian Liang, Meng Qu, Wei Shen, Wenqi Wang, Yuntao Li, Qingping Yang, Shuangzhi Wu

机构 * ByteDance Seed（字节跳动种子） 纠错

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Yansong Ning, Wei Li, Jun Fang, Naiqiang Tan, Hao Liu

机构 * AI Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）人工智能方向） ； Didichuxing Co. Ltd（滴滴出行有限公司） ； CSE, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系） 纠错

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

Comments Under review

SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation

Bin Xu, Yiguan Lin, Yinghao Li, Yang Gao

机构 * School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China（计算机科学与技术学院，北京理工大学，北京） 纠错

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

Comments Accepted by IJCAI2025

Interpreting Emergent Planning in Model-Free Reinforcement Learning

Thomas Bush, Stephen Chung, Usman Anwar, Adrià Garriga-Alonso, David Krueger

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

Comments ICLR 2025 oral

Autonomous Radiotherapy Treatment Planning Using DOLA: A Privacy-Preserving, LLM-Based Optimization Agent

Humza Nusrat, Bing Luo, Ryan Hall, Joshua Kim, Hassan Bagher-Ebadian, Anthony Doemer, Benjamin Movsas, Kundan Thind

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

Comments 19 pages, 5 figures, preprint

Policy Guided Tree Search for Enhanced LLM Reasoning

Yang Li

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

APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents

Jun Yu Chen, Tao Gao

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

Comments 8 pages

StreetviewLLM: Extracting Geographic Information Using a Chain-of-Thought Multimodal Large Language Model

Zongrong Li, Junhao Xu, Siqin Wang, Yifan Wu, Haiyang Li

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

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models

Jiayi Gui, Yiming Liu, Jiale Cheng, Xiaotao Gu, Xiao Liu, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang

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

CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs

Kangsheng Wang, Xiao Zhang, Hao Liu, Songde Han, Huimin Ma, Tianyu Hu

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

LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments

Zixia Jia, Mengmeng Wang, Baichen Tong, Song-Chun Zhu, Zilong Zheng

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

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

Zihao Wang, Anji Liu, Haowei Lin, Jiaqi Li, Xiaojian Ma, Yitao Liang

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

Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models

Daman Arora, Subbarao Kambhampati

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

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

CORE-Acu: 结构化推理轨迹与知识图谱安全验证用于针灸临床决策支持

Liuyi Xu, Yun Guo, Ming Chen, Zihan Dun, Yining Qian, An-Yang Lu, Shuang Li, Lijun Liu

机构 * College of Information Science and Engineering, Northeastern University, Shenyang 110819, China（信息科学与工程学院，东北大学，沈阳110819，中国） ； School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066000, China（信息科学与工程学院，燕山大学，秦皇岛，河北省066000，中国） ； School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China（计算机科学与工程学院，东北大学，沈阳110819，中国） ； School of Artificial Intelligence, Beihang University, Beijing 100000, China（人工智能学院，北航，北京100000，中国） ； Key Laboratory of Bioresource Research and Development of Liaoning Province, Northeastern University, Shenyang 110169, China（辽宁省生物资源研究开发重点实验室，东北大学，沈阳110169，中国） ； College of Life and Health Sciences, Northeastern University, Shenyang 110169, China（生命与健康科学学院，东北大学，沈阳110169，中国） 纠错

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

AI总结 CORE-Acu通过结构化推理轨迹与知识图谱安全验证，提升针灸临床决策支持的可解释性与安全性。

Comments 19 pages, 5 figures, 18 tables. Includes the Acu-Reasoning dataset and TCM knowledge graph schema

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models

Yunxin Li, Zhenyu Liu, Zitao Li, Xuanyu Zhang, Zhenran Xu, Xinyu Chen, Haoyuan Shi, Shenyuan Jiang, Xintong Wang, Jifang Wang, Shouzheng Huang, Xinping Zhao, Borui Jiang, Lanqing Hong, Longyue Wang, Zhuotao Tian, Baoxing Huai, Wenhan Luo, Weihua Luo, Zheng Zhang, Baotian Hu, Min Zhang

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） 纠错

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

Comments v2, 91 Pages, 10 figures; Project: https://github.com/HITsz-TMG/Awesome-Large-Multimodal-Reasoning-Models

Speech World Model: Causal State-Action Planning with Explicit Reasoning for Speech

语音世界模型：基于显式推理的语音因果状态-动作规划

Xuanru Zhou, Jiachen Lian, Henry Hong, Xinyi Yang, Gopala Anumanchipalli

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

AI总结 研究旨在改进语音语言模型推理弱的问题，采用模块化视角和世界模型观点，将语音理解分解为四个模块通过因果图通信，建立认知状态搜索空间，实现显式推理，让语音理解更透明可控。

Comments Accepted to 2026 ICLR

DepsRAG: Towards Agentic Reasoning and Planning for Software Dependency Management

Mohannad Alhanahnah, Yazan Boshmaf

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

ParallelWorld: Test-Time Scaling for Embodied Reasoning

ParallelWorld：具身推理的测试时缩放方法

Min Chen, Shengjun Zhang, Yuxin Li, Zhang Zhang, Xin Fei, Chong Xia, Yueqi Duan

机构 * Tsinghua University（清华大学） ； National University of Singapore（新加坡国立大学） 纠错

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

AI总结 本文针对具身推理现有方法缺乏长程规划的局限，提出ParallelWorld多步测试时缩放框架，通过验证器引导的树搜索实现并行多步轨迹模拟，在ESI-Bench上显著提升了主动感知与推理性能。

Comments Project Page: https://chen-min-22.github.io/ParallelWorld-page/

KGCache: Amortized Subgraph Retrieval for KG Reasoning with LLMs

KGCache：基于大型语言模型的知识图谱推理的摊销子图检索

Uros Stanic, Changcheng Yuan, Sabuj Laskar, Ariful Azad

机构 * Texas A&M University（得克萨斯农工大学） 纠错

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

AI总结 本研究针对KGQA中重复检索知识图谱邻域的问题，提出兼容ToG与RoG范式的KGCache，经在WebQSP和CWQ上评估，可显著加速知识图谱检索。

Comments 11 pages, 5 figures

PACE: Adaptive Budget Allocation for Time-Efficient Embodied Planning

PACE：面向时间高效具身规划的自适应预算分配

Yuchen Huang, Xijiang Ying, Zhenhua Ma, Xiaxiang Yuan, Zhijie Gao, Jiayi Huang, Ruichi Mao, Jiazheng Zhang, Hongsheng Ti, Maotao Tian, Rong Shi, Lu Zhao, Shizhuang Zhang, Zhuo Cui, He Wang, Ling Liu, Wei Zhang

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

AI总结 PACE框架通过交错式思考-执行架构和动态预算分配器，在Robotouille基准测试中较ReAct+Think基线提升规划成功率，同时大幅减少推理时间，实现具身规划的时间效率与质量同步提升。

LLM-Guided Transportation Hub Capacity Planning with Textual Business Inputs

基于文本业务输入的大语言模型引导的交通枢纽容量规划

Xiaoyue Liu, Zheng Dong

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

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

AI总结 研究提出用大语言模型代理依自然语言业务描述迭代提出枢纽容量决策的框架，核心机制是思维链推理协议，经反馈回路验证决策，在实际货运网络中表现优于传统模型。

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents

深度旅行：用于自主旅行规划智能体的端到端智能强化学习框架

Yansong Ning, Rui Liu, Jun Wang, Kai Chen, Wei Li, Jun Fang, Kan Zheng, Naiqiang Tan, Hao Liu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Didichuxing Co. Ltd（滴滴出行有限公司） 纠错

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

AI总结 研究针对旅行规划智能体灵活性和自主性不足问题，提出深度旅行框架，通过构建旅行沙盒、开发分层奖励建模系统及回复增强强化学习方法，使训练后的智能体在行程生成准确率和性能上表现出色。

Comments KDD 2026