大模型推理能力

On the Limits of Innate Planning in Large Language Models

大语言模型中内生规划的极限

Charles Schepanowski, Charles Ling

机构 * Western University（温斯洛大学） 纠错

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

AI总结 研究发现大语言模型在无外部工具的情况下，规划和状态推理能力有限，主要问题在于内部状态表示脆弱和启发式规划能力不足。

Comments 33 pages, 7 figures

EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction

EEG-VLM：一种具有多级特征对齐和视觉增强语言引导推理的分层视觉-语言模型，用于基于EEG图像的睡眠阶段预测

Xihe Qiu, Gengchen Ma, Haoyu Wang, Chen Zhan, Xiaoyu Tan, Shuo Li

机构 * School of Electronic and Electrical Engineering, Shanghai University of Engineering Science（上海工程技术大学电子与电气工程学院） ； Department of Control Science and Engineering, College of Electronics and Information Engineering, Tongji University（同济大学电子信息工程学院控制科学与工程系） ； Tencent Youtu Lab（腾讯云视觉实验室） ； Case Western Reserve University（凯斯西储大学） 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 EEG-VLM通过多级特征对齐和视觉增强语言引导推理，提升基于EEG图像的睡眠阶段分类的准确性和可解释性。

R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search

Yibo Wang, Haotian Luo, Huanjin Yao, Tiansheng Huang, Haiying He, Rui Liu, Naiqiang Tan, Jiaxing Huang, Xiaochun Cao, Dacheng Tao, Li Shen

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

Comments Accepted by NeurIPS FoRLM Workshop

Improving Planning with Large Language Models: A Modular Agentic Architecture

Taylor Webb, Shanka Subhra Mondal, Ida Momennejad

机构 * Princeton University（普林斯顿大学） ； Microsoft Research（微软研究院） 纠错

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

Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation

Yu-Hong Shen, Chuan-Yu Wu, Yi-Ru Yang, Yen-Ling Tai, Yi-Ting Chen

机构 * Department of Computer Science, National Yang Ming Chiao Tung University（计算机科学系，阳明交通大学） ； Department of Computer Science and Information Engineering, National Taiwan University（计算机科学与信息工程系，台湾大学） 纠错

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

CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling

Mingyu Chen, Jingkai Lin, Zhaojie Chu, Xiaofen Xing, Yirong Chen, Xiangmin Xu

机构 * School of EE South China University of Technology Guangzhou China（华南理工大学电子工程学院） ； Foshan University Foshan China（佛山大学） 纠错

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

Comments To be published in EMNLP 2025 Findings

ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving

Xueyi Liu, Zuodong Zhong, Yuxin Guo, Yun-Fu Liu, Zhiguo Su, Qichao Zhang, Junli Wang, Yinfeng Gao, Yupeng Zheng, Qiao Lin, Huiyong Chen, Dongbin Zhao

机构 * SKL-MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China（中国科学院自动化研究所SKL-MAIS部门，北京） ； School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学人工智能学院，北京） ； EACON, Fujian, China（福建EACON机构，中国） ； School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China（北京科技大学自动化与电气工程学院） 纠错

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

Comments 18 pages; 9 figures; https://github.com/Liuxueyi/ReasonPlan

How well can LLMs provide planning feedback in grounded environments?

Yuxuan Li, Victor Zhong

机构 * David R. Cheriton School of Computer Science University of Waterloo（大卫·R·切里顿计算机科学学院滑铁卢大学） 纠错

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

HumorPlanSearch: Structured Planning and HuCoT for Contextual AI Humor

Shivam Dubey

机构 * Indian Institute of Technology Madras（印度理工学院马德拉斯分校） 纠错

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

Performance of GPT-5 in Brain Tumor MRI Reasoning

Mojtaba Safari, Shansong Wang, Mingzhe Hu, Zach Eidex, Qiang Li, Xiaofeng Yang

机构 * Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine（放射肿瘤科，Winship癌症研究所，埃默里大学医学院） 纠错

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

From Reasoning to Super-Intelligence: A Search-Theoretic Perspective

Shai Shalev-Shwartz, Amnon Shashua

机构 * AA-I, July 2025（AA-I） 纠错

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

STAIR: Improving Safety Alignment with Introspective Reasoning

Yichi Zhang, Siyuan Zhang, Yao Huang, Zeyu Xia, Zhengwei Fang, Xiao Yang, Ranjie Duan, Dong Yan, Yinpeng Dong, Jun Zhu

机构 * Tsinghua University（清华大学） ； Beihang University（北航） ； Alibaba Group（阿里巴巴集团） 纠错

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

Comments 22 pages, 8 figures, ICML2025 Oral

HMVLM: Multistage Reasoning-Enhanced Vision-Language Model for Long-Tailed Driving Scenarios

Daming Wang, Yuhao Song, Zijian He, Kangliang Chen, Xing Pan, Lu Deng, Weihao Gu

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

Comments WOD Vision-based End-to-End Driving Challenge

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

Wenqi Zhang, Mengna Wang, Gangao Liu, Xu Huixin, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Weiming Lu, Peng Li, Yueting Zhuang

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； Alibaba Group（阿里巴巴集团） ； DAMO Academy, Alibaba Group（阿里巴巴集团大模型学院） ； Nanjing Institute of Software Technology（南京软件技术研究所） ； Nanjing University of Posts and Telecommunications（南京邮电大学） ； Hohai University（河海大学） 纠错

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

Comments Code: https://github.com/zwq2018/embodied_reasoner Dataset: https://huggingface.co/datasets/zwq2018/embodied_reasoner

Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models

Thilo Hagendorff, Sarah Fabi

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

Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integration

Kostas Hatalis, Despina Christou, Vyshnavi Kondapalli

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

Self-Corrective Task Planning by Inverse Prompting with Large Language Models

Jiho Lee, Hayun Lee, Jonghyeon Kim, Kyungjae Lee, Eunwoo Kim

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

Comments 7 pages, 5 figures, IEEE International Conference on Robotics and Automation (ICRA) 2025

Random Forest-of-Thoughts: Uncertainty-aware Reasoning for Computational Social Science

Xiaohua Wu, Xiaohui Tao, Wenjie Wu, Yuefeng Li, Lin Li

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

Comments 11 pages

Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs

Ziyi Tang, Ruilin Wang, Weixing Chen, Yongsen Zheng, Zechuan Chen, Yang Liu, Keze Wang, Tianshui Chen, Liang Lin

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

Comments 12 pages, 9 figures. 3 tables

SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding

Zhenglin Wang, Jialong Wu, Yilong Lai, Congzhi Zhang, Deyu Zhou

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

Comments Accepted by COLING2025

Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang, Tianqi Shi, Chenyang Lyu, Longyue Wang, Weihua Luo, Kaifu Zhang

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

Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models

Sadegh Mahdavi, Raquel Aoki, Keyi Tang, Yanshuai Cao

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

Comments Neurips 2024

A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

Siwei Wu, Zhongyuan Peng, Xinrun Du, Tuney Zheng, Minghao Liu, Jialong Wu, Jiachen Ma, Yizhi Li, Jian Yang, Wangchunshu Zhou, Qunshu Lin, Junbo Zhao, Zhaoxiang Zhang, Wenhao Huang, Ge Zhang, Chenghua Lin, J. H. Liu

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

Integrating Large Language Models and Reinforcement Learning for Non-Linear Reasoning

Yoav Alon, Cristina David

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

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

Cheng Qian, Chi Han, Yi R. Fung, Yujia Qin, Zhiyuan Liu, Heng Ji

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

Comments Findings of EMNLP 2023

Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks

Lingfeng Sun, Devesh K. Jha, Chiori Hori, Siddarth Jain, Radu Corcodel, Xinghao Zhu, Masayoshi Tomizuka, Diego Romeres

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

Comments 22 pages, 4 figures

AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation

AdaptAgent：一种用于代码适配的多智能体、领域引导推理框架

Xiaokai Rong, Hridya Dhulipala, Aashish Yadavally, Tien N. Nguyen

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

AI总结 本研究提出AdaptAgent框架，通过分工的多智能体实现代码适配，在真实数据集上的语义正确性优于强基线，各智能体对适配效果均有重要作用。

OTAP: Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories

Otap：用于评估智能体轨迹中规划与执行的结构感知最优传输

Babak Barazandeh, Subhabrata Majumdar, George Michailidis

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

AI总结 研究智能体轨迹评估问题，将其重新定义为执行图与有效解决方案图的距离，通过不平衡融合Gromov-Wasserstein传输问题实例化得到\otap{}分数，该分数可区分有效与无效轨迹，对保持依赖的重新排序不变且对冗余步骤有界敏感。

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

多轮长期规划的物理学：通过单教师和多教师策略蒸馏从预训练到训练后

Tianyi Men, Zhuoran Jin, Kang Liu, Jun Zhao

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

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

AI总结 研究多轮长期规划问题，通过引入统一可控环境，利用预训练、GRPO、OPD及MOPD等方法，研究规划能力在不同阶段的获取、塑造与整合，展示了多教师策略蒸馏对跨环境能力整合的作用。

RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning

RetroAgent：利用大语言模型在结构化记忆中进行搜索以实现智能逆合成规划

Yanqiao Zhu, Jingru Gan, Xiaoqi Sun, Fang Sun, Yidan Shi, Md Mofijul Islam, Chao Shang, Wenhao Gao, Connor W. Coley, Yizhou Sun, Wei Wang

机构 * UCLA（加利福尼亚大学洛杉矶分校） ； MIT（麻省理工学院） ； Amazon（亚马逊公司） ； UPenn（宾夕法尼亚大学） 纠错

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

AI总结 研究多步逆合成规划难题，提出RetroAgent智能体，通过结合结构化记忆桥接符号搜索与神经推理，利用记忆和化学工具观察搜索状态，实验证明其在分布内和分布外基准测试中性能强且泛化能力好。

Comments To appear at COLM 2026