大模型推理能力

GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models

GenePlan: 利用大语言模型改进PDDL计划的进化方法

Andrew Murray, Danial Dervovic, Alberto Pozanco, Michael Cashmore

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

AI总结 GenePlan利用大语言模型改进PDDL计划的进化方法，通过优化问题生成高效且低成本的通用计划器，实现了与最先进方法相近的性能。

Comments 54 pages, 4 figures. Accepted to ICAPS 2026

Markovian Transformers for Informative Language Modeling

马尔可夫变换器用于信息语言建模

Scott Viteri, Max Lamparth, Peter Chatain, Clark Barrett

机构 * Department of Computer Science Stanford University（计算机科学系 斯坦福大学） 纠错

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

AI总结 马尔可夫变换器通过引入CoT瓶颈提升语言模型的推理能力，实验显示其在问答任务中表现优异，且对CoT依赖性强。

Comments 21 pages, 6 figures, Accepted at ICLR 2026

Bradley-Terry Policy Optimization for Generative Preference Modeling

基于布雷德利-蒂尔利模型的生成偏好建模政策优化

Shengyu Feng, Yun He, Shuang Ma, Beibin Li, Yuanhao Xiong, Songlin Li, Karishma Mandyam, Julian Katz-Samuels, Shengjie Bi, Licheng Yu, Hejia Zhang, Karthik Abinav Sankararaman, Han Fang, Yiming Yang, Manaal Faruqui

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

AI总结 本文提出布雷德利-蒂尔利政策优化（BTPO），通过引入链式推理改变偏好建模的似然结构，实现对生成偏好模型的有效训练。

Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction

自适应位置层级学习用于长尾移动预测

Yu Wang, Junshu Dai, Yuchen Ying, Hanyang Yuan, Zunlei Feng, Tongya Zheng, Mingli Song

机构 * Zhejiang University（浙江大学） ； Hangzhou City University（杭州市大学） 纠错

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

AI总结 ALOHA通过自适应层级学习缓解长尾移动预测偏差，提升多种模型的预测性能达16.59%。

Comments Accepted by WWW 2026

Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification

逐步简化：引导LLM实现多语言无监督能力控制的句子简化

Jingshen Zhang, Xin Ying Qiu, Lifang Lu, Zhuhua Huang, Yutao Hu, Yuechang Wu, JunYu Lu

机构 * Department of Computer Science, School of Information Science and Technology, Guangdong University of Foreign Studies（计算机科学系，信息科学与技术学院，广东外语外贸大学） ； College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学） ； Lionrock AI Lab, China Merchants Research Institute of Advanced Technology（Lionrock AI实验室，中国远洋科技研究院） 纠错

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

AI总结 本文提出一种多语言无监督句子简化框架，通过分步骤简化提升控制能力，但发现保持语义忠实仍具挑战性。

Comments Accepted to EACL 2026 Findings

Bridging Speech, Emotion, and Motion: a VLM-based Multimodal Edge-deployable Framework for Humanoid Robots

弥合语音、情感与运动：一种基于视觉语言模型的多模态边缘可部署框架用于人形机器人

Songhua Yang, Xuetao Li, Xuanye Fei, Mengde Li, Miao Li

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） 纠错

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

AI总结 本文提出SeM$^2$框架，通过多模态感知、思维链推理和语义序列对齐机制，实现情感一致的多模态交互，提升人形机器人在现实环境中的社交表达能力。

FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation

FutureMind: 通过自适应知识蒸馏为小型语言模型配备战略思维模式先验

Shaoxiong Yang, Junting Li, Mengyuan Zhang, Chao Li, Wei Liu, Jian Luan

机构 * MiLM Plus, Xiaomi Inc.（小米公司） 纠错

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

AI总结 FutureMind通过自适应知识蒸馏为小型语言模型配备战略思维模式先验，提升其在复杂任务中的推理与检索能力。

Comments Accepted by ICLR 2026

AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision Making

AgenticSimLaw: 一个面向可解释高风险表格决策的青少年法庭多智能体辩论模拟

Jon Chun, Kathrine Elkins, Yong Suk Lee

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

AI总结 AgenticSimLaw通过结构化多智能体辩论框架提升高风险表格决策的可解释性和稳定性，适用于需要透明和人类监督的决策任务。

Comments 18 pages, 5 figures

Thinker: A vision-language foundation model for embodied intelligence

Thinker：一个用于具身智能的视觉-语言基础模型

Baiyu Pan, Daqin Luo, Junpeng Yang, Jiyuan Wang, Yixuan Zhang, Hailin Shi, Jichao Jiao

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

AI总结 Thinker通过构建大规模数据集和改进输入方式，在机器人感知与推理任务中实现了最先进的性能。

Comments IROS 2025, 4 pages, 3 figures

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

VIKI-R: 通过强化学习协调具身多智能体合作

Li Kang, Xiufeng Song, Heng Zhou, Yiran Qin, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai, Zhenfei Yin

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

AI总结 VIKI-R通过强化学习协调多智能体合作，提出分层基准VIKI-Bench，显著提升多智能体视觉驱动合作性能。

Comments Accepted by NeurIPS 2025 Track on Datasets and Benchmarks. Project page: https://faceong.github.io/VIKI-R/

KEPT: Knowledge-Enhanced Prediction of Trajectories from Consecutive Driving Frames with Vision-Language Models

KEPT: 基于视觉-语言模型的连续驾驶帧轨迹预测增强方法

Yujin Wang, Tianyi Wang, Quanfeng Liu, Wenxian Fan, Junfeng Jiao, Christian Claudel, Yunbing Yan, Bingzhao Gao, Jianqiang Wang, Hong Chen

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

AI总结 KEPT 通过知识增强的视觉-语言模型，利用时间频率-空间融合编码器和检索增强生成流水线，提升自动驾驶中轨迹预测的准确性和可靠性。

Towards Robust and Fair Next Visit Diagnosis Prediction under Noisy Clinical Notes with Large Language Models

基于大型语言模型的噪声临床笔记下的稳健与公平下次就诊诊断预测

Heejoon Koo

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

AI总结 本文提出基于大型语言模型的稳健与公平下次就诊诊断预测方法，通过标签缩减和分层推理策略提升预测鲁棒性和公平性。

Comments Accepted by the Association for the Advancement of Artificial Intelligence (AAAI) 2026 1st Workshop on Safe, Ethical, Certified, Uncertainty-aware, Robust, and Explainable AI for Health (SECURE-AI4H)

ToC: Tree-of-Claims Search with Multi-Agent Language Models

基于多智能体语言模型的树状主张搜索

Shuyang Yu, Jianan Liang, Hui Hu

机构 * AIGROW 纠错

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

AI总结 ToC通过结合多智能体系统和MCTS，提升专利主张优化的准确性和法律稳健性。

Comments Accepted by AAAI 2026 (Oral)

Talk, Snap, Complain: Validation-Aware Multimodal Expert Framework for Fine-Grained Customer Grievances

Rishu Kumar Singh, Navneet Shreya, Sarmistha Das, Apoorva Singh, Sriparna Saha

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

Comments To be published in the Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026 Special Track on AI for Social Impact )

Addressing the alignment problem in transportation policy making: an LLM approach

Xiaoyu Yan, Tianxing Dai, Yu Marco Nie

机构 * Department of Civil and Environmental Engineering, Northwestern University（土木与环境工程系，西北大学） 纠错

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

Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts

Seungjun Yu, Junsung Park, Youngsun Lim, Hyunjung Shim

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

SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction

Saumya Chaturvedi, Aman Chadha, Laurent Bindschaedler

机构 * Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所） ； AWS GenAI（亚马逊AWS生成式人工智能） 纠错

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

Comments Accepted at NeurIPS 2025, DL4C "Deep Learning for Code" workshop. Code is available at: https://github.com/shollercoaster/SQL-of-Thought

Towards Interactive and Learnable Cooperative Driving Automation: a Large Language Model-Driven Decision-Making Framework

Shiyu Fang, Jiaqi Liu, Mingyu Ding, Yiming Cui, Chen Lv, Peng Hang, Jian Sun

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

TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making

Kechen Jiao, Zhirui Fang, Jiahao Liu, Bei Li, Qifan Wang, Xinyu Liu, Junhao Ruan, Zhongjian Qiao, Yifan Zhu, Yaxin Xu, Jingang Wang, Xiu Li

机构 * Tsinghua University（清华大学） ； Meituan（美团） ； Northeastern University（东北大学） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Meta AI ； Wuhan University（武汉大学） 纠错

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

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS

Alex ZH Dou, Zhongwei Wan, Dongfei Cui, Xin Wang, Jing Xiong, Haokun Lin, Chaofan Tao, Shen Yan, Mi Zhang

机构 * The Ohio State University（俄亥俄州立大学） ； Case Western Reserve University（凯斯西储大学） ； Duke University（杜克大学） ； University of Hong Kong（香港大学） ； City University of Hong Kong（香港城市大学） ； ByteDance（字节跳动） 纠错

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

Comments Technical Report

SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement

Zeyu Lei, Hongyuan Yu, Jinlin Wu, Zhen Chen

机构 * University of Chinese Academy of Sciences Multimedia Department, Xiaomi Inc Chinese Academy of Sciences, Institute of Automation Hong Kong Institute of Science \& Innovation, Chinese Academy of Sciences 纠错

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

Semantic-Geometric-Physical-Driven Robot Manipulation Skill Transfer via Skill Library and Tactile Representation

Mingchao Qi, Yuanjin Li, Xing Liu, Zhengxiong Liu, Panfeng Huang

机构 * Research Center for Intelligent Robotics, School of Astronautics, Northwestern Polytechnical University（智能机器人研究中心，航天学院，西北工业大学） 纠错

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

X-Driver: Explainable Autonomous Driving with Vision-Language Models

Wei Liu, Jiyuan Zhang, Binxiong Zheng, Yufeng Hu, Yingzhan Lin, Zengfeng Zeng

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Baidu Inc.（百度公司） 纠错

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

Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs

Xiang Zhang, Juntai Cao, Jiaqi Wei, Chenyu You, Dujian Ding

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

Comments ACL 2025 main conference

ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning

Ziqiang Xu, Qi Dai, Tian Xie, Yifan Yang, Kai Qiu, DongDong Chen, Zuxuan Wu, Chong Luo

机构 * Fudan University（复旦大学） ； Microsoft（微软公司） 纠错

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

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Yue Cao, Yun Xing, Jie Zhang, Di Lin, Tianwei Zhang, Ivor Tsang, Yang Liu, Qing Guo

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

GPT as a Monte Carlo Language Tree: A Probabilistic Perspective

Kun-Peng Ning, Jia-Yu Yao, Yu-Yang Liu, Mu-Nan Ning, Li Yuan

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

Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination

Qiqi Chen, Xinpeng Wang, Philipp Mondorf, Michael A. Hedderich, Barbara Plank

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

Comments Code: github.com/mainlp/tot-eval

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration

Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua

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

Comments Accepted by EMNLP 2023 Findings

Can Large Language Models Really Improve by Self-critiquing Their Own Plans?

Karthik Valmeekam, Matthew Marquez, Subbarao Kambhampati

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