AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

共收录 11047 篇信号源：cs.CL, cs.AI, cs.LG

1. 规划推理 11047 篇

1811.07550 2018-11-20 cs.CL cs.AI cs.LG cs.NE 78%

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

Yuexin Wu, Xiujun Li, Jingjing Liu, Jianfeng Gao, Yiming Yang

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

Comments 8 pages, 9 figures, AAAI 2019

1811.02119 2018-11-07 cs.RO 78%

Motion Planning for a UAV with a Straight or Kinked Tether

Xuesu Xiao, Jan Dufek, Mohamed Suhail, Robin Murphy

专题命中规划推理：planning(title,abstract)

Comments 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, Madrid, Spain

1811.00234 2018-11-02 math.OC 78%

Joint Fleet Sizing and Charging System Planning for Autonomous Electric Vehicles

Hongcai Zhang, Colin J. R. Sheppard, Timothy E. Lipman, Scott J. Moura

专题命中规划推理：planning(title,abstract)

1810.00804 2018-10-02 cs.RO 78%

Deep sequential models for sampling-based planning

Yen-Ling Kuo, Andrei Barbu, Boris Katz

专题命中规划推理：planning(title,abstract)

Comments Published in IROS 2018

1806.07324 2018-06-21 cs.RO 78%

Multi-agent Gaussian Process Motion Planning via Probabilistic Inference

Luka Petrović, Ivan Marković, Marija Seder

专题命中规划推理：planning(title,abstract)

Comments Accepted for oral presentation at 12th IFAC Symposium on Robot Control (SYROCO 2018)

1804.07276 2018-04-20 cs.RO 78%

Static and Dynamic Path Planning Using Incremental Heuristic Search

Asem Khattab

专题命中规划推理：planning(title,abstract)

Comments Internship Report

1709.08235 2017-09-26 cs.MA 78%

Dynamic Path Planning and Movement Control in Pedestrian Simulation

Fatema Tuj Johora, Philipp Kraus, Jörg P. Müller

专题命中规划推理：planning(title,abstract)

Comments This paper was accepted for the preproceedings of The 2nd International Workshop on Agent-based modelling of urban systems (ABMUS 2017), http://www.modelling-urban-systems.com/

1709.00546 2017-09-05 cs.RO 78%

Autonomous Waypoint Generation with Safety Guarantees: On-Line Motion Planning in Unknown Environments

Sanjeev Sharma

专题命中规划推理：planning(title,abstract)

Comments This paper was accepted for publication in the International Conference on Advanced Robotics 2013. It was not included in the final proceedings of the conference as I was unable to attend the conference to present the paper

1707.09729 2017-08-01 math.OC 78%

Bilevel Optimization Based Transmission Expansion Planning Considering Phase Shifting Transformer

Xiaohu Zhang, Di Shi, Zhiwei Wang, Zhe Yu, Xinan Wang, Desong Bian, Kevin Tomsovic

专题命中规划推理：planning(title,abstract)

Comments To be published (Accepted) in: Proceedings of the North American Power Symposium, Morgantown, WV, Sep. 17-19,2017

1707.00796 2017-07-05 cs.GT 78%

Efficient sensor network planning method using approximate potential game

Su-Jin Lee, Young-Jin Park, Han-Lim Choi

专题命中规划推理：planning(title,abstract)

Comments 24 pages, 4 figures, submitted to IJDSN(International Journal of Distributed Sensor Networks)

1706.09932 2017-07-05 cs.MA cs.RO 78%

Scalable Asymptotically-Optimal Multi-Robot Motion Planning

Andrew Dobson, Kiril Solovey, Rahul Shome, Dan Halperin, Kostas E. Bekris

专题命中规划推理：planning(title,abstract)

Comments 8 pages, 12 figures, submitted to the first International Symposium on Multi-Robot and Multi-Agent Systems (MRS)

1706.01062 2017-06-06 cs.GT cs.MA cs.SI physics.soc-ph 78%

Planning with Multiple Biases

Jon Kleinberg, Sigal Oren, Manish Raghavan

专题命中规划推理：planning(title,abstract)

1701.04350 2017-01-17 cs.RO 78%

An Object-oriented approach to Robotic planning using Taxi domain

Aasheesh Singh

专题命中规划推理：planning(title,abstract)

Comments Standard 4 page IEEE Format Submitted in IEEE-DTU Technical Journal IOTA

1610.00912 2016-10-05 cs.RO 78%

Decentralized Motion Planning with Collision Avoidance for a Team of UAVs under High Level Goals

Christos K. Verginis, Ziwei Xu, Dimos V. Dimarogonas

专题命中规划推理：planning(title,abstract)

Comments Submitted to the IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017

1511.06127 2015-11-20 physics.soc-ph 78%

Modelling consensus building in Delphi practices for participated transport planning

Michela Le Pira, Giuseppe Inturri, Matteo Ignaccolo, Alessandro Pluchino

专题命中规划推理：planning(title,abstract)

Comments 11 pages, 2 figures, 3 tables

1411.7472 2015-04-03 cs.GT cs.CC cs.DS cs.SI 78%

Computational issues in time-inconsistent planning

Pingzhong Tang, Yifeng Teng, Zihe Wang, Shenke Xiao, Yichong Xu

专题命中规划推理：planning(title,abstract)

Comments 20 pages, 7 figures, submitted to EC'15

1403.4174 2014-03-18 cs.RO 78%

A Receding Horizon Approach to Multi-Agent Planning from Local LTL Specifications

Jana Tumova, Dimos V. Dimarogonas

专题命中规划推理：planning(title,abstract)

Comments Extended version of ACC 2014 paper

2010.01931 2020-10-06 cs.LG cs.AI 77%

Offline Learning for Planning: A Summary

Giorgio Angelotti, Nicolas Drougard, Caroline Ponzoni Carvalho Chanel

专题命中规划推理：planning(title,comments)；分类 cs.AI、cs.LG

Comments 9 pages, ICAPS 2020 Conference - Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) Workshop

2608.02148 2026-08-19 cs.IR cs.CL cs.CV 版本更新 77%

Douyin Multimodal Embedding Model Technical Report

抖音多模态嵌入模型技术报告

Haonan Chen, Chu Li, Zhicheng Wang, Yuanwei Liu, Yuanjiang Wang, Shaohua Jiang, Zhicheng Dou

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

AI总结针对现有多模态嵌入模型难以兼顾效率与细粒度区分的问题，提出分两阶段训练的DME模型，在MMEB-v2数据集及抖音生产场景中均取得优异效果。

Comments Technical Report

2608.09857 2026-08-11 cs.RO cs.AI 新提交 77%

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

智能体 harness：面向机器人自主的大语言模型驱动验证层

Rohan Bhagra, Mahantesh Halapannavar, Uddhav Bhattarai

机构 * Carnegie Mellon University（卡内基梅隆大学）； Pacific Northwest National Laboratory（太平洋西北国家实验室）

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

AI总结针对机器人规划模型的安全与伦理风险，提出LLM驱动的验证层作为中间件管控计划，实现近85%的类别准确率、97%的对抗性攻击遏制率，为机器人自主提供可靠保障。

Comments 7 pages. Not yet finalized for conference submission

2606.11678 2026-07-14 cs.CL 版本更新 77%

Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professional Judgment

AI能像城市规划师一样推理吗？基于专业判断的大语言模型基准测试

Yijie Deng, He Zhu, Wen Wang, Junyou Su, Minxin Chen, Wenjia Zhang

机构 * School of Architecture and Urban Planning, Shenzhen University（深圳大学建筑与城市规划学院）； Shenzhen Key Laboratory of Urban Spatial Information and Intelligent Modeling（深圳市城市空间信息与智能建模重点实验室）； Department of Urban Planning and Design, The University of Hong Kong（香港大学城市规划与设计系）

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

AI总结提出UPBench框架，通过4×5知识支柱与认知水平矩阵评估25个LLM，发现模型在分析任务上优于事实回忆和综合判断，揭示了规划知识的制度依赖性。

Comments This paper has been withdrawn by the authors because the current version requires substantial revision and further validation before it can be considered a reliable representation of the work

2606.24597 2026-06-24 cs.CL 新提交 77%

Qwen-AgentWorld: Language World Models for General Agents

Qwen-AgentWorld: 通用智能体的语言世界模型

Yuxin Zuo, Zikai Xiao, Li Sheng, Fei Huang, Jianhong Tu, Yuxuan Liu, Tianyi Tang, Xiaomeng Hu, Yang Su, Qingfeng Lan, Yantao Liu, Qin Zhu, Yinger Zhang, Bowen Yu, Haiquan Zhao, Haiyang Xu, Jianxin Yang, Jiayang Cheng, Junyang Wang, Lianghao Deng, Mingfeng Xue, Tianyi Bai, Yang Fan, Yubo Ma, Yucheng Li, Zeyu Cui, Zhihai Wang, Zhihui Xie, Zhuorui Ye, An Yang, Dayiheng Liu, Jingren Zhou, Ning Ding

机构 * Qwen Team（Qwen团队）

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

AI总结提出基于语言模型的世界模型Qwen-AgentWorld，通过三阶段训练（CPT、SFT、RL）模拟7个领域的智能体环境，并构建AgentWorldBench基准，实验表明其显著优于现有模型，且能作为环境模拟器和智能体基础模型提升下游性能。

2601.12641 2026-06-17 cs.AI 77%

STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models

STEP-LLM: 通过大型语言模型生成CAD STEP模型

Xiangyu Shi, Junyang Ding, Xu Zhao, Sinong Zhan, Payal Mohapatra, Daniel Quispe, Kojo Welbeck, Jian Cao, Wei Chen, Ping Guo, Qi Zhu

机构 * Northwestern University（西北大学）

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

AI总结本文提出STEP-LLM，通过大型语言模型将自然语言转化为CAD STEP模型，采用图结构预处理和强化学习提升几何精度，验证了LLM驱动的STEP模型生成可行性。

Comments Accepted to the Design, Automation & Test in Europe Conference (DATE) 2026

Journal ref In Proceedings of the 2026 Design, Automation & Test in Europe Conference (DATE 2026), 2026

2603.01131 2026-06-16 cs.MA cs.AI 版本更新 77%

MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

MedCollab：基于IBIS引导的多智能体协作与分层疾病关系链的临床诊断

Yuqi Zhan, Xinyue Wu, Tianyu Lin, Yutong Bao, Xiaoyu Wang, Weihao Cheng, Huangwei Chen, Feiwei Qin, Zhu Zhu

机构 * Princeton University（普林斯顿大学）； Springer Heidelberg（斯普林格海德堡）； ABC Institute（ABC研究所）； Rupert-Karls-University Heidelberg（海德堡鲁珀特-卡尔大学）； Hangzhou Dianzi University（杭州电子科技大学）； Zhejiang University（浙江大学）； Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescents’ Health and Diseases（浙江大学医学院儿童医院，国家儿童青少年健康与疾病临床研究中心）

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

AI总结提出MedCollab框架，通过IBIS结构化论证和分层疾病关系链（HDRC）增强多智能体协作，提升临床诊断的准确性、可追溯性和报告质量。

2606.03005 2026-06-03 cs.CV cs.AI 77%

MUSE: A Unified Agentic Harness for MLLMs

MUSE: 多模态大语言模型的统一智能体框架

Jianglin Lu, Hailing Wang, Xu Ma, Qihua Dong, Mingyuan Zhang, Yizhou Wang, Yun Fu

机构 * Northeastern University（东北大学）

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

AI总结提出MUSE框架，通过可组合模块（任务表示、视觉处理、感知工具、结构化解析、确定性验证和验证器引导修复）提升冻结多模态大语言模型性能，无需重新训练。

2602.02416 2026-06-02 cs.AI 77%

Structure Enables Effective Self-Localization of Errors in LLMs

结构使语言模型能够有效自我定位错误

Ankur Samanta, Akshayaa Magesh, Ayush Jain, Kavosh Asadi, Youliang Yu, Daniel Jiang, Boris Vidolov, Kaveh Hassani, Paul Sajda, Jalaj Bhandari, Yonathan Efroni

机构 * Meta AI ； Columbia University（哥伦比亚大学）； Meta Superintelligence Labs（Meta超智能实验室）； Tel Aviv University（特拉维夫大学）

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

AI总结本文提出结构化推理方法，通过将推理分解为离散语义步骤，使语言模型能更可靠地定位错误，并基于此设计了迭代纠正采样框架Thought-ICS，实现20-40%的自我纠正提升。

2602.22508 2026-05-12 cs.AI 77%

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering

元认知行为调节用于多跳问答的大型语言模型

Ik-hwan Kim, Hyeongrok Han, Mingi Jung, Sangwon Yu, Jinseok Hong, Sang Hun Kim, Yoonyoung Choi, Sungroh Yoon

机构 * Dept. of ECE Seoul Nat’l Univ.（首尔国立大学电子工程系）； AI Center Samsung Elec. Korea（三星电子韩国人工智能中心）； AIIS, ASRI, INMC, ISRC, Interdisc. Prog. in AI Seoul Nat’l Univ.（首尔国立大学人工智能研究所、高级研究机构、人工智能中心、国际研究所以及人工智能跨学科研究计划）

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

AI总结本文提出元认知行为调节（MBT）框架，通过五阶段结构提升多跳问答任务的准确性和效率，减少冗余并保持推理轨迹稳定。

Comments 41 pages

2604.27953 2026-05-01 cs.AI cs.CV 77%

The Effects of Visual Priming on Cooperative Behavior in Vision-Language Models

视觉提示对视觉语言模型合作行为的影响

Kenneth J. K. Ong

机构 * ST Engineering, Singapore（1 ST工程，新加坡）

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

AI总结本文研究了视觉提示如何影响视觉语言模型在囚徒困境中的合作行为，通过图像内容和颜色奖励矩阵实验，发现图像内容和颜色提示对模型决策模式有影响，不同模型的敏感性和缓解效果各异。

2602.13156 2026-04-16 cs.CR cs.AI 77%

In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

上下文自主网络事件响应：一种端到端的大语言模型代理方法

Yiran Gao, Kim Hammar, Tao Li

机构 * Department of Systems Engineering, City University of Hong Kong（香港城市大学系统工程系）； Department of Electrical and Electronic Engineering, University of Melbourne（墨尔本大学电子与电气工程系）

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

AI总结本文提出一种端到端的大语言模型代理方法，通过整合感知、推理、规划和行动功能，实现网络事件响应的自主学习与适应，实验表明其恢复效率比前沿模型快23%。

Comments 2026 AAAI Summer Symposium on Human-Aware AI Agents for the Cyber Battlefield

2604.10734 2026-04-14 cs.CL 77%

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

自校正RAG：通过MMKP上下文选择和NLI引导的MCTS增强忠实性

Shijia Xu, Zhou Wu, Xiaolong Jia, Yu Wang, Kai Liu, April Xiaowen Dong

机构 * Chongqing University（重庆大学）； Queen Mary University of London（伦敦玛丽女王大学）； Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing（重庆市大数据智能与隐私计算重点实验室）； Fangda Partners（方达律师事务所）

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

AI总结本研究提出Self-Correcting RAG框架，通过MMKP上下文选择和NLI引导的MCTS机制，提升复杂推理任务中的准确性和减少幻觉。

↑