arXivDaily arXiv每日学术速递 周一至周五更新

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 11004 信号源:cs.CL, cs.AI, cs.LG

1. 规划推理 11004 篇

2008.03007 2020-09-23 cs.AI 83%

Modelling Multi-Agent Epistemic Planning in ASP

Alessandro Burigana, Francesco Fabiano, Agostino Dovier, Enrico Pontelli

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

Comments Paper presented at the 36th International Conference on Logic Programming (ICLP 2019), University Of Calabria, Rende (CS), Italy, September 2020, 16 pages

Journal ref Theory and Practice of Logic Programming 20 (2020) 593-608

详情

展开后加载摘要…

URL PDF HTML 收藏
1906.06047 2020-06-04 cs.LO cs.AI cs.MA math.LO 83%

Dynamic Term-Modal Logics for First-Order Epistemic Planning

Andrés Occhipinti Liberman, Andreas Achen, Rasmus Kræmmer Rendsvig

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2005.05849 2020-05-13 cs.AI 83%

Argument Schemes for Explainable Planning

Quratul-ain Mahesar, Simon Parsons

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1812.01569 2020-03-06 cs.AI 83%

Nested Reasoning About Autonomous Agents Using Probabilistic Programs

Iris Rubi Seaman, Jan-Willem van de Meent, David Wingate

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1910.02461 2019-10-08 cs.AI cs.RO 83%

Risk-Aware Reasoning for Autonomous Vehicles

Majid Khonji, Jorge Dias, Lakmal Seneviratne

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1909.08259 2019-09-19 cs.AI cs.IT cs.LO cs.MA math.IT 83%

Design of a Solver for Multi-Agent Epistemic Planning

Francesco Fabiano

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

Comments In Proceedings ICLP 2019, arXiv:1909.07646. arXiv admin note: text overlap with arXiv:1511.01960 by other authors

Journal ref EPTCS 306, 2019, pp. 403-412

详情

展开后加载摘要…

URL PDF HTML 收藏
1810.02497 2019-07-24 math.OC cs.AI 83%

Compositional planning in Markov decision processes: Temporal abstraction meets generalized logic composition

Xuan Liu, Jie Fu

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

Comments 8 pages, 4 figures, 2 tables, accepted as a conference paper for presentation at American Control Conference 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
1906.06436 2019-06-18 cs.AI 83%

Towards Empathetic Planning

Maayan Shvo, Sheila A. McIlraith

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1807.06777 2019-05-23 cs.LO cs.AI 83%

Planning and Synthesis Under Assumptions

Benjamin Aminof, Giuseppe De Giacomo, Aniello Murano, Sasha Rubin

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1810.08431 2018-10-22 cs.AI 83%

Assumption-Based Planning

Damien Pellier, Humbert Fiorino

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

Journal ref Proceedings of the International Conference on Advances in Intelligence Systems Theory and Applications (AISTA), 2004, November, pages 367-376, Luxembourg-Kirchberg, Luxembourg

详情

展开后加载摘要…

URL PDF HTML 收藏
1512.07943 2015-12-29 cs.AI 83%

Toward a Research Agenda in Adversarial Reasoning: Computational Approaches to Anticipating the Opponent's Intent and Actions

Alexander Kott, Michael Ownby

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

Comments A version of this paper was presented at the SPIE Symposium on Enabling Technologies for Simulation Science

详情

展开后加载摘要…

URL PDF HTML 收藏
1401.3470 2014-01-16 cs.AI 83%

Message-Based Web Service Composition, Integrity Constraints, and Planning under Uncertainty: A New Connection

Jörg Hoffmann, Piergiorgio Bertoli, Malte Helmert, Marco Pistore

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

Journal ref Journal Of Artificial Intelligence Research, Volume 35, pages 49-117, 2009

详情

展开后加载摘要…

URL PDF HTML 收藏
1302.6801 2013-02-28 cs.AI 83%

A Probabilistic Model of Action for Least-Commitment Planning with Information Gather

Denise L. Draper, Steve Hanks, Daniel Weld

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

Comments Appears in Proceedings of the Tenth Conference on Uncertainty in Artificial Intelligence (UAI1994)

详情

展开后加载摘要…

URL PDF HTML 收藏
1110.1016 2011-10-06 cs.AI 83%

Engineering Benchmarks for Planning: the Domains Used in the Deterministic Part of IPC-4

S. Edelkamp, R. Englert, J. Hoffmann, F. Liporace, S. Thiebaux, S. Trueg

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

Journal ref Journal Of Artificial Intelligence Research, Volume 26, pages 453-541, 2006

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.20164 2026-05-12 cs.LG cs.AI cs.CL 83%

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering

计划是什么?LLMs中隐式规划的度量及其在押韵生成和问答中的应用

Jim Maar, Denis Paperno, Callum Stuart McDougall, Neel Nanda

机构 * HPI / University of Potsdam(HPI/波茨坦大学) Utrecht University(乌特勒支大学) Google DeepMind(谷歌DeepMind)

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

AI总结 本文提出简单方法评估LLM隐式规划,通过押韵生成和问答案例展示其可扩展性,发现隐式规划在1B参数模型中普遍存在,为AI安全提供新视角。

Comments 41 pages, 34 figures, Accepted at ICLR 2026, Code available at https://github.com/Jim-Maar/implicit-planning-in-llms

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.12626 2026-08-14 cs.CL cs.AI cs.MA 新提交 82%

LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning

大型语言模型(LLMs)并非优秀的战略家,然而记忆增强的智能体可提升推理能力

Yi Wu, Zhimin Hu

机构 * University of Chicago(芝加哥大学) University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

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

AI总结 该研究针对LLM在长时环境中战略推理的缺陷,提出EpicStar框架,结合跨回合记忆与动态门控机制,在星际争霸II测试中实现更高胜率且令牌消耗大幅减少。

Journal ref Published at Reasoning and Planning for LLMs at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10117 2026-06-01 cs.LG cs.AI 82%

Biases in the Blind Spot: Detecting What LLMs Fail to Mention

盲点中的偏见:检测大语言模型未能提及的内容

Iván Arcuschin, David Chanin, Adrià Garriga-Alonso, Oana-Maria Camburu

机构 * Poseidon Research(Poseidon研究) University College London, United Kingdom(伦敦大学学院, 英国) Imperial College London, United Kingdom(伦敦帝国学院, 英国)

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

AI总结 提出全自动黑盒流水线,通过统计测试和思维链分析,自动检测大语言模型在任务中未明确表述的偏见。

Comments Published at the 43rd International Conference on Machine Learning (ICML 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18167 2025-10-23 cs.LG cs.AI 82%

Understanding Reasoning in Thinking Language Models via Steering Vectors

Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

机构 * University of Oxford(牛津大学) University of Buenos Aires(布宜诺斯艾利斯大学)

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

Comments Accepted to the Workshop on Reasoning and Planning for Large Language Models at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.16078 2025-04-23 cs.LG cs.AI 82%

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

Thomas Schmied, Jörg Bornschein, Jordi Grau-Moya, Markus Wulfmeier, Razvan Pascanu

机构 * ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz(ELLIS单元、LIT人工智能实验室、机器学习研究所、JKU林茨) Google DeepMind(谷歌DeepMind)

专题命中 规划推理 :reasoning(abstract);chain-of-thought(abstract);CoT(abstract);self-correction(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.16198 2025-02-25 cs.NI cs.AI cs.ET cs.LG 82%

An Autonomous Network Orchestration Framework Integrating Large Language Models with Continual Reinforcement Learning

Masoud Shokrnezhad, Tarik Taleb

专题命中 规划推理 :reasoning(abstract);chain-of-thought(abstract);CoT(abstract);planning(abstract)

Comments IEEE Communications Magazine

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.04467 2024-10-16 cs.AI cs.CL cs.GT 82%

Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games

Nathan Herr, Fernando Acero, Roberta Raileanu, María Pérez-Ortiz, Zhibin Li

专题命中 规划推理 :reasoning(abstract);chain-of-thought(abstract);CoT(abstract);logical reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22983 2026-08-18 cs.RO 版本更新 82%

Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives

基础模型时代中的具身机器人操作:规划与学习视角

Shuanghao Bai, Wenxuan Song, Jiayi Chen, Yuheng Ji, Zhide Zhong, Jin Yang, Han Zhao, Wanqi Zhou, Zhe Li, Pengxiang Ding, Cheng Chi, Chang Xu, Xiaolong Zheng, Donglin Wang, Haoang Li, Shanghang Zhang, Badong Chen

机构 * Xi’an Jiaotong Univeristy(西安交通大学) Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) Chinese Academy of Sciences(中国科学院) Westlake University(西湖大学) Zhejiang University(浙江大学) University of Sydney(悉尼大学) BAAI(百度人工智能研究院) Peking University(北京大学)

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

AI总结 本文探讨了基础模型时代机器人操作的规划与学习方法,分析了高层推理与低层控制的统一框架,并提出了未来研究方向。

Comments This work is a re-architected core derived from the full survey (arXiv:2510.10903), refined to highlight the most central themes and representative studies

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.09333 2026-08-11 cs.RO 新提交 82%

DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving

DH-VLM:面向自动驾驶的双时域协同隐层推理框架

Ziyi Song, Chen Xia, Hang Yu, Sheng Zhou, Zhisheng Niu

机构 * Tsinghua University(清华大学)

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

AI总结 本文提出DH-VLM双时域协同隐层推理框架,结合基础设施与自车实现非对称语义协同,构建协同QA数据集支撑推理,在规划性能、通信成本等指标上优于现有方法,为协同自动驾驶提供实用鲁棒范式。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.03556 2026-08-07 cs.CV cs.RO 版本更新 82%

Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation

Afford-X:面向任务型操作的通用且轻量化的可供性推理模型

Xiaomeng Zhu, Yuyang Li, Leiyao Cui, Pengfei Li, Huan-ang Gao, Yixin Zhu, Hao Zhao

机构 * Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院) Department of Computer Science and Engineering, Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系) Shenyang Institute of Automation, Chinese Academy of Sciences(中国科学院沈阳自动化研究所) Institute for Al Industry Research, Tsinghua University(清华大学人工智能产业研究院) Department of Computer Science, Tsinghua University(清华大学计算机科学系)

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

AI总结 研究人员推出LVIS-Aff数据集,开发了Afford-X可供性推理模型,其性能优于现有非LLM方法和此前会议论文结果,参数紧凑、推理速度快,可部署于本地设备助力机器人任务导向型操作。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03779 2026-08-05 cs.CV 新提交 82%

AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding

AgenticVAU:用于视频异常理解的多智能体探索-验证推理框架

Yuxiang Duan, Huining Li, Ao Li, Shuai Feng, Lanju Kong, Ning Liu, Jian Zhang, Xingdong Sheng, Yuntao Du

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

AI总结 本文提出无需训练的多智能体框架AgenticVAU,通过四个专门智能体协作完成视频异常理解的探索-验证过程,在VAU-Bench数据集上优于零样本推理及强化学习基线方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.01201 2026-08-04 cs.RO cs.CV 新提交 82%

PRISM: Privileged Probabilistic Latent Supervision for End-to-End Autonomous Driving Motion Planning

PRISM:面向端到端自动驾驶运动规划的特权概率潜在监督

Volodymyr Havrylov, Faris Janjoš, Andreas Look, Jürgen Mathes, Andreas Geiger

机构 * University of Tübingen(蒂宾根大学) Bosch Center for Artificial Intelligence(博世人工智能中心) Coburg University(科堡大学) Tübingen AI Center(蒂宾根人工智能中心)

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

AI总结 该研究针对端到端自动驾驶模型梯度微弱问题,提出基于真实值的概率潜在监督框架,在 nuScenes 数据集上实现规划 L2 误差降 8%、碰撞率降 3%,且计算开销可忽略。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.12244 2026-08-04 cs.RO 版本更新 82%

Any House Any Task: Scalable Long-Horizon Planning for Abstract Human Tasks

任何房屋任何任务:为抽象人类任务的可扩展长周期规划

Zhihong Liu, Yang Li, Rengming Huang, Cewu Lu, Panpan Cai

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

AI总结 AHAT是一种优化长周期规划的家庭任务规划器,通过结合LLM和TGPO算法,在复杂家庭任务中实现高效规划。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.10383 2026-07-31 cs.CV 版本更新 82%

Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios

代理视频生成:通过工具约束的LLM规划从文本到可执行事件图

Nicolae Cudlenco, Mihai Masala, Marius Leordeanu

机构 * Institute of Mathematics of the Romanian Academy(罗马尼亚科学院数学研究所) National University of Science and Technology Politehnica Bucharest(布加勒斯特理工大学) Büchi Labortechnik AG(布奇实验室技术股份公司)

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

AI总结 本文提出了一种代理系统,通过LLM生成结构化的事件图规范,并在3D引擎中确定性执行,解决了传统视频生成的语义可靠性问题,展示了在物理真实性和语义对齐上的优越表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.25388 2026-07-29 cs.RO 新提交 82%

SGTP: Sampling-based Game-Theoretic Planning for Real-Time Multi-Vehicle Autonomous Racing

SGTP:基于采样的博弈论实时多车辆自主赛车规划

Zhouheng Li, Fangguo Zhao, Mattia Piccinini, Baha Zarrouki, Yuan Gao, Zitong Shan, Johannes Betz, Chen Lv, Lei Xie

机构 * Zhejiang University(浙江大学) Nanyang Technological University(南洋理工大学) Technical University of Munich(慕尼黑工业大学)

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

AI总结 针对自主多车辆赛车中平衡战略多样性与计算效率的难题,提出基于采样的博弈论规划(SGTP)框架,结合博弈论推理与GPU加速采样,经可行性选择确保安全过渡,模拟显示其在多智能体场景表现良好,还开源代码及基准促进研究。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.21906 2026-07-27 physics.soc-ph 新提交 82%

A Knowledge-Grounded Behavioral Reasoning Framework for Training-Free Urban Healthcare OD Prediction

一种用于无训练城市医疗保健 OD 预测的知识驱动行为推理框架

Linzhen Yang, Xueliang Liu, Chengbo Zhang, Meng Meng

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

AI总结 研究城市医疗保健 OD 预测问题,提出基于知识驱动行为推理的无训练框架,将异构城市信息组织成知识图谱,通过多智能体推理实现预测。实验表明该框架性能优于传统深度学习基线,凸显城市智能在医疗保健出行建模上从数据拟合到知识驱动推理的潜力。

Comments 16 pages, 9 figures. Submitted to the 4th International Conference on Urban Science and Intelligence

详情

展开后加载摘要…

URL PDF HTML 收藏