大模型推理能力 - arXivDaily 专题

2108.12537 2022-05-27 cs.RO cs.AI 83%

An Anytime Hierarchical Approach for Stochastic Task and Motion Planning

Naman Shah, Siddharth Srivastava

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

2204.00288 2022-04-04 cs.AI 83%

Symbolic Search for Optimal Planning with Expressive Extensions

David Speck

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

Comments PhD thesis, University of Freiburg, Germany, 2022

2201.03647 2022-01-12 cs.AI 83%

CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning

Utkarshani Jaimini, Amit Sheth

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

Journal ref IEEE Internet Computing, 26 (1), Jan-Feb 2022

2101.02648 2021-02-16 cs.AI 83%

Argument Schemes and Dialogue 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

Comments arXiv admin note: text overlap with arXiv:2005.05849

2102.00834 2021-02-02 cs.AI 83%

Counterfactual Planning in AGI Systems

Koen Holtman

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

2009.07517 2021-01-15 cs.RO cs.HC cs.LG cs.SY eess.SY 83%

MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control

Boris Ivanovic, Amine Elhafsi, Guy Rosman, Adrien Gaidon, Marco Pavone

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

Comments 14 pages, 6 figures, 1 table. All code, models, and data can be found at https://github.com/StanfordASL/MATS . Conference on Robot Learning (CoRL) 2020

2003.13924 2020-10-23 cs.CV cs.LG cs.MA cs.RO 83%

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

Jiachen Li, Fan Yang, Masayoshi Tomizuka, Chiho Choi

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

Comments NeurIPS 2020. Website: https://jiachenli94.github.io/publications/Evolvegraph/

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

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

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

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

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

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

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

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

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

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

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

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

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)

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

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

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

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)

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

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)

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

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)

2512.01946 2026-08-25 cs.RO cs.CV 版本更新 82%

Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models

为视觉-语言机器人操控扩展跨环境故障推理数据

Paul Pacaud, Ricardo Garcia, Shizhe Chen, Cordelia Schmid

机构 * Inria, École normale supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所、巴黎高等师范学院、法国国家科学研究中心、巴黎文理研究大学）

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

AI总结本文提出自动框架生成多样化的机器人规划与执行故障数据，构建FailCoT数据集，训练Guardian模型提升故障检测泛化能力。

Comments Code, Data, and Models available at https://www.di.ens.fr/willow/research/guardian/. The paper contains 8 pages, 7 figures, 7 tables

2608.21180 2026-08-24 eess.IV cs.CV 新提交 82%

Toward Vision Language Model-based Assessment of Clinical Quality and Usability of LGE-MR Images for Cardiac Ablation Planning

面向基于视觉语言模型的LGE-MR图像临床质量与可用性评估以用于心脏消融规划

Bipasha Kundu, Abhishek Chaturvedi, Axel W. E. Wismueller, Richard Simon, Cristian A. Linte

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

AI总结本研究提出两阶段VLM框架用于左心房LGE-MRI的临床导向图像质量评估，在60个图像切片-文本对数据集上，InternVL2的标准级准确率最高，DeepSeek实现完美临床可用性一致性。

1. 规划推理 11088 篇

An Anytime Hierarchical Approach for Stochastic Task and Motion Planning

Symbolic Search for Optimal Planning with Expressive Extensions

CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning

Argument Schemes and Dialogue for Explainable Planning

Counterfactual Planning in AGI Systems

MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

Modelling Multi-Agent Epistemic Planning in ASP

Dynamic Term-Modal Logics for First-Order Epistemic Planning

Argument Schemes for Explainable Planning

Nested Reasoning About Autonomous Agents Using Probabilistic Programs

Risk-Aware Reasoning for Autonomous Vehicles

Design of a Solver for Multi-Agent Epistemic Planning

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

Towards Empathetic Planning

Planning and Synthesis Under Assumptions

Assumption-Based Planning

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

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

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

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

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

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

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

Understanding Reasoning in Thinking Language Models via Steering Vectors

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

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

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

Guardian: Detecting Robotic Planning and Execution Errors with Vision-Language Models

Toward Vision Language Model-based Assessment of Clinical Quality and Usability of LGE-MR Images for Cardiac Ablation Planning