大模型推理能力 - arXivDaily 专题

2310.10103 2023-10-17 cs.RO cs.AI cs.CL cs.LG 82%

Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning

Dhruv Shah, Michael Equi, Blazej Osinski, Fei Xia, Brian Ichter, Sergey Levine

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

Comments Videos, code, and an interactive Colab notebook that runs in your browser https://sites.google.com/view/lfg-nav/

2305.16646 2023-10-10 cs.CL cs.AI cs.LG 82%

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Xiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou, James Y. Zhang, Jun Zhou, Chenhao Tan, Hongyuan Mei

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

Comments NeurIPS 2023 camera-ready

2309.15129 2023-09-28 cs.AI cs.CL cs.LG 82%

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

Ida Momennejad, Hosein Hasanbeig, Felipe Vieira, Hiteshi Sharma, Robert Osazuwa Ness, Nebojsa Jojic, Hamid Palangi, Jonathan Larson

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

2212.04088 2023-09-08 cs.AI cs.CL cs.CV cs.LG cs.RO 82%

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M. Sadler, Wei-Lun Chao, Yu Su

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

Comments 14 pages, 5 figures

2209.00465 2023-07-18 cs.AI cs.CL cs.LG cs.RO 82%

On Grounded Planning for Embodied Tasks with Language Models

Bill Yuchen Lin, Chengsong Huang, Qian Liu, Wenda Gu, Sam Sommerer, Xiang Ren

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

Comments Accepted to AAAI 2023 Project website: https://yuchenlin.xyz/g-planet/

2305.16653 2023-06-01 cs.CL cs.AI cs.LG 82%

AdaPlanner: Adaptive Planning from Feedback with Language Models

Haotian Sun, Yuchen Zhuang, Lingkai Kong, Bo Dai, Chao Zhang

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

2304.02251 2023-04-06 cs.RO 82%

ERRA: An Embodied Representation and Reasoning Architecture for Long-horizon Language-conditioned Manipulation Tasks

Chao Zhao, Shuai Yuan, Chunli Jiang, Junhao Cai, Hongyu Yu, Michael Yu Wang, Qifeng Chen

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

Comments Accepted to IEEE Robotics and Automation Letters (RA-L)

2303.05510 2023-03-10 cs.LG cs.AI cs.CL cs.PL 82%

Planning with Large Language Models for Code Generation

Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B. Tenenbaum, Chuang Gan

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

Comments ICLR 2023. Project page:https://codeaimcts.github.io

2206.02928 2023-02-17 cs.CL cs.AI cs.LG 82%

Neuro-Symbolic Procedural Planning with Commonsense Prompting

Yujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, William Yang Wang

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

Comments ICLR 2023 Spotlight

2302.00763 2023-02-03 cs.LG cs.AI cs.CL 82%

Collaborating with language models for embodied reasoning

Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, Arun Ahuja, Sheila Babayan, Felix Hill, Rob Fergus

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

Comments Presented at NeurIPS 2022 Language and Reinforcement Learning Workshop (best paper) and NeurIPS 2022 Foundation Models for Decision Making Workshop. 4 pages main; 14 pages total (including references and appendix); 3 figures

2204.00598 2022-05-30 cs.CV cs.AI cs.CL cs.LG 82%

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Andy Zeng, Maria Attarian, Brian Ichter, Krzysztof Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, Pete Florence

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

Comments https://socraticmodels.github.io/

2106.13948 2022-05-26 cs.LG cs.AI cs.CL cs.CV cs.RO 82%

Core Challenges in Embodied Vision-Language Planning

Jonathan Francis, Nariaki Kitamura, Felix Labelle, Xiaopeng Lu, Ingrid Navarro, Jean Oh

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

Comments Journal of Artificial Intelligence Research 74 (2022) 459-515

2202.07349 2022-02-16 cs.HC 82%

IF-City: Intelligible Fair City Planning to Measure, Explain and Mitigate Inequality

Yan Lyu, Hangxin Lu, Min Kyung Lee, Gerhard Schmitt, Brian Y. Lim

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

Comments 18 pages including references and bios, 11 figures, submitted to IEEE Transactions on Visualization and Computer Graphics

2110.12003 2021-10-26 q-fin.ST cs.AI cs.CL cs.LG 82%

Embracing advanced AI/ML to help investors achieve success: Vanguard Reinforcement Learning for Financial Goal Planning

Shareefuddin Mohammed, Rusty Bealer, Jason Cohen

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

2011.00621 2020-11-03 cs.RO 82%

Semantic Task Planning for Service Robots in Open World

Guowei Cui, Wei Shuai, Xiaoping Chen

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

2005.03342 2020-05-08 cs.RO 82%

Arranging Test Tubes in Racks Using Combined Task and Motion Planning

Weiwei Wan, Takeyuki Kotaka, Kensuke Harada

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

2003.14368 2020-04-01 cs.RO 82%

Enabling Topological Planning with Monocular Vision

Gregory J. Stein, Christopher Bradley, Victoria Preston, Nicholas Roy

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

Comments 7 pages (6 for content + 1 for references), 5 figures. Accepted to the 2020 IEEE International Conference on Robotics and Automation

1911.08642 2019-11-21 cs.MA 82%

Scalable Decision-Theoretic Planning in Open and Typed Multiagent Systems

Adam Eck, Maulik Shah, Prashant Doshi, Leen-Kiat Soh

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

Comments Pre-print with appendices for AAAI 2020

1909.00230 2019-09-15 cs.AI cs.CL cs.LG 82%

Collaborative Policy Learning for Open Knowledge Graph Reasoning

Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, Xiang Ren

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

1905.09434 2019-07-03 cs.CG cs.RO 82%

Automated Process Planning for Turning: A Feature-Free Approach

Morad Behandish, Saigopal Nelaturi, Chaman Singh Verma, Mats Allard

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

Comments A shorter version of the paper was presented at the International Conference on Manufacturing Research (ICMR'2018), Skövde, Sweden

Journal ref Journal of Production and Manufacturing Research, 2019

1903.03823 2019-03-12 cs.RO 82%

Locomotion Planning through a Hybrid Bayesian Trajectory Optimization

Tim Seyde, Jan Carius, Ruben Grandia, Farbod Farshidian, Marco Hutter

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

Comments Accepted for publication at the IEEE International Conference on Robotics and Automation (ICRA) 2019

1808.10568 2018-09-13 cs.AI cs.CL cs.LG 82%

Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Xi Victoria Lin, Richard Socher, Caiming Xiong

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

Comments Accepted to EMNLP 2018, 12 pages

1808.09442 2018-09-07 cs.CL cs.AI cs.LG 82%

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen

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

Comments 11 pages, 10 figures, EMNLP 2018 long paper

1801.06176 2018-05-24 cs.CL cs.AI cs.LG cs.NE 82%

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su

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

Comments 11 pages, 8 figures, Accepted in ACL 2018

1709.00155 2017-09-04 cs.CL cs.AI cs.IR cs.LG 82%

Order-Planning Neural Text Generation From Structured Data

Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui

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

1603.08177 2016-03-29 cs.GT cs.MA cs.SI physics.soc-ph 82%

Planning Problems for Sophisticated Agents with Present Bias

Jon Kleinberg, Sigal Oren, Manish Raghavan

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

2606.09027 2026-06-09 cs.CL cs.AI 新提交 82%

SafeRun: Enabling Determinism in LLM Planning for Running

SafeRun：在跑步规划中实现LLM的确定性

Meilin Chen, Zepeng Zhai, Jiaxuan Zhao, Yuan Lu

机构 * University of California, Berkeley（加州大学伯克利分校）； Stanford University（斯坦福大学）

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

AI总结针对LLM在跑步规划中因概率性导致安全违规的问题，提出SafeRun框架，通过解耦架构将LLM的软解释与确定性求解器的硬约束分离，实现100%安全评分。

Comments Workshop on Planning in the Era of LLMs (LM4Plan) at ICML 2026

2511.05540 2026-04-22 cs.RO cs.AI cs.CV cs.LG cs.NE 82%

Constructing the Umwelt: Cognitive Planning through Belief-Intent Co-Evolution

构建环境：通过信念-意图共演的认知规划

Shiyao Sang

机构 * Shiyao Sang（桑世尧）

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

AI总结本文提出基于信念-意图共演的认知规划方法，通过MBCWM和TIWM模型实现环境与现实的认知一致性，提升自动驾驶规划性能并展现类人认知行为。

Comments 12 pages, 8 figures. A paradigm shift from reconstructing the world to understanding it: planning through Belief-Intent Co-Evolution

2601.06102 2026-01-13 cs.AI cs.LG 82%

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems

动态智能上限：测量人工智能系统长期规划和创造力的长期限制

Truong Xuan Khanh, Truong Quynh Hoa

机构 * H&K Research Studio, Clevix LLC（Clevix LLC 研究室）

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

AI总结本文提出动态智能上限概念，通过轨迹导向评估框架量化人工智能系统长期规划与创造力的限制，揭示智能上限的动态性与轨迹依赖性。

Comments This paper introduces a trajectory-centric evaluation framework for analyzing long-horizon intelligence limits in artificial systems, focusing on developmental behavior, planning, and structural creativity rather than proposing new learning algorithms. 11 pages, 2 figures

2511.08595 2025-12-09 cs.CL cs.AI 82%

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning

砍树：基于语义相似性的动态剪枝用于树状思维推理

Joongho Kim, Xirui Huang, Zarreen Reza, Gabriel Grand

机构 * Massachusetts Institute of Technology (MIT)（麻省理工学院）

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

AI总结 SSDP通过动态剪枝技术提升树状思维推理效率，实现2.3倍速度提升且保持高准确性。

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop on Efficient Reasoning

1. 规划推理 11120 篇

Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

On Grounded Planning for Embodied Tasks with Language Models

AdaPlanner: Adaptive Planning from Feedback with Language Models

ERRA: An Embodied Representation and Reasoning Architecture for Long-horizon Language-conditioned Manipulation Tasks

Planning with Large Language Models for Code Generation

Neuro-Symbolic Procedural Planning with Commonsense Prompting

Collaborating with language models for embodied reasoning

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Core Challenges in Embodied Vision-Language Planning

IF-City: Intelligible Fair City Planning to Measure, Explain and Mitigate Inequality

Embracing advanced AI/ML to help investors achieve success: Vanguard Reinforcement Learning for Financial Goal Planning

Semantic Task Planning for Service Robots in Open World

Arranging Test Tubes in Racks Using Combined Task and Motion Planning

Enabling Topological Planning with Monocular Vision

Scalable Decision-Theoretic Planning in Open and Typed Multiagent Systems

Collaborative Policy Learning for Open Knowledge Graph Reasoning

Automated Process Planning for Turning: A Feature-Free Approach

Locomotion Planning through a Hybrid Bayesian Trajectory Optimization

Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

Order-Planning Neural Text Generation From Structured Data

Planning Problems for Sophisticated Agents with Present Bias

SafeRun: Enabling Determinism in LLM Planning for Running

Constructing the Umwelt: Cognitive Planning through Belief-Intent Co-Evolution

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning