大模型推理能力 - arXivDaily 专题

2502.20422 2025-03-03 cs.CL cs.AI 73%

SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models

Zicheng Cai, Yaohua Tang, Yutao Lai, Hua Wang, Zhi Chen, Hao Chen

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

2501.02486 2025-02-26 cs.AI cs.CL 73%

LLMPC: Large Language Model Predictive Control

Gabriel Maher

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

2311.09682 2025-02-25 cs.CL cs.AI 73%

MacGyver: Are Large Language Models Creative Problem Solvers?

Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas L. Griffiths, Faeze Brahman

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

Comments NAACL 2024

2502.13475 2025-02-24 cs.CL cs.AI 73%

LLM should think and action as a human

Haun Leung, ZiNan Wang

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

Comments 12 pages, 4 figures, 1 table

2407.11686 2025-02-18 cs.CL cs.AI 73%

CCoE: A Compact and Efficient LLM Framework with Multi-Expert Collaboration for Resource-Limited Settings

Shaomang Huang, Jianfeng Pan, Min Peng, Hanzhong Zheng

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

2502.10732 2025-02-18 cs.LG cs.AI 73%

Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents

Mauricio Tec, Guojun Xiong, Haichuan Wang, Francesca Dominici, Milind Tambe

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

2403.16527 2025-02-12 cs.AI cs.CL cs.RO 73%

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art

Neeloy Chakraborty, Melkior Ornik, Katherine Driggs-Campbell

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

Comments Accepted to ACM Computing Surveys; 55 pages, 5 tables, 3 figures

2502.04392 2025-02-10 cs.CL cs.AI 73%

Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents

Chenyang Shao, Xinyuan Hu, Yutang Lin, Fengli Xu

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

2501.13545 2025-01-24 cs.CL cs.AI 73%

LLMs Can Plan Only If We Tell Them

Bilgehan Sel, Ruoxi Jia, Ming Jin

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

Comments ICLR 2025

2501.06189 2025-01-14 cs.AI cs.CL 73%

A Multimodal Social Agent

Athina Bikaki, Ioannis A. Kakadiaris

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

Comments 9 pages

2406.19643 2025-01-06 cs.CL cs.AI 73%

Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation

Zhe Hu, Hou Pong Chan, Jing Li, Yu Yin

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

Comments Accepted at COLING 2025

2402.10980 2024-12-10 physics.chem-ph cs.AI cs.CE cs.LG 73%

ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback

Henry W. Sprueill, Carl Edwards, Khushbu Agarwal, Mariefel V. Olarte, Udishnu Sanyal, Conrad Johnston, Hongbin Liu, Heng Ji, Sutanay Choudhury

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

Comments 9 pages, accepted by ICML 2024, final version

2403.05468 2024-11-19 cs.CL cs.AI cs.CV 73%

Will GPT-4 Run DOOM?

Adrian de Wynter

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

Journal ref IEEE Transactions on Games (2024)

2411.07760 2024-11-13 cs.LG cs.AI cs.RO 73%

Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning

Alexi Canesse, Mathieu Petitbois, Ludovic Denoyer, Sylvain Lamprier, Rémy Portelas

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

Comments Under review. Code will be released upon acceptance

2303.12153 2024-11-01 cs.RO cs.AI cs.LG 73%

Text2Motion: From Natural Language Instructions to Feasible Plans

Kevin Lin, Christopher Agia, Toki Migimatsu, Marco Pavone, Jeannette Bohg

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

Comments Published in Autonomous Robots, Special Issue: Large Language Models in Robotics 2023. Project page: https://sites.google.com/stanford.edu/text2motion. First two authors contributed equally

2410.19923 2024-10-29 cs.AI cs.LG stat.ME 73%

Language Agents Meet Causality -- Bridging LLMs and Causal World Models

John Gkountouras, Matthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov

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

Comments Project page: https://j0hngou.github.io/LLMCWM/

2407.09985 2024-10-25 cs.AI cs.LG 73%

A Training Data Recipe to Accelerate A* Search with Language Models

Devaansh Gupta, Boyang Li

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

Comments Accepted to Findings of EMNLP, 2024

2310.08588 2024-10-22 cs.CV cs.AI cs.LG cs.RO 73%

Octopus: Embodied Vision-Language Programmer from Environmental Feedback

Jingkang Yang, Yuhao Dong, Shuai Liu, Bo Li, Ziyue Wang, Chencheng Jiang, Haoran Tan, Jiamu Kang, Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu

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

Comments Project Page: https://choiszt.github.io/Octopus/, Codebase: https://github.com/dongyh20/Octopus

2410.14198 2024-10-21 cs.CL cs.AI 73%

Supervised Chain of Thought

Xiang Zhang, Dujian Ding

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

2410.08164 2024-10-11 cs.AI cs.CL cs.CV 73%

Agent S: An Open Agentic Framework that Uses Computers Like a Human

Saaket Agashe, Jiuzhou Han, Shuyu Gan, Jiachen Yang, Ang Li, Xin Eric Wang

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

Comments 23 pages, 16 figures, 9 tables

2303.03548 2024-10-03 cs.RO cs.CL cs.HC cs.LG 73%

Large Language Models as Zero-Shot Human Models for Human-Robot Interaction

Bowen Zhang, Harold Soh

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

Comments 8 pages

2409.20502 2024-10-01 cs.LG cs.AI cs.CV cs.GR 73%

COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models

Divyanshu Daiya, Damon Conover, Aniket Bera

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

Comments 9 pages, 6 figures

2409.20010 2024-10-01 cs.AI cs.CL 73%

Customized Information and Domain-centric Knowledge Graph Construction with Large Language Models

Frank Wawrzik, Matthias Plaue, Savan Vekariya, Christoph Grimm

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

Comments Presented at CAIPI Workshop at AAAI 2024

2409.01326 2024-09-04 cs.RO cs.AI cs.LG 73%

Grounding Language Models in Autonomous Loco-manipulation Tasks

Jin Wang, Nikos Tsagarakis

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

Comments Summit to ICRA@40. arXiv admin note: substantial text overlap with arXiv:2406.14655

2408.09176 2024-08-20 cs.AI cs.CL cs.SC 73%

Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making

Siyu Wu, Alessandro Oltramari, Jonathan Francis, C. Lee Giles, Frank E. Ritter

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

Comments 20 pages, 8 figures, 2 tables

2408.06318 2024-08-13 cs.AI cs.LG 73%

Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example

Yanan Chen, Ali Pesaranghader, Tanmana Sadhu, Dong Hoon Yi

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

Comments 13 pages, 2 figures, 4 tables

2408.01423 2024-08-05 cs.CL cs.AI 73%

Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting

Xiangyu Zhao, Chengqian Ma

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

Comments 8 pages,4 figures

2407.10311 2024-07-16 cs.AI cs.CL cs.CV 73%

Sora and V-JEPA Have Not Learned The Complete Real World Model -- A Philosophical Analysis of Video AIs Through the Theory of Productive Imagination

Jianqiu Zhang

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

Comments 30 pages, 9 figures

2309.17382 2024-07-02 cs.AI cs.LG 73%

Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency

Zhihan Liu, Hao Hu, Shenao Zhang, Hongyi Guo, Shuqi Ke, Boyi Liu, Zhaoran Wang

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

Comments Accepted by International Conference on Machine Learning (ICML) 2024

2407.00118 2024-07-02 cs.LG cs.AI 73%

From Efficient Multimodal Models to World Models: A Survey

Xinji Mai, Zeng Tao, Junxiong Lin, Haoran Wang, Yang Chang, Yanlan Kang, Yan Wang, Wenqiang Zhang

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

1. 规划推理 11047 篇

SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models

LLMPC: Large Language Model Predictive Control

MacGyver: Are Large Language Models Creative Problem Solvers?

LLM should think and action as a human

CCoE: A Compact and Efficient LLM Framework with Multi-Expert Collaboration for Resource-Limited Settings

Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art

Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents

LLMs Can Plan Only If We Tell Them

A Multimodal Social Agent

Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation

ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback

Will GPT-4 Run DOOM?

Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning

Text2Motion: From Natural Language Instructions to Feasible Plans

Language Agents Meet Causality -- Bridging LLMs and Causal World Models

A Training Data Recipe to Accelerate A* Search with Language Models

Octopus: Embodied Vision-Language Programmer from Environmental Feedback

Supervised Chain of Thought

Agent S: An Open Agentic Framework that Uses Computers Like a Human

Large Language Models as Zero-Shot Human Models for Human-Robot Interaction

COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models

Customized Information and Domain-centric Knowledge Graph Construction with Large Language Models

Grounding Language Models in Autonomous Loco-manipulation Tasks

Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making

Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example

Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting

Sora and V-JEPA Have Not Learned The Complete Real World Model -- A Philosophical Analysis of Video AIs Through the Theory of Productive Imagination

Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency

From Efficient Multimodal Models to World Models: A Survey