AI Agent - arXivDaily 专题

2410.06108 2024-10-10 cs.AI 83%

ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution

Corban Rivera, Grayson Byrd, William Paul, Tyler Feldman, Meghan Booker, Emma Holmes, David Handelman, Bethany Kemp, Andrew Badger, Aurora Schmidt, Krishna Murthy Jatavallabhula, Celso M de Melo, Lalithkumar Seenivasan, Mathias Unberath, Rama Chellappa

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2311.01530 2024-10-08 cs.RO cs.AI 83%

NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors

Shuo Cheng, Caelan Garrett, Ajay Mandlekar, Danfei Xu

专题命中规划决策：planning(title,abstract)；tool-use(abstract)；分类 cs.AI

2409.19226 2024-10-01 cs.RO cs.AI 83%

Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning

Alicia Li, Nishanth Kumar, Tomás Lozano-Pérez, Leslie Kaelbling

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2409.16830 2024-09-26 cs.RO cs.AI 83%

OffRIPP: Offline RL-based Informative Path Planning

Srikar Babu Gadipudi, Srujan Deolasee, Siva Kailas, Wenhao Luo, Katia Sycara, Woojun Kim

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 7 pages, 6 figures, submitted to ICRA 2025

2409.13754 2024-09-24 cs.AI cs.MA cs.RO 83%

Increasing the Value of Information During Planning in Uncertain Environments

Gaurab Pokharel

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments Honors thesis submitted to Computer Science Department at Oberlin College. https://digitalcommons.oberlin.edu/honors/833/

2409.12411 2024-09-20 cs.CL 83%

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation

Chen Liang, Zhifan Feng, Zihe Liu, Wenbin Jiang, Jinan Xu, Yufeng Chen, Yong Wang

专题命中规划决策：agent(title,abstract)；autonomous agent(abstract)；分类 cs.CL

2402.10778 2024-09-17 cs.RO cs.AI 83%

AutoGPT+P: Affordance-based Task Planning with Large Language Models

Timo Birr, Christoph Pohl, Abdelrahman Younes, Tamim Asfour

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 13 pages, 18 pages including references and appendix, 5 figures

2209.01535 2024-09-13 cs.AI cs.CY cs.MA 83%

Simulation-Assisted Optimization for Large-Scale Evacuation Planning with Congestion-Dependent Delays

Kazi Ashik Islam, Da Qi Chen, Madhav Marathe, Henning Mortveit, Samarth Swarup, Anil Vullikanti

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2309.17277 2024-09-04 cs.AI 83%

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

Jiaxian Guo, Bo Yang, Paul Yoo, Bill Yuchen Lin, Yusuke Iwasawa, Yutaka Matsuo

专题命中规划决策：agent(title,abstract)；planning(abstract)；分类 cs.AI

2307.16769 2024-08-22 eess.SY cs.AI cs.SY 83%

2-Level Reinforcement Learning for Ships on Inland Waterways: Path Planning and Following

Martin Waltz, Niklas Paulig, Ostap Okhrin

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2307.16062 2024-08-20 cs.RO cs.LG 83%

Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning

Zengjie Zhang, Jayden Hong, Amir Soufi Enayati, Homayoun Najjaran

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

2407.19667 2024-07-30 cs.AI 83%

Smart Language Agents in Real-World Planning

Annabelle Miin, Timothy Wei

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 5 pages, 1 figure

2404.02831 2024-07-26 cs.AI 83%

Empowering Biomedical Discovery with AI Agents

Shanghua Gao, Ada Fang, Yepeng Huang, Valentina Giunchiglia, Ayush Noori, Jonathan Richard Schwarz, Yasha Ektefaie, Jovana Kondic, Marinka Zitnik

专题命中规划决策：AI agent(title,abstract)；planning(abstract)；分类 cs.AI

2407.16533 2024-07-24 cs.AI cs.RO 83%

HAPFI: History-Aware Planning based on Fused Information

Sujin Jeon, Suyeon Shin, Byoung-Tak Zhang

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 7 pages, 3 figures, published to ICRA 2024

2407.06356 2024-07-10 cs.PL cs.SE 83%

Toward Programming Languages for Reasoning: Humans, Symbolic Systems, and AI Agents

Mark Marron

专题命中规划决策：AI agent(title,abstract)；agent(abstract)；分类 cs.SE

2302.01560 2024-07-09 cs.AI 83%

Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian Ma, Yitao Liang

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments NeurIPS 2023

2306.03604 2024-06-27 cs.AI 83%

Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

Bin Hu, Chenyang Zhao, Pu Zhang, Zihao Zhou, Yuanhang Yang, Zenglin Xu, Bin Liu

专题命中规划决策：agent(title,abstract)；planning(abstract)；分类 cs.AI

Comments 17 pages

2310.05723 2024-06-24 cs.LG 83%

Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning

Trevor McInroe, Adam Jelley, Stefano V. Albrecht, Amos Storkey

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

Comments 10 pages, 17 figures, published at RLC 2024

2401.07314 2024-06-21 cs.AI cs.CV cs.RO 83%

MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation

Jiaqi Chen, Bingqian Lin, Ran Xu, Zhenhua Chai, Xiaodan Liang, Kwan-Yee K. Wong

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments LLM/VLM-based VLN Agents. Accepted to ACL 2024. Project: https://chen-judge.github.io/MapGPT/

2404.00977 2024-06-18 nlin.AO cs.AI math.DS 83%

Nonlinear dynamical social and political prediction algorithm for city planning and public participation using the Impulse Pattern Formulation

Rolf Bader, Simon Linke, Stefanie Gernert

专题命中规划决策：planning(title,abstract)；workflow(abstract)；分类 cs.AI

2406.04028 2024-06-12 cs.AI 83%

Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents

Yoann Poupart

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments Worskhop on Interpretable Policies in Reinforcement Learning @ RLC-2024, 18 pages and 15 figures

2405.12862 2024-06-12 cs.AI 83%

Toward Constraint Compliant Goal Formulation and Planning

Steven J. Jones, Robert E. Wray

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 16 pages + refs. 5 figures, 2 tables. Minor revisions based on reviewer feedback. Accepted for presentation at Advances in Cognitive Systems (Jun 2024, Palermo)

2403.05766 2024-06-06 cs.CL 83%

FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs

Shamik Roy, Sailik Sengupta, Daniele Bonadiman, Saab Mansour, Arshit Gupta

专题命中规划决策：planning(title,abstract)；workflow(abstract)；分类 cs.CL

Comments NAACL 2024 (Camera Ready) (fixed minor typos)

2401.12459 2024-06-03 cs.AI 83%

Towards Socially and Morally Aware RL agent: Reward Design With LLM

Zhaoyue Wang

专题命中规划决策：agent(title,abstract)；planning(abstract)；分类 cs.AI

2312.11027 2024-05-21 cs.AI 83%

Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making

Jingqing Ruan, Kaishen Wang, Qingyang Zhang, Dengpeng Xing, Bo Xu

专题命中规划决策：planning(title,abstract)；AI agent(abstract)；分类 cs.AI

Comments Accepted by Machine Intelligence Research

2404.17833 2024-04-30 cs.AI cs.PL 83%

Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs

Zhenlan Ji, Daoyuan Wu, Pingchuan Ma, Zongjie Li, Shuai Wang

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2310.03624 2024-04-22 cs.CV cs.LG cs.RO 83%

High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning

Lennart Schulze, Hod Lipson

专题命中规划决策：planning(title,abstract)；autonomous agent(abstract)；分类 cs.LG

Comments International Conference on Robotics and Automation (ICRA) 2024; ICCV 2023 Workshop on Neural Fields for Autonomous Driving and Robotics (oral)

2404.09927 2024-04-16 cs.RO cs.LG 83%

Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning

Yuan Bi, Cheng Qian, Zhicheng Zhang, Nassir Navab, Zhongliang Jiang

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

2404.07063 2024-04-11 cs.RO cs.AI 83%

LaPlaSS: Latent Space Planning for Stochastic Systems

Marlyse Reeves, Brian C. Williams

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2404.02361 2024-04-10 cs.MA cs.AI 83%

EnergAIze: Multi Agent Deep Deterministic Policy Gradient for Vehicle to Grid Energy Management

Tiago Fonseca, Luis Ferreira, Bernardo Cabral, Ricardo Severino, Isabel Praca

专题命中规划决策：agent(title,abstract)；multi-agent(abstract)；分类 cs.AI

Comments 6 pages, 6 figures, 2 tables

1. 规划决策 35686 篇

ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution

NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors

Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning

OffRIPP: Offline RL-based Informative Path Planning

Increasing the Value of Information During Planning in Uncertain Environments

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation

AutoGPT+P: Affordance-based Task Planning with Large Language Models

Simulation-Assisted Optimization for Large-Scale Evacuation Planning with Congestion-Dependent Delays

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

2-Level Reinforcement Learning for Ships on Inland Waterways: Path Planning and Following

Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning

Smart Language Agents in Real-World Planning

Empowering Biomedical Discovery with AI Agents

HAPFI: History-Aware Planning based on Fused Information

Toward Programming Languages for Reasoning: Humans, Symbolic Systems, and AI Agents

Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning

MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation

Nonlinear dynamical social and political prediction algorithm for city planning and public participation using the Impulse Pattern Formulation

Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents

Toward Constraint Compliant Goal Formulation and Planning

FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs

Towards Socially and Morally Aware RL agent: Reward Design With LLM

Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making

Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs

High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning

Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning

LaPlaSS: Latent Space Planning for Stochastic Systems

EnergAIze: Multi Agent Deep Deterministic Policy Gradient for Vehicle to Grid Energy Management