REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Puzhen, Ma, Angyuan, Yao, Yunchao, Yao, Huaxiu, Tomizuka, Masayoshi, Ding, Mingyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912298848747520
author Yuan, Puzhen
Ma, Angyuan
Yao, Yunchao
Yao, Huaxiu
Tomizuka, Masayoshi
Ding, Mingyu
author_facet Yuan, Puzhen
Ma, Angyuan
Yao, Yunchao
Yao, Huaxiu
Tomizuka, Masayoshi
Ding, Mingyu
contents Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers several appealing benefits: 1) Robots can initially explore and reason about the environment without complex prompt design. 2) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 3) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC's effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3-mini, QwQ, and Grok3, demonstrating REMAC's superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation
Yuan, Puzhen
Ma, Angyuan
Yao, Yunchao
Yao, Huaxiu
Tomizuka, Masayoshi
Ding, Mingyu
Robotics
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically rely on prior environmental knowledge or carefully designed task-specific prompts, making them struggle with dynamic scene changes or unexpected task conditions, e.g., a robot attempting to put a carrot in the microwave but finds the door was closed. Such challenges underscore two critical issues: adaptability and efficiency. To address them, in this work, we propose an adaptive multi-agent planning framework, termed REMAC, that enables efficient, scene-agnostic multi-robot long-horizon task planning and execution through continuous reflection and self-evolution. REMAC incorporates two key modules: a self-reflection module performing pre-condition and post-condition checks in the loop to evaluate progress and refine plans, and a self-evolvement module dynamically adapting plans based on scene-specific reasoning. It offers several appealing benefits: 1) Robots can initially explore and reason about the environment without complex prompt design. 2) Robots can keep reflecting on potential planning errors and adapting the plan based on task-specific insights. 3) After iterations, a robot can call another one to coordinate tasks in parallel, maximizing the task execution efficiency. To validate REMAC's effectiveness, we build a multi-agent environment for long-horizon robot manipulation and navigation based on RoboCasa, featuring 4 task categories with 27 task styles and 50+ different objects. Based on it, we further benchmark state-of-the-art reasoning models, including DeepSeek-R1, o3-mini, QwQ, and Grok3, demonstrating REMAC's superiority by boosting average success rates by 40% and execution efficiency by 52.7% over the single robot baseline.
title REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation
topic Robotics
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.22122