This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction paradigm with a structured memory system to decompose tasks into executable robot skills while dynamically validating actions against environmental constraints. We present MultiPlan+, a dataset of more than 18,000 annotated planning instances spanning 100 scenarios, including a subset of impractical cases to mitigate hallucination. To evaluate performance, we propose the Robot Planning Assessment Schema (RPAS), combining automated metrics with LLM-aided expert grading. Experiments demonstrate EmbodiedAgent's superiority over state-of-the-art models, achieving 71.85% RPAS score. Real-world validation in an office service task highlights its ability to coordinate heterogeneous robots for long-horizon objectives.
@article{arxiv.2504.10030,
title = {EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Control},
author = {Hanwen Wan and Yifei Chen and Yixuan Deng and Zeyu Wei and Dongrui Li and Zexin Lin and Donghao Wu and Jiu Cheng and Xiaoqiang Ji},
journal= {arXiv preprint arXiv:2504.10030},
year = {2025}
}