A closed-loop multi-agent LLM framework enables heterogeneous robots to collaboratively manipulate objects by decomposing tasks, grounding actions via visual tools, and recovering from execution failures hierarchically.
A survey and analysis of multi-robot coordination.Interna- tional Journal of Advanced Robotic Systems, 2013
2 Pith papers cite this work, alongside 641 external citations. Polarity classification is still indexing.
2
Pith papers citing it
641
external citations · OpenAlex
fields
cs.RO 2years
2026 2verdicts
CONDITIONAL 2representative citing papers
AEROS models each robot as one persistent agent with installable Embodied Capability Modules and a policy-separated runtime, reporting 100% simulated task success versus 67–93% for reimplemented baselines.
citing papers explorer
-
A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation
A closed-loop multi-agent LLM framework enables heterogeneous robots to collaboratively manipulate objects by decomposing tasks, grounding actions via visual tools, and recovering from execution failures hierarchically.
-
AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules
AEROS models each robot as one persistent agent with installable Embodied Capability Modules and a policy-separated runtime, reporting 100% simulated task success versus 67–93% for reimplemented baselines.