{"ID":6138078,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T04:12:54.209499018Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06990","arxiv_id":"2607.06990","title":"A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation","abstract":"Multi-robot systems provide the parallelism and redundancy necessary for long-horizon tasks, while Large Language Models (LLMs) offer the reasoning capabilities to decompose these objectives into actionable plans. However, effectively grounding this high-level reasoning in physical multi-robot execution remains an open challenge. Existing LLM-based approaches fall mainly into two categories: Single-robot methods achieve robust contact-rich manipulation but lack the coordination mechanisms required for tasks spanning multiple workspaces. Current multi-robot frameworks focus on high-level planning, often treating manipulation as an idealized primitive that fails to account for real-world execution uncertainties. To address this, we propose a hierarchical closed-loop agentic LLM-based framework to ensure robust multi-robot manipulation. Our system consists of three specialized agents: the Planning Agent decomposes instructions into allocated sub-tasks, the Manipulation Agent for each robot executes actions via adaptive tool use, and the Verification Agent closes the loop by monitoring physical outcomes and feeding back semantic corrections. Extensive real-world experiments demonstrate that our framework achieves superior success rates, ensures robust adaptability ranging from single to cross workspace manipulation, and offers a generalizable approach for diverse manipulation tasks.","short_abstract":"Multi-robot systems provide the parallelism and redundancy necessary for long-horizon tasks, while Large Language Models (LLMs) offer the reasoning capabilities to decompose these objectives into actionable plans. However, effectively grounding this high-level reasoning in physical multi-robot execution remains an open...","url_abs":"https://arxiv.org/abs/2607.06990","url_pdf":"https://arxiv.org/pdf/2607.06990v1","authors":"[\"Yi-Xiang He\",\"Lan Wei\",\"Haoming Cen\",\"Jian-Jian Jiang\",\"Zhuohao Li\",\"Guanxing Lu\",\"Yihan Yang\",\"Dandan Zhang\",\"Wei-Shi Zheng\"]","published":"2026-07-08T04:23:41Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}