# A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation Source: [A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation]() Collection index: [llms.txt]() Data updated: 2026-07-10T05:00:01.278Z Authors: Yi-Xiang He, Lan Wei, Haoming Cen, Jian-Jian Jiang, Zhuohao Li, Guanxing Lu, Yihan Yang, Dandan Zhang, Wei-Shi Zheng Published: 2026-07-08T04:23:41.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Block-stacking on Block-stacking External Disturbances](): Block-stacking; Block-stacking External Disturbances; Success Rate: 50. - [Robotic Manipulation on Table Top Tasks Block Stacking](): Robotic Manipulation; Table Top Tasks Block Stacking; Success Rate: 70. - [Robotic Manipulation on Table Top Tasks Table Organization](): Robotic Manipulation; Table Top Tasks Table Organization; Success Rate: 11. - [Robotic Manipulation on Table Top Tasks Object Stowing](): Robotic Manipulation; Table Top Tasks Object Stowing; Success Rate: 14. - [Object Stowing on Desktop Tasks External Disturbances](): Object Stowing; Desktop Tasks External Disturbances; Success Rate (SR): 8. - [Table Organization on Desktop Tasks External Disturbances](): Table Organization; Desktop Tasks External Disturbances; Success Rate (SR): 60. ## Original sources and implementation [Original paper]() [PDF]()