Reproduce “LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Kay Köhle, Darko Anicic, Thomas A. Runkler, René Graf

The authors present a multi-agent factory-control framework that combines MCP tool servers, OPC UA machine skills, MQTT communication, and injected factory-state updates. They compare orchestrator, peer-to-peer, and monolithic architectures in a Python simulation. Across nine challenges, monolithic and peer-to-peer average 93% solve rate, versus 87% for the orchestrator; on one silent conveyor fault, it succeeds in all 10 runs.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.