Llm agents coordinate to control smart factory modules with fault handling
LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing
Multiagent SystemsArtificial Intelligence
Summary
Factories need to quickly adapt their machines for custom products and small batch sizes, which is hard to do with fixed programs. The authors show how language-model-driven agents can work together to plan factory tasks and react to unexpected problems like machine faults. Each part of the factory gets its own agent, and they communicate in real time to fix issues without pre-written instructions. Their experiments in a simulated factory show that these agents can detect and work around machinery problems automatically, making factory control more flexible.
What this means in practice
- •For industrial automation engineers: Use LLM-driven agents paired with factory modules to automate reprogramming and handle unexpected machine faults in flexible production lines.
- •For maintenance teams in manufacturing: Employ multi-agent LLM systems to autonomously detect and reroute around hardware faults during production, reducing downtime.
Authors
Kay Köhle, Darko Anicic, Thomas A. Runkler, René Graf
Abstract
Factories are shifting toward smaller lot sizes with high product customization, requiring frequent re-programming of flexible and reconfigurable automation systems. LLM-based agents can be deployed in two complementary roles: Offline, they generate deterministic production sequences, reducing programming effort; online, they operate live machines and handle unforeseen runtime faults that static programs cannot anticipate. We propose a solution in which each factory module is paired with a dedicated LLM-based agent and an MCP tool server that exposes the module's skills via OPC UA method calls, with agents coordinating over MQTT and grounded by real-time updates of the factory state. We compare three agent architectures (orchestrator, peer-to-peer, and monolithic) across nine production challenges of increasing complexity in a simulation of a physical six-module hexagonal factory, including silent hardware fault detection. The monolithic and peer-to-peer architectures both achieve the highest mean solve rate (93\%), while the orchestrator uniquely resolves a silent conveyor-belt fault in all ten runs by autonomously rerouting plates around the blocked segment. All architectures exhibit emergent fault-diagnosis behavior without any explicit failure-handling logic, establishing standardized MCP tooling, MQTT-based inter-agent communication, and real-time state injection as a viable and reproducible foundation for LLM-programmed smart manufacturing.