Logic-Based Verification of Task Allocation for LLM-Enabled Multi-Agent Manufacturing Systems

TL;DR

This paper presents a logic-based framework that verifies safe task allocation in manufacturing systems enhanced with large language models, ensuring safety despite system reconfigurations.

Contribution

It introduces a novel verification approach combining temporal logic and discrete event systems to ensure safety in LLM-enabled multi-agent manufacturing.

Findings

Unsafe tasks are identified and prevented before execution.

The framework effectively verifies task safety in a multi-robot assembly case study.

Abstract

Manufacturing industries are facing increasing product variability due to the growing demand for personalized products. Under these conditions, ensuring safety becomes challenging as frequent reconfigurations can lead to unintended hazardous behaviors. Multi-agent control architectures have been proposed to improve flexibility through decentralized decision-making and coordination. However, these architectures are based on predefined task models, which limit their ability to adapt task planning to new product requirements while preserving safety. Recently, large language models have been introduced into manufacturing systems to enhance adaptability, but reliability remains a key challenge. To address this issue, we propose a control architecture that leverages the flexibility of large language models while preserving safety on the manufacturing shop floor. Specifically, the proposed framework verifies large language model-enabled task allocations by using temporal logic and discrete event systems. The effectiveness of the proposed framework is demonstrated through a case study that involves a multi-robot assembly scenario, showing that unsafe tasks can be allocated safely before task execution.