A Two-Stage Reflection and Reprompting Framework for LLM-Based Solution of Petri Net Reachability Problems in Industrial Applications
For industrial manufacturing scheduling and verification, this work provides a more reliable LLM-based approach to Petri net reachability, though the improvement is incremental over existing LLM-based planning methods.
The paper proposes a two-stage reflection and reprompting framework for LLMs to solve Petri net reachability problems in manufacturing, achieving improved reliability and stability across six solvable configurations and multiple LLMs.
Manufacturing systems exhibit strong concurrency, synchronization, and contention for shared reusable resources, which makes fast and reliable scheduling and verification challenging. Petri nets provide a rigorous formalism for modeling such discrete-event manufacturing systems, but reachability analysis and solving remain difficult for conventional graph search or optimization-based solvers, particularly under state-space explosion and evolving production requirements. Recently, Large language models (LLMs) have shown promise as flexible planners that can generate candidate action sequences from textual specifications. However, direct use of LLMs for Petri net reachability remains unreliable. This paper proposes an LLM-based solving framework augmented with a two-stage reflection and reprompting mechanism. The combined effects of reflection and re-clarification improve the accuracy of feasible sequence generation. The proposed method is evaluated on an industrial case modeled as a Petri net. Under a fixed Petri net structure, the proposed strategy is assessed on six solvable reachability configurations. The results demonstrate improved reliability and stability in solving Petri net reachability problems. The proposed framework is further evaluated across multiple LLMs, which indicates that the framework is not tied to any specific model.