DSevolve: Enabling Real-Time Adaptive Scheduling on Dynamic Shop Floor with LLM-Evolved Heuristic Portfolios

TL;DR

DSevolve is a framework that evolves diverse dispatching rules offline and adaptively deploys them online for real-time scheduling in dynamic manufacturing environments, outperforming existing methods.

Contribution

It introduces a behaviorally diverse rule portfolio evolved with topology-aware operators and a rapid selection mechanism for adaptive shop floor scheduling.

Findings

Outperforms state-of-the-art AHD frameworks, classical rules, genetic programming, and deep RL.

Provides a practical solution with second-level response time for real-time scheduling.

Validated on 500 real industrial instances, demonstrating superior adaptability.

Abstract

In dynamic manufacturing environments, disruptions such as machine breakdowns and new order arrivals continuously shift the optimal dispatching strategy, making adaptive rule selection essential. Existing LLM-powered Automatic Heuristic Design (AHD) frameworks evolve toward a single elite rule that cannot meet this adaptability demand. To address this, we present DSevolve, an industrial scheduling framework that evolves a quality-diverse portfolio of dispatching rules offline and adaptively deploys them online with second-level response time. Multi-persona seeding and topology-aware evolutionary operators produce a behaviorally diverse rule archive indexed by a MAP-Elites feature space. Upon each disruption event, a probe-based fingerprinting mechanism characterizes the current shop floor state, retrieves high-quality candidate rules from an offline knowledge base, and selects the best one via rapid look-ahead simulation. Evaluated on 500 dynamic flexible job shop instances derived from real industrial data, DSevolve outperforms state-of-the-art AHD frameworks, classical dispatching rules, genetic programming, and deep reinforcement learning, offering a practical and deployable solution for intelligent shop floor scheduling.