Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling

2026-05-27

AI Summary

Dynamic flexible job shop scheduling faces the challenge of simultaneously achieving millisecond-level real-time responsiveness and long-term global optimization. To address this, this work proposes RACE-Sched, a framework featuring an asynchronous dual-stream architecture that decouples execution from reasoning: a reactive stream employs low-latency symbolic heuristics for immediate scheduling decisions, while a deliberative stream leverages large language models to parallelly generate, validate, and evolve scheduling rules. The framework innovatively incorporates a semantic rule repository to enable cross-scale transferability and integrates sandbox validation with atomic update mechanisms to ensure system safety. Experimental results demonstrate that RACE-Sched significantly outperforms existing deep reinforcement learning and LLM-based approaches on GEN-Bench, MK-Bench, and JMS-Bench, achieving superior performance in both scheduling quality and dynamic adaptability.

Abstract

The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimization of production goals. Conventional priority rules are insufficiently flexible to handle complex disruptions, whereas learning-based approaches often compromise interpretability or fail to generalize across problem scales. Although Large Language Models (LLMs) offer advanced reasoning capabilities to bridge this gap, their substantial inference latency is incompatible with the millisecond-level decision cycles of industrial control systems. To resolve this conflict, we introduce RACE-Sched, an asynchronous agent-based framework that decouples policy execution from logical reasoning via a dual-stream architecture. The Reactive Stream executes low-latency symbolic heuristics to enable real-time dispatching, while the parallel Deliberative Stream leverages an LLM to synthesize, validate, and evolve these rules. Candidate rules undergo rigorous testing in a sandbox and are deployed via atomic updates, ensuring safety without blocking the control loop. Additionally, a semantic rule repository indexes validated heuristics for retrieval-based initialization which enhances transferability across problem scales. Extensive evaluations on GEN-Bench, MK-Bench, and JMS-Bench demonstrate that RACE-Sched outperforms leading Deep Reinforcement Learning and other LLM-based baselines. This approach harmonizes real-time constraints with long-horizon reasoning to achieve superior solution quality and robust adaptation to dynamic events.

Problem

• Dynamic Flexible Job Shop Scheduling
• Real-Time Constraints
• Long-Horizon Reasoning
• Stochastic Disturbances
• Industrial Control Systems

Innovation

• asynchronous agentic framework
• dual-stream architecture
• LLM-based scheduling
• real-time dynamic scheduling
• semantic rule repository