MAFIG: Multi-agent Driven Formal Instruction Generation Framework

2026-04-13

AI Summary

This study addresses the challenge of localized functional failures in scheduling systems caused by sudden emergencies, which existing approaches struggle to handle due to their reliance on predefined rules or computationally expensive global rescheduling. To overcome this limitation, the authors propose a lightweight, multi-agent-driven emergency repair framework that enables rapid generation of formalized scheduling instructions within affected regions through coordinated perception and decision-making agents. Furthermore, they introduce a Span-Focused Loss–guided local knowledge distillation mechanism to efficiently transfer capabilities from large cloud-based models to compact local models. Evaluated on port, warehouse, and deck scheduling datasets, the method achieves repair success rates of 98.49%, 94.97%, and 97.50%, respectively, with average processing times of only 0.33, 0.23, and 0.19 seconds—demonstrating high performance with significantly reduced inference latency.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning
• Search and Optimization: Local Search

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Emergency situations in scheduling systems often trigger local functional failures that undermine system stability and even cause system collapse. Existing methods primarily rely on robust scheduling or reactive scheduling, handling emergencies through predefined rules or rescheduling strategies. However, the diversity and unpredictability of real-world emergencies make them difficult to anticipate, which limits the adaptability of these methods in complex scenarios. Recent studies have shown that Large Language Models (LLMs) possess strong potential for complex scheduling tasks because of their extensive prior knowledge and strong reasoning capabilities. Nevertheless, the high inference latency of LLMs and the lengthy contextual information of scheduling systems significantly hinder their application for emergency handling. To mitigate these issues, we propose the Multi-agent Driven Formal Instruction Generation Framework (MAFIG). The framework constrains the decision scope to local functional modules affected by emergency situations and repairs scheduling logic rapidly by generating formal instructions. MAFIG contains a Perception Agent and an Emergency Decision Agent, which mitigates the adverse impact of lengthy system contexts on emergency decision-making. We further introduce span-focused loss-driven local distillation mechanism (SFL) to transfer the decision-making capability of powerful Cloud Large Language Models (C-LLMs) to lightweight local models, reducing inference latency while preserving decision-making effectiveness. Experiments in the Port, Warehousing, and Deck scheduling datasets show success rates of 98.49\%, 94.97\%, and 97.50\%, with average processing times of 0.33 s, 0.23 s, and 0.19 s. These results demonstrate that MAFIG effectively mitigates the impact of emergencies and improves the robustness and adaptability of scheduling systems.

Problem

• emergency handling
• scheduling systems
• Large Language Models
• system robustness
• real-time decision-making

Innovation

• Multi-agent Framework
• Formal Instruction Generation
• Local Distillation
• Emergency Scheduling
• Large Language Models