Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10989 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914467723345920 |
|---|---|
| author | Zhao, Shixing Si, Zheng Ouyang, Pengpeng Hu, Zhengqing Zhu, Wanqi Chen, Dong Guo, Yibo Xu, Mingliang |
| author_facet | Zhao, Shixing Si, Zheng Ouyang, Pengpeng Hu, Zhengqing Zhu, Wanqi Chen, Dong Guo, Yibo Xu, Mingliang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10989 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MAFIG: Multi-agent Driven Formal Instruction Generation Framework Zhao, Shixing Si, Zheng Ouyang, Pengpeng Hu, Zhengqing Zhu, Wanqi Chen, Dong Guo, Yibo Xu, Mingliang Artificial Intelligence 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. |
| title | MAFIG: Multi-agent Driven Formal Instruction Generation Framework |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.10989 |