MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research
Authors:
- Yifan ShiYSYifan Shi
- Jialong ShiJSJialong Shi
- Jiayi WangJWJiayi Wang
- Ye FanYFYe Fan
- Jianyong SunJSJianyong Sun
Preprint
Abstract
Operations Research (OR) relies on expert-driven modeling-a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing approaches either rely on costly post-training or employ multi-agent frameworks, yet most still lack reliable collaborative error correction and task-specific retrieval, often leading to incorrect outputs. We propose MIRROR, a fine-tuning-free, end-to-end multi-agent framework that directly translates natural language optimization problems into mathematical models and solver code. MIRROR integrates two core mechanisms: (1) execution-driven iterative adaptive revision for automatic error correction, and (2) hierarchical retrieval to fetch relevant modeling and coding exemplars from a carefully curated exemplar library. Experiments show that MIRROR outperforms existing methods on standard OR benchmarks, with notable results on complex industrial datasets such as IndustryOR and Mamo-ComplexLP. By combining precise external knowledge infusion with systematic error correction, MIRROR provides non-expert users with an efficient and reliable OR modeling solution, overcoming the fundamental limitations of general-purpose LLMs in expert optimization tasks.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement LearningProceedings of the AAAI Conference on Artificial Intelligence, 2026
- ORLM: A Customizable Framework in Training Large Models for Automated Optimization ModelingOperations Research, 2025
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature, 2025
- A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions2025
- ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research2025
- LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages2025
- Artificial intelligence in supply chain and operations management: a multiple case study researchInternational Journal of Production Research, 2023
- Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models2022