用多智能体迭代优化，把自然语言问题自动转为可解的数学模型。
OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
- 多智能体分工协作，逐步提炼变量与约束并自我修正。
- 在4个基准中3个达顶尖水平，尤其在线性与混合整数规划上表现突出。
- 过程透明可审计，适合需要可解释建模的工业场景使用。
我们提出 OptiAgent，一个将运筹学问题的自然语言描述转化为可求解数学公式及可执行代码的多智能体框架。该架构聚焦数学建模环节，通过专用智能体提取决策变量、约束等结构，并支持迭代自修正。引入新型多层验证机制，包含四种针对性反馈，分别应对误理解、结构缺陷、数学不一致、验证失败和代码错误。除提升准确性外，模块化设计增强了求解过程的透明度，每个智能体均暴露推理与反馈，使建模全流程可审计。在涵盖线性规划（LP）、混合整数规划（MILP）及非线性规划任务的4个基准中，框架在3个上达到当前最优性能，其余任务也保持高度竞争力。
原文摘要 · Abstract (English)
We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulation as well as executable code. Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures, such as decision variables and constraints, enabling iterative self-correction. We introduce a novel multi-loop validation architecture with four specialized feedback mechanisms, each targeting a distinct failure mode such as misinterpretation, structural defects, mathematical inconsistencies, validation failures, and code errors. Alongside accuracy, our modular design improves the process of solving optimization problems by improving transparency, as each agent exposes its reasoning and feedback, making the full modeling process auditable. Our framework achieves state-of-the-art performance on 3 out of 4 benchmarks across LP, MILP, and Nonlinear Programming tasks, while remaining highly competitive on the remaining dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。