OptSkills: 通过基于聚类的蒸馏从问题原型中学习可泛化的优化技能
OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation
AI总结：
提出OptSkills系统，通过聚类问题原型、蒸馏成功轨迹为可复用工作流技能，并动态扩展技能库，提升优化建模与求解的分布内和分布外泛化能力。
摘要：
利用大型语言模型（LLM）从自然语言自动制定和求解优化问题已成为自动化优化的高效范式。然而，现有方法仍表现出有限的泛化能力：它们对表面叙述变化敏感，主要在案例层面复用经验，难以适应变化或新兴的问题类型。我们提出OptSkills，一个以原型为中心的技能学习和推理智能体系统，用于优化建模和求解。为提升鲁棒泛化，我们的系统根据问题的底层原型而非表面叙述进行聚类。为提升分布内泛化，它在每个聚类内探索多样的建模范式和求解器配置，然后将成功轨迹蒸馏为可重用的工作流级技能。为提升分布外泛化，它利用新获得的轨迹改进现有技能或扩展技能库。我们的系统在涵盖多种问题类型和场景的数据集上达到了68.27%的最先进微平均准确率。此外，在极具挑战性的大规模高维基准MIPLIB-NL上，它达到了26.91%的准确率，比DeepSeek-V3.2-Thinking高出4.53%。在Nano-CO上进行技能学习后，它在OOD NLCO基准上达到了72.79%。代码和技能可在https://github.com/fujiwaranoM0kou/OptSkills获取。
英文摘要：
Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient paradigm for automated optimization. However, existing methods still exhibit limited generalization: they are sensitive to superficial narrative variations, reuse experience mainly at the case level, and struggle to adapt to shifted or emerging problem types. We propose OptSkills, an archetype-centric skill learning and reasoning agent system for optimization modeling and solving. To improve robust generalization, our system clusters problems by their underlying archetypes rather than surface narratives. To improve in-distribution generalization, it explores diverse modeling paradigms and solver configurations within each cluster, then distills successful trajectories into reusable workflow-level skills. To improve out-of-distribution generalization, it refines existing skills or expands the skill library using newly obtained trajectories. Our system achieves a state-of-the-art micro-averaged accuracy of 68.27% on datasets encompassing diverse problem types and scenarios. In addition, on MIPLIB-NL, a highly challenging large-scale and high-dimensional benchmark, it achieves 26.91% accuracy, outperforming DeepSeek-V3.2-Thinking by 4.53%. After skill learning on Nano-CO, it reaches 72.79% on the OOD NLCO benchmark. Code and skills are available at https://github.com/fujiwaranoM0kou/OptSkills.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
