2605.29829v1 May 28, 2026 cs.AI

OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation

Xingyu Lu
Xingyu Lu
Citations: 140
h-index: 3
Haochen Yang
Haochen Yang
Citations: 34
h-index: 3
Hong Qian
Hong Qian
Citations: 179
h-index: 9
Keyu Zhao
Keyu Zhao
Citations: 145
h-index: 4
Mengyuan Ma
Mengyuan Ma
Citations: 54
h-index: 3
Xiangfeng Wang
Xiangfeng Wang
Citations: 145
h-index: 7

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.

0 Citations
0 Influential
32.547189562171 Altmetric
162.7 Score
Original PDF
4

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!