analiza aiqbench
OptSkills advances automated optimization by clustering problems into underlying archetypes rather than relying on surface narratives, enabling LLMs to distill reusable workflow-level skills for better generalization. This approach significantly improves performance on challenging benchmarks like MIPLIB-NL and out-of-distribution scenarios compared to current state-of-the-art models. The method represents a meaningful step toward robust, adaptable AI agents capable of solving complex mathematical problems from natural language descriptions.
OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation
arXiv:2605.29829v2 Announce Type: replace-cross Abstract: 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.
Abstract: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 this https URL.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2605.29829 [cs.AI]
(or arXiv:2605.29829v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.29829 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 280 cuvinte
Subiecte conexe
Presentation: Designing AI Platforms for Reliability: Tools for Certainty, Agents for Discovery
InfoQ · 27 mai 2026
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning
arXiv · 28 iul. 2026
The basic argument for making AI better at moral philosophy
LessWrong · 14 oct. 2026
Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye
Import AI · 24 aug. 2026