cs.AIOct 30, 2026

Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling

Authors: Anran Liu, Benzhao Hou, Zongsheng Cao, Daichao Wang, Lang Chen, Shitong Chen

Abstract

Large Language Models (LLMs) can turn natural-language optimization tasks into solver-checked answers, but current agents remain brittle under narrative rewrites and often store reusable experience at the instance level. We introduce ArchOR, an archetype-centric skill agent that builds on OptSkills by adding two retrieval-focused modules. Centroid-Aware Representation Learning (CARL) refines the ordering of cached skill representations through a low-rank prototype residual. Signature-Guided Retrieval (S\textsuperscript{3}R) attaches open-dimensional structural signatures to skills, prioritizes candidates by weighted Jaccard overlap, and bounds semantic re-ranking to a top-KK set. A baseline-preserving arbitration rule determines when the structural route should replace the original selector. With the same DeepSeek-V4.1-Flash backbone and released skill library, ArchOR reaches 65.00% Micro-Avg.\ Pass@1 across five benchmarks, improving over OptSkills by 1.64pp Micro-Avg.\ and 2.68pp Macro-Avg.

Figures & tables

Explore similar work

CardsList
  1. OptiSkill: A Hierarchical and Evolving SkillBank for LLM-Based Optimization Modeling

    Sep 19, 2026Ruiqing Zhao, Rui Liu, Yuan Zuo +3Large Language Model-Guided OptimizationNatural Language to Optimization Modeling

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

    May 28, 2026Haochen Yang, Ke Zhao, Mengyuan Ma +3Large Language Model-Guided OptimizationOOD Generalization