---
title: "Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41909v1"
permalink: "https://feed.astralor.com/items/itm_ba1a9650e77cd49194235bd5"
published: "2026-10-30T15:45:17.000Z"
score: 54
channel: "tech"
tags: ["LLM","AI Agent","推理效率","RAG","Structure-Aware Skill Retrieval","Arbitration","Optimization Modeling Large","Language Models"]
---

# Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling

## At a glance

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…

## Key points

- 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 \textsc{ArchOR}, an archetype-centric skill agent that builds on \textsc{OptSkills} by adding two retrieval-focused modules.
- \emph{Centroid-Aware Representation Learning} (CARL) refines the ordering of cached skill representations through a low-rank prototype residual.

## Full text

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 \textsc{ArchOR}, an archetype-centric skill agent that builds on \textsc{OptSkills} by adding two retrieval-focused modules. \emph{Centroid-Aware Representation Learning} (CARL) refines the ordering of cached skill representations through a low-rank prototype residual. \emph{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-$K$ 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, \textsc{ArchOR} reaches 65.00\% Micro-Avg.\ Pass@1 across five benchmarks, improving over \textsc{OptSkills} by 1.64~pp Micro-Avg.\ and 2.68~pp Macro-Avg.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_ba1a9650e77cd49194235bd5