arXiv cs.AI· Anran Liu, Benzhao Hou, Zongsheng Cao, Daichao Wang, Lang Chen, Shitong Chen·· 1 天前AI 评分31
ArchOR：面向优化建模的结构感知技能检索与仲裁
Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling
AI 导读
ArchOR 在 OptSkills 基础上新增两个检索模块，以 DeepSeek-V4.1-Flash 为骨干，在五个基准上达到 65.00% Micro-Avg. Pass@1，较 OptSkills 提升 1.64 个百分点 Micro-Avg. 和 2.68 个百分点 Macro-Avg.。
正文 · 原文
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 \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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41909 [cs.AI] |
| (or arXiv:2610.41909v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41909 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: An Liu [view email]
[v1]
Fri, 30 Oct 2026 15:45:17 UTC (1,124 KB)
来源：arXiv cs.AI · arxiv.org