arXiv:2610.41909v1 Announce Type: new
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.
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.
This article has been indexed from cs.AI updates on arXiv.org
Read the original article:
Structure-Aware Skill Retrieval and Arbitration for Optimization Modeling