Metraipolis › archive › dc_2f47e3698dbe
COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling — arXiv:2611.12060
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12060
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:42.280Z
- SHA-256 of the archived text
03cb9285a14f86167aaf2ed0f03515408cca687c8db57a487589674bea2ce6e1- Stable URL of this page
https://metraipolis.com/documento/dc_2f47e3698dbe
How to cite
COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling — arXiv:2611.12060 — arXiv (en), https://arxiv.org/abs/2611.12060 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f47e3698dbe (Metraipolis archive dc_2f47e3698dbe, sha256 03cb9285a14f86167aaf2ed0f03515408cca687c8db57a487589674bea2ce6e1)
BibTeX
@misc{dc2f47e3698dbe,
title = {COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling — arXiv:2611.12060},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12060},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f47e3698dbe; sha256 03cb9285a14f86167aaf2ed0f03515408cca687c8db57a487589674bea2ce6e1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12060. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models offer a promising technique for translating natural-language optimization problems into solver code, but their reliability remains constrained by the quality of template retrieval. While recent structured methods improve over flat prompting through hierarchical taxonomy search, their traversal rules remain fixed or LLM-driven at inference time, leaving retrieval unable to improve from past successes and failures. This motivates treating template retrieval as a policy that can be learned from modeling experience, rather than as a static inference-time rule. We propose COMPASS, a policy-amortized framework for retrieving optimization templates in LLM-based solver modeling, which represents the template library as a directed acyclic graph and formulates retrieval as a sequential decision process over template nodes. A deep Q-network learns a reusable traversal policy from template-level judgments and execution feedback, reducing reliance on fixed heuristic traversal through feedback-driven graph navigation. To support extensible retrieval, COMPASS embeds problem descriptions and template nodes in a shared semantic space, allowing newly inserted templates to be scored from their text descriptions without redefining the action space. Experiments across multiple LLM backbones and optimization-modeling benchmarks demonstrate that COMPASS consistently improves over heuristic structured retrieval, with the largest gains on complex and mixed-category problems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.12060 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.533Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).