Metraipolis › archive › dc_7ee46cf59779

OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework — arXiv:2610.00912

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00912
License (as archived): CC0-1.0
Archived: 2026-10-06T12:03:02.889Z
SHA-256 of the archived text: 6147812277f9c19df1afec4713211fbbe9f4b984847744ab3d1cc77290c99a5a
Stable URL of this page: https://metraipolis.com/documento/dc_7ee46cf59779

How to cite

OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework — arXiv:2610.00912 — arXiv (en), https://arxiv.org/abs/2610.00912 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ee46cf59779 (Metraipolis archive dc_7ee46cf59779, sha256 6147812277f9c19df1afec4713211fbbe9f4b984847744ab3d1cc77290c99a5a)

BibTeX

@misc{dc7ee46cf59779,
  title = {OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework — arXiv:2610.00912},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00912},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ee46cf59779; sha256 6147812277f9c19df1afec4713211fbbe9f4b984847744ab3d1cc77290c99a5a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00912. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A solver can then return an optimal solution to the wrong problem. Even when the solution satisfies the intended operating rules, a better plan may exist. For organizations that repeatedly use optimization modeling, an LLM-based framework should produce accurate formulations at low cost and, ideally, run locally. We study how to verify improvements and allocate attempts across LLMs that differ in price and capability. We develop OSCAR (Optimization modeling by Simulator, Coder, And Reviewer), which uses an offline Simulator certified against labeled decision examples to compare candidates and continues searching beyond feasibility. We model the search for the next certified improvement as sequential decisions under unobserved difficulty: which LLMs to call and when to stop. In a simplified known-prior setting, we give conditions under which cost-ordered escalation is optimal. For general menus, we derive a prior-free competitive guarantee. On five benchmark problems, OSCAR achieves 95% to 100% accuracy at the reported settings using two small open-weight LLMs, each deployable locally on a single GPU. Their single-attempt accuracies average 29% and 48%. In five runs per problem, Codex and Claude Code incur average token costs 3.1 and 5.8 times OSCAR's, respectively. OSCAR supports open-weight models locally or in the cloud, depending on budget and confidentiality requirements. Firms should maintain labeled decision examples of feasible and infeasible decisions to clarify plain-language operating rules. OSCAR follows these labels when an LLM's interpretation conflicts with them. As LLM capabilities and prices change, OSCAR's simple operating rules and adjustable settings help firms adapt their model choices and benefit from these advances.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.00912 — 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 2026-10-06T10:21:27.893Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).