Metraipolis › archive › dc_4d8eb693efe6
TACIT: Optimization Models that Learn from Their Mistakes — arXiv:2609.38434
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38434
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:43:42.641Z
- SHA-256 of the archived text
098fa1aa4baa404b4ac5ab554c4d5383e3e63b0a994dc38991e380e4e83531d8- Stable URL of this page
https://metraipolis.com/documento/dc_4d8eb693efe6
How to cite
TACIT: Optimization Models that Learn from Their Mistakes — arXiv:2609.38434 — arXiv (en), https://arxiv.org/abs/2609.38434 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d8eb693efe6 (Metraipolis archive dc_4d8eb693efe6, sha256 098fa1aa4baa404b4ac5ab554c4d5383e3e63b0a994dc38991e380e4e83531d8)
BibTeX
@misc{dc4d8eb693efe6,
title = {TACIT: Optimization Models that Learn from Their Mistakes — arXiv:2609.38434},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38434},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d8eb693efe6; sha256 098fa1aa4baa404b4ac5ab554c4d5383e3e63b0a994dc38991e380e4e83531d8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38434. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world optimization problems are difficult to model accurately because many objectives and constraints reside in domain experts' tacit knowledge, making them hard to formalize. As a result, optimization models often contain miscalibrated objectives, missing constraints, or omitted decision variables, leading to solutions that fail to reflect operational realities. We address this challenge by automatically repairing misspecified formulations using historical data consisting of past solutions and subsequent user overrides. Traditional approaches such as inverse optimization and constraint learning tend to overfit sparse data and produce complex formulations. Our central idea is to combine the reasoning capabilities and prior knowledge of LLMs with the formal grounding provided by optimization. We realize this idea through two complementary paradigms. Top-down, an LLM proposes structural repairs, including new constraints and variables, whose numerical parameters are calibrated and validated through optimization. Bottom-up, optimization infers cuts from observed decisions, which the LLM contextualizes into interpretable, generalizable modeling constraints. We evaluate our approach on 38 misspecification scenarios spanning nine classes of optimization problems, several drawn from real-world applications, and show that TACIT can repair 78.9% of them (vs. 60.5% for the best baseline). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Optimization and Control (math.OC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.38434 — 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 2026-10-07T12:14:13.878Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).