Metraipolis › archive › dc_2276112f228d
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization — arXiv:2609.05258
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05258
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:29:12.618Z
- SHA-256 of the archived text
c2f84a2c7b9b49c63770e6b79b214294cf77935ea15918dbe86f31b1fb43c6ef- Stable URL of this page
https://metraipolis.com/documento/dc_2276112f228d
How to cite
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization — arXiv:2609.05258 — arXiv (en), https://arxiv.org/abs/2609.05258 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2276112f228d (Metraipolis archive dc_2276112f228d, sha256 c2f84a2c7b9b49c63770e6b79b214294cf77935ea15918dbe86f31b1fb43c6ef)
BibTeX
@misc{dc2276112f228d,
title = {Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization — arXiv:2609.05258},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05258},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2276112f228d; sha256 c2f84a2c7b9b49c63770e6b79b214294cf77935ea15918dbe86f31b1fb43c6ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05258. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operations research (OR) requests are often incomplete: missing objectives, constraints, or business rules can change the resulting mathematical program. Existing evaluations largely assume a complete specification and therefore overlook whether an agent knows when clarification is needed before modeling. We introduce OR-Clarify, a benchmark for pre-formulation clarification. Each task presents a partial public problem description, withholds structured hidden slots, and evaluates agents through bounded interaction with a simulated user. The benchmark supports both openended and choice-based clarification, and measures slot recovery, stopping behavior, silent assumptions, and interaction cost. We further propose Interactive Optimization (InterOPT), a two-stage framework that identifies unresolved formulation-critical gaps and uses them to guide whether to ask the next question or to stop. In our choice-based experiments, InterOPT substantially outperforms all baselines in exact slot recovery; in the open-ended setting, it remains competitive with strong prior methods. Together, OR-Clarify and InterOPT reframe OR assistance as a selective completeness decision: clarify when needed, stop when ready, and quantify what remains missing. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI). Categorie arXiv: Optimization and Control (math.OC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.05258 — 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 2026-10-16T22:18:11.582Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).