| title | Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization |
|---|---|
| authors | Sihan Ge, Yichen Lin, Chenyu Zhou, Jianghao Lin, Tao Yao, Dongdong Ge |
| date | 2026-09-04 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.05258 |
| affiliation | AIOR |
| upvotes | 19 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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. |
cite
@misc{ge2026ask,
title={Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization},
author={Sihan Ge and Yichen Lin and Chenyu Zhou and Jianghao Lin and Tao Yao and Dongdong Ge},
year={2026},
eprint={2609.05258},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.05258}
}