Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
The paper tests whether optimization agents know when a problem is still underspecified before they build the model.
It introduces OR-Clarify, a benchmark where agents must recover hidden formulation details through limited interaction with a simulated user. The benchmark measures slot recovery, stopping behavior, silent assumptions, and interaction cost. The authors also propose InterOPT, which decides whether to ask another clarification question or stop. In choice-based experiments, InterOPT beats all baselines on exact slot recovery; in open-ended tests, it stays competitive with strong prior methods. HF Daily Papers' note
It introduces OR-Clarify, a benchmark where agents must recover hidden formulation details through limited interaction with a simulated user. The benchmark measures slot recovery, stopping behavior, silent assumptions, and interaction cost. The authors also propose InterOPT, which decides whether to ask another clarification question or stop. In choice-based experiments, InterOPT beats all baselines on exact slot recovery; in open-ended tests, it stays competitive with strong prior methods. HF Daily Papers' note
score 4