優化前先釐清：互動式優化中的動態前置規劃澄清

摘要

大型語言模型（LLM）日益被用於從自然語言問題描述中建構最佳化模型；然而，真實世界的作業研究（OR）請求往往不完整：缺少的目標函數、限制式或商業規則，都可能改變最終的數學規劃。現有評測大多假設規格完整無缺，因而忽略了代理是否知道在建模前何時需要釐清。我們提出 OR-Clarify，這是一個針對建模前釐清的基準測試：每個任務皆提供部分的公開問題描述並隱藏結構化槽位，再透過代理與模擬使用者之間有限次數的互動來評測其表現。該基準同時支援開放式與選項式釐清，並衡量槽位恢復、停止行為、隱性假設與互動成本。我們進一步提出互動式最佳化（InterOPT），這是一個兩階段框架：先識別尚未解決且對建模至關重要的缺口，再以此決定應提出下一個問題，或是停止提問。在我們以選項式為主的實驗中，InterOPT 在精確槽位恢復上大幅優於所有基線方法；在開放式設定下，它也能與表現強勁的既有方法並駕齊驅。總而言之，OR-Clarify 與 InterOPT 將 OR 輔助重新定位為一項選擇性完整性決策：需要時釐清、就緒時停止，並量化仍有所缺的資訊。

English

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.