SAILOR: Solver-Assisted Interactive LLM-based Optimization Recovery

2026-09-12

AI Summary

针对自然语言描述的优化问题中数值信息不完整的问题，SAILOR系统通过与用户互动提问来补充缺失值，并更新模型以求解。

Abstract

Natural-language descriptions of optimization problems may be incomplete or vague about numerical information that a solver requires, including costs, capacities, demands, bounds, and penalties. A language model can translate the description into code, but when a required value is absent it must either stop or guess. We present SAILOR, a proof-of-concept system that detects such unsupported numerical choices, asks the user targeted follow-up questions, and updates the optimization model before returning a solution. Questions are prioritized using uncertainty and solver-derived estimates of how strongly each missing value affects the current model. We evaluate the pipeline on 1,723 instances from seven masked benchmarks using an idealized simulator that returns ground-truth values. Exact objective-value agreement ranges from 27.0% to 87.6% across datasets, with 1.4--5.7 questions per instance on average. These results establish feasibility under controlled branch-and-reveal feedback; they do not measure performance with human users or general structural model repair. Code is available at: https://github.com/sshaghayeghs/SAILOR.

Problem

• natural-language descriptions
• optimization problems
• numerical information
• solver
• missing values

Innovation

• Solver-Assisted
• Interactive LLM
• Optimization Recovery
• Uncertainty Estimation
• Targeted Follow-up Questions