SAILOR: Solver-Assisted Interactive LLM-based Optimization Recovery

Researchers presented SAILOR, a proof-of-concept system that detects unsupported numerical choices in natural-language optimization problems, asks users targeted follow-up questions, and updates the optimization model before returning a solution. Evaluated on 1,723 instances from seven masked benchmarks using an idealized simulator returning ground-truth values, SAILOR achieved exact objective-value agreement ranging from 27.0% to 87.6% across datasets, with 1.4 to 5.7 questions per instance on average. The authors state the results establish feasibility under controlled branch-and-reveal feedback and do not measure performance with human users or general structural model repair; code is available at https://github.com/sshaghayeghs/SAILOR.

arXiv:2609.13945v1 Announce Type: new 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.