SAILOR: Solver-Assisted Interactive LLM-based Optimization Recovery
Quick summary
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
Key takeaways
- 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.
Why it matters
“SAILOR: Solver-Assisted Interactive LLM-based Optimization Recovery” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments