mlsanityData to 14 Oct 2026

SAILOR: Solver-Assisted Interactive LLM-based Optimization Recovery

arXiv 2609.13945 ↗First posted 12 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 12 Sep 2026.

Builds on

32 of 41 references.

References · 32

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  9. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  10. 2023Large Language Models as Optimizerscited by 864
  11. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  12. 2017Smart "Predict, then Optimize"cited by 339
20 more
  1. 2018Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimizationcited by 227
  2. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 185
  3. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  4. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 144
  5. 2023NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptionscited by 135
  6. 2024ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modelingcited by 124
  7. 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Modelscited by 109
  8. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 108
  9. 2023SatLM: Satisfiability-Aided Language Models Using Declarative Promptingcited by 102
  10. 2024LLMOPT: Learning to Define and Solve General Optimization Problems from Scratchcited by 102
  11. 2023Large Language Models for Supply Chain Optimizationcited by 64
  12. 2022Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptionscited by 54
  13. 2024OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scalecited by 38
  14. 2025A Survey of Optimization Modeling Meets LLMs: Progress and Future Directionscited by 31
  15. 2023Diagnosing Infeasible Optimization Problems Using Large Language Modelscited by 27
  16. 2025OptimAI: Optimization from Natural Language Using LLM-Powered AI Agentscited by 22
  17. 2024Deep Bayesian Active Learning for Preference Modeling in Large Language Modelscited by 19
  18. 2022Python Code Generation by Asking Clarification Questionscited by 17
  19. 2025AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Librarycited by 14
  20. 2025Large Language Models in Operations Research: Methods, Applications, and Challengescited by 6

Built on by

Not cited yet.