# OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents arXiv: https://arxiv.org/abs/2602.19439 ยท HTML: https://mlsanity.com/paper/2602.19439/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. - Builds on 22 of its 49 references that are in the map. - First posted on arXiv 23 Feb 2026. ## Placed in - LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/) ## Builds on (most cited first, 22 of 22) - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024) - [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022) - [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023) - [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024) - [OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models](https://mlsanity.com/paper/2402.10172/) (2024) - [OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling](https://mlsanity.com/paper/2407.09887/) (2024) - [Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models](https://mlsanity.com/paper/2507.02778/) (2025) - [Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints](https://mlsanity.com/paper/2504.11320/) (2025) - [Auto-Formulating Dynamic Programming Problems with Large Language Models](https://mlsanity.com/paper/2507.11737/) (2025) - [Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards](https://mlsanity.com/paper/2506.16658/) (2025) - [Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs](https://mlsanity.com/paper/2510.16062/) (2025) - [Large Language Models for Supply Chain Decisions](https://mlsanity.com/paper/2507.21502/) (2025) - [Large-Scale Optimization Model Auto-Formulation: Harnessing LLM Flexibility via Structured Workflow](https://mlsanity.com/paper/2601.09635/) (2026) - [Best Arm Identification with LLM Judges and Limited Human](https://mlsanity.com/paper/2601.21471/) (2026) - [AI Agents for Inventory Control: Human-LLM-OR Complementarity](https://mlsanity.com/paper/2602.12631/) (2026) - [AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory Manager](https://mlsanity.com/paper/2508.11416/) (2025) - [PPI-SVRG: Unifying Prediction-Powered Inference and Variance Reduction for Semi-Supervised Optimization](https://mlsanity.com/paper/2601.21470/) (2026) - [Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management](https://mlsanity.com/paper/2510.03310/) (2025) - [ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research](https://mlsanity.com/paper/2601.21008/) (2026) ## Built on by (most cited first, 5 of 5) - [The Value of Information in Resource-Constrained Pricing](https://mlsanity.com/paper/2603.24974/) (2026) - [Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers](https://mlsanity.com/paper/2604.11507/) (2026) - [YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate](https://mlsanity.com/paper/2607.09706/) (2026) - [TACIT: Optimization Models that Learn from Their Mistakes](https://mlsanity.com/paper/2609.38434/) (2026) - [OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework](https://mlsanity.com/paper/2610.00912/) (2026) ## Abstract (arXiv) Supply chain optimization models frequently become infeasible because of modeling errors. Diagnosis and repair require scarce OR expertise: analysts must interpret solver diagnostics, trace root causes across echelons, and fix formulations without sacrificing operational soundness. Whether AI agents can perform this task remains untested. We decompose this task into two phases: a domain-agnostic feasibility phase that iteratively repairs any LP using IIS-guided diagnosis, and a domain-specific validation phase that enforces five rationality checks grounded in inventory theory. We test 22 API models from seven families on 976 multi-echelon supply chain problems and train two 8B-parameter models with self-taught reasoning and solver-verified rewards. The trained models reach 81.7% Rational Recovery Rate (RRR) -- the fraction of problems resolved to both feasibility and operational rationality -- versus 42.2% for the best API model and 21.3% on average. The gap concentrates in Phase 1 repair, where API models average 27.6% recovery rate versus 97.2% for trained models. Two gaps separate current AI from reliable model repair: solver interaction, as API models restore only 27.6% of infeasible formulations; and operational rationale, as roughly one in four feasible repairs violate supply chain theory. Each gap requires a different intervention -- targeted training closes the solver interaction gap, while explicit specification as solver-verifiable checks closes the rationality gap. For organizations adopting AI in operational planning, formalizing what 'rational' means in their context is the higher-return investment.