Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.19439v1</id>\n    <title>OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents</title>\n    <updated>2026-02-23T02:19:05Z</updated>\n    <link href='https://arxiv.org/abs/2602.19439v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.19439v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Problem Definition. 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.\n  Methodology/Results. OptiRepair splits this task into a domain-agnostic feasibility phase (iterative IIS-guided repair of any LP) and a domain-specific validation phase (five rationality checks grounded in inventory theory). We test 22 API models from 7 families on 976 multi-echelon supply chain problems and train two 8B-parameter models using self-taught reasoning with 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: API models average 27.6% recovery rate versus 97.2% for trained models.\n  Managerial Implications. Two gaps separate current AI from reliable model repair: solver interaction (API models restore only 27.6% of infeasible formulations) and operational rationale (roughly one in four feasible repairs violate supply chain theory). Each requires a different intervention: solver interaction responds to targeted training; operational rationale requires explicit specification as solver-verifiable checks. For organizations adopting AI in operational planning, formalizing what \"rational\" means in their context is the higher-return investment.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.OC'/>\n    <published>2026-02-23T02:19:05Z</published>\n    <arxiv:comment>34 pages, 8 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Ruicheng Ao</name>\n    </author>\n    <author>\n      <name>David Simchi-Levi</name>\n    </author>\n    <author>\n      <name>Xinshang Wang</name>\n    </author>\n  </entry>"
}