AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems

AutoOR is a scalable synthetic data generation and reinforcement learning pipeline that trains large language models to autoformalize operations research problems expressed in natural language across linear, mixed‑integer, and non‑linear categories. By generating verified training data from standard optimization forms and using solver execution feedback as a reward signal, AutoOR enables post‑training of an 8B model to achieve state‑of‑the‑art or competitive results on six established OR benchmarks, matching significantly larger frontier models. For non‑linear problems involving physical dynamics, a curriculum RL strategy bootstraps from limited initial data, making this class tractable for post‑training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• reinforcement-learning
• benchmarks