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

• URL: http://arxiv.org/abs/2604.16804v1
• Date: Sat, 18 Apr 2026 03:24:54 GMT
• Title: AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems
• Abstract summary: We present AutoOR, a scalable synthetic data generation and reinforcement learning pipeline that trains LLMs to autoformalize optimization problems specified in natural language.<n>AutoOR generates verified training data from standard optimization forms and uses solver execution feedback as the reward signal for RL post-training.<n>We believe that methods such as AutoOR can significantly accelerate industrial decision-making with AI.
• Score: 54.593031581486116
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Optimization problems are central to decision-making in manufacturing, logistics, scheduling, and other industrial settings. Translating complicated descriptions of these problems into solver-ready formulations requires specialized operations research (OR) expertise, making it hard to scale. We present AutoOR, a scalable synthetic data generation and reinforcement learning pipeline that trains LLMs to autoformalize optimization problems specified in natural language across linear, mixed-integer, and non-linear categories. AutoOR generates verified training data from standard optimization forms and uses solver execution feedback as the reward signal for RL post-training. AutoOR applied to an 8B model achieves state-of-the-art or competitive results across six established OR benchmarks, matching significantly larger frontier models. For a non-linear problem class involving physical dynamics, where frontier models score near 0%, we introduce a curriculum RL strategy that bootstraps from limited initial training data to make this class tractable for post-training. We believe that methods such as AutoOR can significantly accelerate industrial decision-making with AI.

Related papers

• FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization [61.43300970020897]
  Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation.<n>Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity.<n>We introduce FrontierOR, among the first benchmarks to evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems.
  arXiv  Detail & Related papers  (2026-05-24T20:10:42Z)
• Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization [15.738083856839749]
  We train custom Transformer-based policies using offline reinforcement learning on detailed historical state representations.<n>We explore LLMs operating on abstracted, human-readable state descriptions.<n>Our findings demonstrate that both approaches offer viable paths toward AI-assisted operational decision-making.
  arXiv  Detail & Related papers  (2026-03-25T23:56:25Z)
• Automated Optimization Modeling via a Localizable Error-Driven Perspective [20.591721861026414]
  We propose a novel error-driven learning framework for automated optimization modeling.<n>MIND customized the whole model training framework from data synthesis to post-training.<n>MIND consistently outperforms all the state-of-the-art automated optimization modeling approaches.
  arXiv  Detail & Related papers  (2026-01-17T09:59:01Z)
• DiRL: An Efficient Post-Training Framework for Diffusion Language Models [54.405206032785706]
  Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models.<n>Existing methods suffer from computational inefficiency and objective mismatches between training and inference.<n>We introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference.
  arXiv  Detail & Related papers  (2025-12-23T08:33:19Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling [3.253908111652627]
  Large Language Models (LLMs) often struggle to generate formally correct and usable models against hallucinations.<n>We present a novel framework that significantly improves the authenticity of LLMs for optimization modeling using Reinforcement Learning with Verifiable Reward.
  arXiv  Detail & Related papers  (2025-05-17T02:32:03Z)
• ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling [15.67321902882617]
  We propose a viable path for training open-source LLMs capable of optimization modeling and developing solver codes.<n>This work also introduces IndustryOR, the first industrial benchmark for evaluating LLMs in solving practical OR problems.
  arXiv  Detail & Related papers  (2024-05-28T01:55:35Z)
• Learning-enabled Flexible Job-shop Scheduling for Scalable Smart Manufacturing [11.509669981978874]
  In smart manufacturing systems, flexible job-shop scheduling with transportation constraints is essential to optimize solutions for maximizing productivity. Recent developments in deep reinforcement learning (DRL)-based methods for FJSPT have encountered a scale generalization challenge. We introduce a novel graph-based DRL method, named the Heterogeneous Graph Scheduler (HGS)
  arXiv  Detail & Related papers  (2024-02-14T06:49:23Z)
• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning [50.9692060692705]
  This paper introduces $textbfLanguage Models for $textbfMo$tion Control ($textbfLaMo$), a general framework based on Decision Transformers for offline RL.<n>Our framework highlights four crucial components:.<n>Initializing Decision Transformers with sequentially pre-trained LMs, (2) employing the LoRA fine-tuning method,.<n>In particular, our method demonstrates superior performance in scenarios with limited data samples.
  arXiv  Detail & Related papers  (2023-10-31T16:24:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.