ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling

• URL: http://arxiv.org/abs/2605.02728v1
• Date: Mon, 04 May 2026 15:28:10 GMT
• Title: ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling
• Abstract summary: ORPilot is an agentic AI system that translates real-world business problems into solver-ready optimization models.<n>It represents the first attempt to target production-level business problems rather than textbook operations research (OR) cases.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents ORPilot, an open-source agentic AI system that translates real-world business problems into solver-ready optimization models. Unlike academic LLM-for-OR tools that assume clean problem specifications with preformatted inline data, ORPilot is designed for production conditions: ambiguous descriptions, large-scale raw operational data, and the need for portability across solver backends. The system introduces four novel components: (1) a conversational interview agent to elicit complete problem specifications, (2) a data collection agent that retrieves data independently of prompts, (3) a parameter computation agent to bridge raw tabular data and model-ready parameters, and (4) a solver-agnostic Intermediate Representation (IR) for deterministic, zero-LLM-call recompilation to Gurobi, CPLEX, PuLP, Pyomo, or OR-Tools solvers. Additionally, self-correcting retry loops utilize solver tracebacks for targeted repairs. ORPilot represents the first attempt to target production-level business problems rather than textbook operations research (OR) cases. Evaluation on real-world problems demonstrates promising results. When tested against traditional academic benchmarks: IndustryOR, NL4OPT and NLP4LP, ORPilot outperformed state-of-the-art tools in accuracy on the IndustryOR benchmark and delivered comparable performance on NL4OPT and NLP4LP.

Related papers

• From Data to Action: Accelerating Refinery Optimization with AI [0.0]
  Refinery optimization utilizes sheer amounts of data, which can be handled with modern Linear Programming (LP) software.<n>Anomaly Detection tools are proposed to be used in tandem with the LP output.<n>New methods are proposed to handle high-dimensional data: choosing the most informative pairs.
  arXiv  Detail & Related papers  (2026-05-14T17:07:41Z)
• Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers [52.23061619664667]
  Large Language Models (LLMs) struggle to solve complex problems through direct reasoning, so recent neuro-symbolic systems increasingly use them to synthesize executable solvers.<n>We introduce CP-SynC-XL, a benchmark of 100 problems (4,577 instances), and evaluate three solver--construction paradigms: native algorithmic search (Python), constraint modeling through a Python solver API (Python + OR-Tools), and declarative constraint modeling.
  arXiv  Detail & Related papers  (2026-05-12T17:15:45Z)
• AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems [54.593031581486116]
  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.
  arXiv  Detail & Related papers  (2026-04-18T03:24:54Z)
• Execution-Verified Reinforcement Learning for Optimization Modeling [49.171122807323634]
  Execution-verified learning framework treats a mathematical programming solver as a deterministic, interactive verifier.<n>Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT.
  arXiv  Detail & Related papers  (2026-04-01T03:39:11Z)
• MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research [15.28095645151852]
  MIRROR is a fine-tuning-free, end-to-end multi-agent framework for operations research.<n>It translates natural language optimization problems into mathematical models and solver code.<n>Experiments show that MIRROR outperforms existing methods on standard Operations Research benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T09:46:56Z)
• OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models [3.7202906625021934]
  Large language models (LLMs) demonstrate strong mathematical reasoning.<n>We introduce OR-Toolformer, which fine-tunes Llama-3.1-8B-Instruct with a semi-automatic data synthesis pipeline.<n>On three of four standard benchmarks, OR-Toolformer achieves up to 80.1% execution accuracy.
  arXiv  Detail & Related papers  (2025-09-24T14:42:40Z)
• SciML Agents: Write the Solver, Not the Solution [69.5021018644143]
  We introduce two new datasets: a diagnostic dataset of adversarial "misleading" problems; and a large-scale benchmark of 1,000 diverse ODE tasks.<n>We evaluate open- and closed-source LLM models along two axes: (i) unguided versus guided prompting with domain-specific knowledge; and (ii) off-the-shelf versus fine-tuned variants.<n>Preliminary results indicate that careful prompting and fine-tuning can yield a specialized LLM agent capable of reliably solving simple ODE problems.
  arXiv  Detail & Related papers  (2025-09-12T02:53:57Z)
• GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics [9.549568621873386]
  GateLens is an LLM-based system for analyzing data in the automotive domain.<n>Unlike traditional multi-agent or planning-based systems that can be slow, opaque, and costly to maintain, GateLens emphasizes speed, transparency, and reliability.
  arXiv  Detail & Related papers  (2025-03-27T17:48:32Z)
• GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration [31.07238612043854]
  GraphTeam consists of five LLM-based agents from three modules, and the agents with different specialities can collaborate to address complex problems.<n>Experiments on six graph analysis benchmarks demonstrate that GraphTeam achieves state-of-the-art performance with an average 25.85% improvement over the best baseline in terms of accuracy.
  arXiv  Detail & Related papers  (2024-10-23T17:02:59Z)
• OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling [62.19438812624467]
  Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning.<n>We propose OptiBench, a benchmark for End-to-end optimization problem-solving with human-readable inputs and outputs.
  arXiv  Detail & Related papers  (2024-07-13T13:27:57Z)
• MLLM-DataEngine: An Iterative Refinement Approach for MLLM [62.30753425449056]
  We propose a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data. For quality, we resort to GPT-4 to generate high-quality data with each given data type.
  arXiv  Detail & Related papers  (2023-08-25T01:41:04Z)
• Bandit Data-Driven Optimization [62.01362535014316]
  There are four major pain points that a machine learning pipeline must overcome in order to be useful in settings. We introduce bandit data-driven optimization, the first iterative prediction-prescription framework to address these pain points. We propose PROOF, a novel algorithm for this framework and formally prove that it has no-regret.
  arXiv  Detail & Related papers  (2020-08-26T17:50:49Z)

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.