# OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

arXiv: https://arxiv.org/abs/2503.10009 · HTML: https://mlsanity.com/paper/2503.10009/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 9 of 9)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [Cardinal Optimizer (COPT) User Guide](https://mlsanity.com/paper/2208.14314/) (2022)

## Built on by (most cited first, 15 of 15)

- [Strategy-Aware Optimization Modeling with Reasoning LLMs](https://mlsanity.com/paper/2605.02545/) (2026)
- [ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling](https://mlsanity.com/paper/2605.02728/) (2026)
- [TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling](https://mlsanity.com/paper/2605.23966/) (2026)
- [OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents](https://mlsanity.com/paper/2605.28158/) (2026)
- [Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems](https://mlsanity.com/paper/2607.10768/) (2026)
- [Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization](https://mlsanity.com/paper/2508.18091/) (2025)
- [Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization](https://mlsanity.com/paper/2605.21751/) (2026)
- [ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?](https://mlsanity.com/paper/2606.19787/) (2026)
- [From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience](https://mlsanity.com/paper/2604.11041/) (2026)
- [PARM: Pipeline-Adapted Reward Model](https://mlsanity.com/paper/2604.18327/) (2026)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)
- [ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience](https://mlsanity.com/paper/2606.10359/) (2026)
- [Large Language Models as Optimizers: A Survey of Direct vs. Tool-Augmented Approaches and Their Performance Frontiers](https://mlsanity.com/paper/2606.15577/) (2026)
- [Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process](https://mlsanity.com/paper/2608.00015/) (2026)
- [Learning to Optimize through Solver-Grounded Self-Play](https://mlsanity.com/paper/2609.34205/) (2026)

## Abstract (arXiv)

With the rise of artificial intelligence (AI), applying large language models (LLMs) to mathematical problem-solving has attracted increasing attention. Most existing approaches attempt to improve Operations Research (OR) optimization problem-solving through prompt engineering or fine-tuning strategies for LLMs. However, these methods are fundamentally constrained by the limited capabilities of non-reasoning LLMs. To overcome these limitations, we propose OR-LLM-Agent, an AI agent framework built on reasoning LLMs for automated OR problem solving. The framework decomposes the task into three sequential stages: mathematical modeling, code generation, and debugging. Each task is handled by a dedicated sub-agent, which enables more targeted reasoning. We also construct BWOR, an OR dataset for evaluating LLM performance on OR tasks. Our analysis shows that in the benchmarks NL4OPT, MAMO, and IndustryOR, reasoning LLMs sometimes underperform their non-reasoning counterparts within the same model family. In contrast, BWOR provides a more consistent and discriminative assessment of model capabilities. Experimental results demonstrate that OR-LLM-Agent utilizing DeepSeek-R1 in its framework outperforms advanced methods, including GPT-o3, Gemini 2.5 Pro, DeepSeek-R1, and ORLM, by at least 7% in accuracy. These results demonstrate the effectiveness of task decomposition for OR problem solving.