# MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

arXiv: https://arxiv.org/abs/2505.14148 · HTML: https://mlsanity.com/paper/2505.14148/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 3 of its 68 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 3 of 3)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)

## Built on by (most cited first, 25 of 25)

- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models](https://mlsanity.com/paper/2512.24618/) (2025)
- [ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modeling](https://mlsanity.com/paper/2510.27610/) (2025)
- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition](https://mlsanity.com/paper/2510.15280/) (2025)
- [PRInTS: Reward Modeling for Long-Horizon Information Seeking](https://mlsanity.com/paper/2511.19314/) (2025)
- [Agent-Omit: Adaptive Context Omission for Efficient LLM Agents](https://mlsanity.com/paper/2602.04284/) (2026)
- [ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generation](https://mlsanity.com/paper/2511.17689/) (2025)
- [MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research](https://mlsanity.com/paper/2602.03318/) (2026)
- [FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data](https://mlsanity.com/paper/2510.25223/) (2025)
- [ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis](https://mlsanity.com/paper/2604.16922/) (2026)
- [EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management](https://mlsanity.com/paper/2606.03841/) (2026)
- [An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigation](https://mlsanity.com/paper/2510.07825/) (2025)
- [Large Language Model-Assisted Planning of Electric Vehicle Charging Infrastructure with Real-World Case Study](https://mlsanity.com/paper/2511.19055/) (2025)
- [EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions](https://mlsanity.com/paper/2605.02289/) (2026)
- [Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models](https://mlsanity.com/paper/2605.11813/) (2026)
- [PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language](https://mlsanity.com/paper/2607.18256/) (2026)
- [FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving](https://mlsanity.com/paper/2608.25220/) (2026)
- [Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science](https://mlsanity.com/paper/2602.05289/) (2026)
- [How Far Are We? Systematic Evaluation of LLMs vs. Human Experts in Mathematical Contest in Modeling](https://mlsanity.com/paper/2604.04791/) (2026)
- [Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving](https://mlsanity.com/paper/2604.20183/) (2026)
- [Large language models for partial differential equation workflows](https://mlsanity.com/paper/2608.03600/) (2026)
- [From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities](https://mlsanity.com/paper/2608.26950/) (2026)
- [Benchmarking Language Models for Statistical Problem Formulation](https://mlsanity.com/paper/2609.01982/) (2026)
- [Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations](https://mlsanity.com/paper/2609.03860/) (2026)

## Abstract (arXiv)

Mathematical modeling is a cornerstone of scientific discovery and engineering practice, enabling the translation of real-world problems into formal systems across domains such as physics, biology, and economics. Unlike mathematical reasoning, which assumes a predefined formulation, modeling requires open-ended problem analysis, abstraction, and principled formalization. While Large Language Models (LLMs) have shown strong reasoning capabilities, they fall short in rigorous model construction, limiting their utility in real-world problem-solving. To this end, we formalize the task of LLM-powered real-world mathematical modeling, where agents must analyze problems, construct domain-appropriate formulations, and generate complete end-to-end solutions. We introduce MM-Bench, a curated benchmark of 111 problems from the Mathematical Contest in Modeling (MCM/ICM), spanning the years 2000 to 2025 and across ten diverse domains such as physics, biology, and economics. To tackle this task, we propose MM-Agent, an expert-inspired framework that decomposes mathematical modeling into four stages: open-ended problem analysis, structured model formulation, computational problem solving, and report generation. Experiments on MM-Bench show that MM-Agent significantly outperforms baseline agents, achieving an 11.88% improvement over human expert solutions while requiring only 15 minutes and 0.88 per task using GPT-4o. Furthermore, under official MCM/ICM protocols, MM-Agent assisted two undergraduate teams in winning the Finalist Award (top 2.0% among 27,456 teams) in MCM/ICM 2025, demonstrating its practical effectiveness as a modeling copilot. Our code is available at https://github.com/usail-hkust/LLM-MM-Agent