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

• URL: http://arxiv.org/abs/2505.14148v1
• Date: Tue, 20 May 2025 09:55:31 GMT
• Title: MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem
• Abstract summary: We formalize the task of Large Language Models (LLMs)-powered real-world mathematical modeling.<n>We propose MM-Agent, an expert-inspired framework that decomposes modeling into four stages: open-ended problem analysis, structured model formulation, computational problem solving, and report generation.<n> MM-Agent significantly outperforms baseline agents, achieving an 11.88% improvement over human expert solutions.
• Score: 11.81434494801394
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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 (\textbf{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

Related papers

• MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research [62.221184989046826]
  MathCoPilot is a human-in-the-loop system that embodies a new human--AI symbiotic paradigm for mathematical research.<n>MathCoPilot unifies three core capabilities: an interactive proof blueprint that decomposes a proof into navigable steps the human can directly inspect, direct, and refine; automated proving skill orchestration with adaptive knowledge base search and Lean-integrated iterative verification; and topic-driven paper retrieval and automated formalization into a verified Lean knowledge base.
  arXiv  Detail & Related papers  (2026-07-16T05:22:40Z)
• From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier [109.93387172162984]
  We argue that the next leap in AI4Math systems requires a decisive shift from predefined problem-solvers to research agents.<n>We provide a systematic review of the field, covering datasets, auto-formalization, and proof synthesis.
  arXiv  Detail & Related papers  (2026-07-08T17:46:36Z)
• MechMath Agent Team: LLM Driven Agents for Mathematical Research [17.23955320294417]
  MechMath Agent Team (MMAT) is a large language model driven agent designed to serve as a co-pilot throughout the full cycle of mathematical research.<n>We design a tripartite Harness Architecture that decouples system responsibilities into Control, Execution, and Augmentation planes.<n>We evaluate MMAT on open problems in Number Theory, Algebraic Complexity Theory, Differential Algebra, Operator Algebra, and Inequalities.
  arXiv  Detail & Related papers  (2026-07-05T16:37:40Z)
• From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics [79.81905350372067]
  We study gap through contextual mathematical reasoning.<n>We introduce ContextMATH, a benchmark that repurposes AIME and MATH-500 problems into two contextual settings.<n>Open-source models decline by 13 and 34 points on SG and CS, while proprietary models drop by 13 and 20.
  arXiv  Detail & Related papers  (2026-01-30T14:56:04Z)
• Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics [25.762535169301984]
  We introduce Numina-Lean-Agent, which combines Claude Code with Numina-Lean-MCP to enable autonomous interaction with Lean.<n>Using Claude Opus 4.5 as the base model, Numina-Lean-Agent solves all problems in Putnam 2025 (12 / 12), matching the best closed-source system.
  arXiv  Detail & Related papers  (2026-01-20T14:51:45Z)
• MMFormalizer: Multimodal Autoformalization in the Wild [79.24853896733154]
  MMFormalizer extends autoformalization beyond text by integrating adaptive grounding with entities from real-world mathematical and physical domains.<n>We evaluate MMFormalizer on a new benchmark, PhyX-AF, comprising 115 curated samples from MathVerse, PhyX, Synthetic Geometry, and Analytic Geometry.<n>Results show GPT-5 and Gemini-3-Pro achieve the highest compile and semantic accuracy, with GPT-5 excelling in physical reasoning.
  arXiv  Detail & Related papers  (2026-01-06T13:42:51Z)
• Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning [66.79506488139707]
  Large language model (LLM) agents exhibit strong mathematical problem-solving abilities.<n>In this work, we make the first attempt to build a medalist-level LLM agent for geometry and present InternGeometry.<n> InternGeometry overcomes the limitations in geometry by iteratively proposing propositions and auxiliary constructions, verifying them with a symbolic engine.<n>Built on InternThinker-32B, InternGeometry solves 44 of 50 IMO geometry problems, exceeding the average gold medalist score (40.9), using only 13K training examples.
  arXiv  Detail & Related papers  (2025-12-11T11:05:04Z)
• ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges [72.19809898215857]
  We introduce ModelingBench, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains.<n>These tasks require translating natural language into formal mathematical formulations, applying appropriate tools, and producing structured, defensible reports.<n>We also present ModelingAgent, a multi-agent framework that coordinates tool use, supports structured, creative solutions, and generates well-grounded, creative solutions.
  arXiv  Detail & Related papers  (2025-05-21T03:33:23Z)
• MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection [53.325457460187046]
  We introduce MathAgent, a novel Mixture-of-Math-Agent framework designed specifically to address these challenges.<n>MathAgent decomposes error detection into three phases, each handled by a specialized agent.<n>We evaluate MathAgent on real-world educational data, demonstrating approximately 5% higher accuracy in error step identification.
  arXiv  Detail & Related papers  (2025-03-23T16:25:08Z)
• MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task [49.355810887265925]
  We introduce MathFimer, a novel framework for mathematical reasoning step expansion.<n>We develop a specialized model, MathFimer-7B, on our carefully curated NuminaMath-FIM dataset.<n>We then apply these models to enhance existing mathematical reasoning datasets by inserting detailed intermediate steps into their solution chains.
  arXiv  Detail & Related papers  (2025-02-17T11:22:24Z)
• ProcessBench: Identifying Process Errors in Mathematical Reasoning [62.80402845414901]
  We introduce ProcessBench for measuring the ability to identify erroneous steps in mathematical reasoning.<n>ProcessBench consists of 3,400 test cases, primarily focused on competition- and Olympiad-level math problems.<n>We conduct extensive evaluation on ProcessBench, involving two types of models: process reward models (PRMs) and critic models.
  arXiv  Detail & Related papers  (2024-12-09T15:11:40Z)
• LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages [14.04286044600141]
  Large Language Models (LLMs) have demonstrated strong performance across various natural language processing tasks.<n>But their proficiency in mathematical reasoning remains a key challenge.<n>We propose a process-oriented framework to evaluate LLMs' ability to construct mathematical models.
  arXiv  Detail & Related papers  (2024-05-21T18:29:54Z)
• Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent [15.81048994298046]
  Large language models (LLMs) face challenges in solving complex mathematical problems. We propose a formal description of the mathematical solving and extend LLMs with an agent-based zero-shot framework. Experiments on miniF2F and MATH have demonstrated the effectiveness of PRER and proposed MathAgents.
  arXiv  Detail & Related papers  (2023-12-14T13:33:50Z)
• JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving [77.51817534090789]
  We propose textbfJiuZhang2.0, a unified Chinese PLM specially for multi-task mathematical problem solving. Our idea is to maintain a moderate-sized model and employ the emphcross-task knowledge sharing to improve the model capacity in a multi-task setting.
  arXiv  Detail & Related papers  (2023-06-19T15:45:36Z)
• UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression [127.68780714438103]
  Two main geometry problems: calculation and proving, are usually treated as two specific tasks. We construct a large-scale Unified Geometry problem benchmark, UniGeo, which contains 4,998 calculation problems and 9,543 proving problems. We also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously.
  arXiv  Detail & Related papers  (2022-12-06T04:37:51Z)

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.