Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?

2026-03-03

AI Summary

This work addresses the scarcity of high-quality, challenging mathematical problems that hinders the training and evaluation of large language models by proposing an automated problem evolution framework based on multi-agent collaboration. The approach leverages large language model–driven code agents that autonomously explore within an executable environment to transform existing mathematical problems into novel, more difficult, yet solvable ones. A solvability verification and difficulty assessment mechanism ensures the quality of the generated problems. Experimental results demonstrate that the evolved problems significantly increase in difficulty while remaining solvable, thereby validating the effectiveness and novelty of code-driven multi-agent systems for scalable generation of high-difficulty mathematical problems.

Technology Category

• Multiagent Systems: Distributed Problem Solving
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Evolutionary Learning

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code agents have demonstrated sophisticated skills in agentic coding and reasoning, suggesting that code execution can serve as a scalable environment for mathematical experimentation. In this paper, we investigate the potential of code agents to autonomously evolve existing math problems into more complex variations. We introduce a multi-agent framework designed to perform problem evolution while validating the solvability and increased difficulty of the generated problems. Our experiments demonstrate that, given sufficient test-time exploration, code agents can synthesize new, solvable problems that are structurally distinct from and more challenging than the originals. This work provides empirical evidence that code-driven agents can serve as a viable mechanism for synthesizing high-difficulty mathematical reasoning problems within scalable computational environments. Our data is available at https://github.com/TarferSoul/Code2Math.

Problem

• mathematical problem generation
• code agents
• problem evolution
• high-difficulty problems
• scalable mathematical reasoning

Innovation

• code agents
• problem evolution
• mathematical reasoning
• multi-agent framework
• automated problem synthesis