MLEvolve 解决了现有 MLE 智能体在长周期任务中信息隔离、无记忆搜索和缺乏分层控制的问题，做自动化机器学习算法发现的团队可以直接用它来加速实验迭代，值得关注。
MLEvolve 是一个基于大语言模型的自进化多智能体框架，用于端到端的机器学习算法自动发现。它通过 Progressive MCGS 扩展树搜索，利用图参考边实现跨分支信息流动，并采用熵驱动的渐进调度从广泛探索转向聚焦利用。引入的 Retrospective Memory 结合冷启动领域知识库和动态全局记忆，支持任务特定经验的检索与复用。在 MLE-Bench 评估中，MLEvolve 在 12 小时预算（标准运行时的一半）下，平均奖牌率和有效提交率等多个维度达到最先进水平，并在数学算法优化任务上超越 AlphaEvolve 等专门方法。
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution becomes a key capability. However, existing MLE agents suffer from inter-branch information isolation, memoryless search, and lack of hierarchical control, which together hinder long-horizon optimization. We present MLEvolve, an LLM-based self-evolving multi-agent framework for end-to-end machine learning algorithm discovery. By extending tree search to Progressive MCGS, MLEvolve enables cross-branch information flow through graph-based reference edges and gradually shifts the search from broad exploration to focused exploitation with an entropy-inspired progressive schedule. To allow the agent to evolve with accumulated experience, we introduce Retrospective Memory, which combines a cold-start domain knowledge base with a dynamic global memory for task-specific experience retrieval and reuse. For stable long-horizon iteration, we further decouple strategic planning from code generation with adaptive coding modes. Evaluation on MLE-Bench shows that MLEvolve achieves state-of-the-art performance across multiple dimensions including average medal rate and valid submission rate under a 12-hour budget (half the standard runtime). Moreover, MLEvolve also outperforms specialized algorithm discovery methods including AlphaEvolve on mathematical algorithm optimization tasks, demonstrating strong cross-domain generalization. Our code is available at https://github.com/InternScience/MLEvolve.