AutoMLGen：导航编码代理的细粒度优化
AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
AI总结：
AutoMLGen提出结合领域知识库与蒙特卡洛图搜索的编码代理，解决LLM在AutoML等任务中缺乏细粒度先验和搜索多样性不足的问题，在MLE-Bench上以半预算实现SOTA性能。
摘要：
大型语言模型（LLMs）在一般编程任务中表现出色。然而，在机器学习工程（MLE）场景中，如AutoML和Kaggle竞赛，实现高性能在很大程度上依赖于专家干预和反复调整，而非仅仅生成正确的代码。当直接应用于这些任务时，LLMs往往缺乏细粒度的领域先验知识，而现有的MLE方法使用线性或树状结构搜索，限制了知识向相邻层级链接的传递。因此，它们无法利用过去的完整轨迹或在分支间共享信息，限制了自我进化能力和搜索空间多样性。为解决这些局限性，我们引入了AutoMLGen，一个基于LLM的编码代理，它集成了领域知识库以提供高质量的先验指导，并采用蒙特卡洛图搜索（MCGS）进行高效探索。MCGS保留了MCTS的树引导探索，同时在扩展阶段嵌入图结构，以实现动态路径重组、历史轨迹重用和多解决方案融合，从而支持自我进化和协作学习。结合细粒度的算子集，这种设计提高了稳定性并加速了收敛。在MLE-Bench上的评估表明，AutoMLGen在12小时预算（标准运行时间的一半）下，在平均奖牌率和有效提交率等多个维度上达到了最先进的性能。代码可在https://github.com/Alpha-Innovator/InternAgent获取。
英文摘要：
Large language models (LLMs) have shown impressive performance in general programming tasks. However, in Machine Learning Engineering (MLE) scenarios such as AutoML and Kaggle competitions, achieving high performance depends heavily on expert intervention and repeated adjustments rather than simply generating correct code. When applied directly to these tasks, LLMs often lack fine-grained domain priors, and existing MLE approaches that use linear or tree-structured searches limit knowledge transfer to adjacent hierarchical links. As a result, they cannot leverage past full trajectories or share information across branches, limiting self-evolving ability and search space diversity. To address these limitations, we introduce AutoMLGen, an LLM-based coding agent that integrates a domain knowledge base for high-quality prior guidance and Monte Carlo Graph Search (MCGS) for efficient exploration. MCGS retains the tree-guided exploration of MCTS while embedding a graph structure into the expansion stage to enable dynamic path reorganization, historical trajectory reuse, and multi-solution fusion to support both self-evolution and collaborative learning. Combined with fine-grained operator sets, this design improves stability and accelerates convergence. Evaluation on the MLE-Bench shows that AutoMLGen achieves state-of-the-art performance in numerous dimensions, such as the average medal rate and the valid submission rate, under a 12-hour budget (half the standard runtime). The code is available at https://github.com/Alpha-Innovator/InternAgent.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
