合成沙盒用于训练机器学习工程代理
Synthetic Sandbox for Training Machine Learning Engineering Agents
AI总结：
本文提出SandMLE框架，通过生成多样化的合成机器学习工程环境，显著提升机器学习工程代理的训练效率，实现大规模在线策略学习，并在多个基准测试中取得显著性能提升。
摘要：
本文提出SandMLE框架，通过生成多样化的合成机器学习工程环境，显著提升机器学习工程代理的训练效率，实现大规模在线策略学习，并在多个基准测试中取得显著性能提升。
英文摘要：
As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via fast-executing unit tests, MLE verification requires running full ML pipelines -- data preprocessing, model training, and metric evaluation -- on large datasets at each rollout step, rendering trajectory-wise on-policy reinforcement learning (RL) prohibitively slow. Existing approaches retreat to supervised fine-tuning (SFT) or offline proxy rewards, sacrificing the exploration and generalization benefits of on-policy RL. We observe that sandbox data size is the primary source of this bottleneck. Based on this insight, we introduce SandMLE, a multi-agent framework that generates diverse, verifiable synthetic MLE environments from a small number of seed tasks, preserving the structural and technical complexity of real-world problems while constraining datasets to micro-scale (each task is paired with only 50-200 training samples). Through extensive experiments, we show that SandMLE reduces execution time by over 13 times, enabling large-scale, on-policy trajectory-wise RL for the first time in the MLE domain. On MLE-bench-lite, SandMLE yields significant gains over SFT baselines across Qwen3-8B, 14B, and 30B-A3B, with relative medal rate improvements ranging from 20.3% to 66.9%. Furthermore, the trained policy generalizes across unseen agentic scaffolds, achieving up to 32.4% better HumanRank score on MLE-Dojo.
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。
