MARS让AI自动研究更智能，能省成本还学会跨路径举一反三。
MARS: Modular Agent with Reflective Search for Automated AI Research
- 用带预算约束的搜索规划，平衡效果与计算开销
- 在MLE-Bench上表现超越开源框架，接近顶尖方法
- 63%的教训来自不同路径间的知识迁移，泛化能力强
自动化人工智能研究的关键瓶颈在于复杂机器学习工程（MLE）任务的执行。与通用软件工程不同，MLE具有计算成本高（如模型训练）和性能归因不透明的特点。现有基于大模型的代理常生成单一脚本，忽略执行成本和因果因素。我们提出MARS（模块化反射搜索智能体），专为自主AI研究优化。MARS基于三大支柱：(1) 基于成本约束蒙特卡洛树搜索（MCTS）的预算感知规划，显式权衡性能与执行开销；(2) 模块化构建，采用“设计-分解-实现”流程管理复杂研究仓库；(3) 对比反思记忆，通过分析解决方案差异提炼高信噪比洞察。MARS在同等条件下于MLE-Bench上达到开源框架最先进水平，竞争力媲美全球榜单顶级方法。此外，系统展现出定性“顿悟”时刻，其中63%所用经验源自跨分支迁移，表明代理能有效泛化不同搜索路径中的洞察。
原文摘要 · Abstract (English)
A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often generating monolithic scripts that ignore execution costs and causal factors. We introduce MARS (Modular Agent with Reflective Search), a framework optimized for autonomous AI research. MARS relies on three pillars: (1) Budget-Aware Planning via cost-constrained Monte Carlo Tree Search (MCTS) to explicitly balance performance with execution expense; (2) Modular Construction, employing a "Design-Decompose-Implement" pipeline to manage complex research repositories; and (3) Comparative Reflective Memory, which addresses credit assignment by analyzing solution differences to distill high-signal insights. MARS achieves state-of-the-art performance among open-source frameworks on MLE-Bench under comparable settings, maintaining competitiveness with the global leaderboard's top methods. Furthermore, the system exhibits qualitative "Aha!" moments, where 63% of all utilized lessons originate from cross-branch transfer, demonstrating that the agent effectively generalizes insights across search paths.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。