用大模型驱动多智能体系统，全自动处理多模态机器学习任务
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
- 基于大模型的多智能体框架，自动完成从数据到模型的全流程
- 在25项多模态任务中成功率达92%，比竞品高263.6%
- 仅用80亿参数模型就超越全尺寸现有系统，适合低资源场景
现有AutoML系统虽已实现部分自动化，但在处理多模态数据时仍需大量人工配置与专家干预。我们提出MLZero，一种基于大语言模型（LLM）的新型多智能体框架，可在多种数据模态下实现端到端机器学习自动化，几乎无需人工参与。首先通过认知感知模块将原始多模态输入转化为感知上下文，有效引导后续流程。为克服LLM常见问题如代码幻觉和过时API知识，我们引入语义与情景记忆增强迭代式代码生成。在MLE-Bench Lite上，MLZero在成功率和解决方案质量上均优于所有对手，斩获六枚金牌。在包含25个更复杂任务的多模态AutoML代理基准测试中，其成功率高达0.92（较竞品提升263.6%），平均排名2.28。该方法即使使用小型8B LLM也表现出强大性能，优于现有大型系统。
原文摘要 · Abstract (English)
Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when handling multimodal data. We introduce MLZero, a novel multi-agent framework powered by Large Language Models (LLMs) that enables end-to-end ML automation across diverse data modalities with minimal human intervention. A cognitive perception module is first employed, transforming raw multimodal inputs into perceptual context that effectively guides the subsequent workflow. To address key limitations of LLMs, such as hallucinated code generation and outdated API knowledge, we enhance the iterative code generation process with semantic and episodic memory. MLZero demonstrates superior performance on MLE-Bench Lite, outperforming all competitors in both success rate and solution quality, securing six gold medals. Additionally, when evaluated on our Multimodal AutoML Agent Benchmark, which includes 25 more challenging tasks spanning diverse data modalities, MLZero outperforms the competing methods by a large margin with a success rate of 0.92 (+263.6\%) and an average rank of 2.28. Our approach maintains its robust effectiveness even with a compact 8B LLM, outperforming full-size systems from existing solutions.
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。