A Multi-Agent Framework for Code-Guided, Modular, and Verifiable Automated Machine Learning

TL;DR

This paper introduces iML, a multi-agent AutoML framework that emphasizes code-guided, modular, and verifiable design to improve reliability, transparency, and performance in real-world machine learning tasks.

Contribution

iML presents a novel multi-agent architecture with code-guided planning, modular implementation, and verifiable integration, addressing hallucination and unreliability in LLM-based AutoML.

Findings

Achieves 85% valid submission rate on MLE-BENCH.

Outperforms state-of-the-art agents with 38%-163% higher APS on iML-BENCH.

Maintains 70% success rate under stripped task descriptions.

Abstract

Automated Machine Learning (AutoML) has revolutionized the development of data-driven solutions; however, traditional frameworks often function as "black boxes", lacking the flexibility and transparency required for complex, real-world engineering tasks. Recent Large Language Model (LLM)-based agents have shifted toward code-driven approaches. However, they frequently suffer from hallucinated logic and logic entanglement, where monolithic code generation leads to unrecoverable runtime failures. In this paper, we present iML, a novel multi-agent framework designed to shift AutoML from black-box prompting to a code-guided, modular, and verifiable architectural paradigm. iML introduces three main ideas: (1) Code-Guided Planning, which synthesizes a strategic blueprint grounded in autonomous empirical profiling to eliminate hallucination; (2) Code-Modular Implementation, which decouples preprocessing and modeling into specialized components governed by strict interface contracts; and (3) Code-Verifiable Integration, which enforces physical feasibility through dynamic contract verification and iterative self-correction. We evaluate iML across MLE-BENCH and the newly introduced iML-BENCH, comprising a diverse range of real-world Kaggle competitions. The experimental results show iML's superiority over state-of-the-art agents, achieving a valid submission rate of 85% and a competitive medal rate of 45% on MLE-BENCH, with an average standardized performance score (APS) of 0.77. On iML-BENCH, iML significantly outperforms the other approaches by 38%-163% in APS. Furthermore, iML maintains a robust 70% success rate even under stripped task descriptions, effectively filling information gaps through empirical profiling. These results highlight iML's potential to bridge the gap between stochastic generation and reliable engineering, marking a meaningful step toward truly AutoML.