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

2026-02-15

AI Summary

This work addresses the limitations of traditional AutoML systems—namely, their lack of transparency and flexibility—and the susceptibility of existing large language model (LLM) agents to unrecoverable errors caused by logical hallucinations and tightly coupled code generation. To overcome these challenges, the authors propose iML, a multi-agent framework that introduces code-guided planning, interface-contract-based modular decoupling, and an integrated mechanism combining dynamic contract validation with self-correction. This design significantly enhances the system’s interpretability, reliability, and engineering feasibility. Empirical evaluations demonstrate that iML achieves an 85% valid submission rate and a 45% medal rate (APS=0.77) on MLE-BENCH, and outperforms baseline methods by 38%–163% on the newly introduced iML-BENCH, maintaining a 70% success rate even under conditions of incomplete information.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Automated Machine Learning
• black-box
• hallucination
• logic entanglement
• code verifiability

Innovation

• Code-Guided Planning
• Modular Implementation
• Verifiable Integration
• Multi-Agent AutoML
• Empirical Profiling