LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data

2025-07-17

AI Summary

Existing AutoML systems for tabular data tasks suffer from limited flexibility and robustness due to over-reliance on a single underlying tool. This work proposes a collaborative multi-AutoML agent framework that integrates LLM-driven code generation, dynamic multi-engine scheduling, and task-feedback-guided iterative optimization to achieve end-to-end automated modeling. By decoupling the system from fixed tool dependencies, the architecture significantly enhances adaptability and fault tolerance in challenging scenarios—including heterogeneous data, noisy inputs, and small-sample regimes. Evaluated on multiple Kaggle benchmark tasks, our approach surpasses current open-source state-of-the-art methods, achieving an average performance gain of 3.2% while demonstrating superior generalization and stability. The implementation is publicly available.

Technology Category

• Machine Learning: Auto ML and Hyperparameter Tuning
• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

AutoML has advanced in handling complex tasks using the integration of LLMs, yet its efficiency remains limited by dependence on specific underlying tools. In this paper, we introduce LightAutoDS-Tab, a multi-AutoML agentic system for tasks with tabular data, which combines an LLM-based code generation with several AutoML tools. Our approach improves the flexibility and robustness of pipeline design, outperforming state-of-the-art open-source solutions on several data science tasks from Kaggle. The code of LightAutoDS-Tab is available in the open repository https://github.com/sb-ai-lab/LADS

Problem

• Enhances AutoML flexibility for tabular data tasks
• Integrates LLM-based code generation with AutoML tools
• Improves pipeline design robustness over existing solutions

Innovation

• LLM-based code generation for AutoML
• Integration of multiple AutoML tools
• Enhanced pipeline flexibility and robustness