LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data
This work addresses efficiency issues in AutoML for data scientists working with tabular data, but it appears incremental as it builds on existing AutoML and LLM integration methods.
The paper tackles the problem of limited efficiency in AutoML due to tool dependence by introducing LightAutoDS-Tab, a multi-AutoML agentic system for tabular data that combines LLM-based code generation with AutoML tools, resulting in improved flexibility and robustness that outperforms state-of-the-art open-source solutions on Kaggle tasks.
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