Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data

TL;DR

MALMAS is a memory-augmented multi-agent system leveraging LLMs for automated feature generation on tabular data, enhancing diversity and quality through iterative refinement and task-aware exploration.

Contribution

We introduce MALMAS, a novel multi-agent framework with memory modules that broadens feature space exploration and improves feature quality for tabular data tasks.

Findings

Outperforms state-of-the-art baselines on multiple datasets.

Enhances feature diversity and quality through iterative refinement.

Demonstrates effectiveness of memory modules in feature generation.

Abstract

Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. Traditional methods rely on predefined operator libraries and cannot leverage task semantics, limiting their ability to produce diverse, high-value features for complex tasks. Recent Large Language Model (LLM)-based approaches introduce richer semantic signals, but still suffer from a restricted feature space due to fixed generation patterns and from the absence of feedback from the learning objective. To address these challenges, we propose a Memory-Augmented LLM-based Multi-Agent System (\textbf{MALMAS}) for automated feature generation. MALMAS decomposes the generation process into agents with distinct responsibilities, and a Router Agent activates an appropriate subset of agents per iteration, further broadening exploration of the feature space. We further integrate a memory module comprising procedural memory, feedback memory, and conceptual memory, enabling iterative refinement that adaptively guides subsequent feature generation and improves feature quality and diversity. Extensive experiments on multiple public datasets against state-of-the-art baselines demonstrate the effectiveness of our approach. The code is available at https://github.com/fxdong24/MALMAS