Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations

TL;DR

Agent0 leverages multiple LLM agents to automatically extract and construct multi-value features from unstructured text, improving recommender system performance through automated feature discovery and prompt tuning.

Contribution

This work introduces Agent0, a novel LLM-based agent system that automates feature extraction and prompt engineering for recommender systems, addressing a key challenge in feature engineering.

Findings

Effective automated feature discovery demonstrated

Closed-loop prompt tuning improves feature relevance

Enhances recommender system development efficiency

Abstract

Large language models (LLMs) and their associated agent-based frameworks have significantly advanced automated information extraction, a critical component of modern recommender systems. While these multitask frameworks are widely used in code generation, their application in data-centric research is still largely untapped. This paper presents Agent0, an LLM-driven, agent-based system designed to automate information extraction and feature construction from raw, unstructured text. Categorical features are crucial for large-scale recommender systems but are often expensive to acquire. Agent0 coordinates a group of interacting LLM agents to automatically identify the most valuable text aspects for subsequent tasks (such as models or AutoML pipelines). Beyond its feature engineering capabilities, Agent0 also offers an automated prompt-engineering tuning method that utilizes dynamic feedback loops from an oracle. Our findings demonstrate that this closed-loop methodology is both practical and effective for automated feature discovery, which is recognized as one of the most challenging phases in current recommender system development.