I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search

TL;DR

This paper introduces I-MCTS, an improved AutoML agent that uses introspective analysis and LLM-based evaluation to enhance decision-making, resulting in a 4% performance boost over existing AutoML agents.

Contribution

The paper proposes I-MCTS, a novel introspective Monte Carlo Tree Search method that refines node evaluation through analysis and integrates LLM-based value models for better AutoML performance.

Findings

Achieves 4% performance improvement over baseline AutoML agents.

Utilizes LLM-based value models for pre-rollout node evaluation.

Demonstrates effectiveness across various machine learning tasks.

Abstract

Recent advancements in large language models (LLMs) have shown remarkable potential in automating machine learning tasks. However, existing LLM-based agents often struggle with low-diversity and suboptimal code generation. While recent work has introduced Monte Carlo Tree Search (MCTS) to address these issues, limitations persist in the quality and diversity of thoughts generated, as well as in the scalar value feedback mechanisms used for node selection. In this study, we introduce Introspective Monte Carlo Tree Search (I-MCTS), a novel approach that iteratively expands tree nodes through an introspective process that meticulously analyzes solutions and results from parent and sibling nodes. This facilitates a continuous refinement of the node in the search tree, thereby enhancing the overall decision-making process. Furthermore, we integrate a Large Language Model (LLM)-based value model to facilitate direct evaluation of each node's solution prior to conducting comprehensive computational rollouts. A hybrid rewarding mechanism is implemented to seamlessly transition the Q-value from LLM-estimated scores to actual performance scores. This allows higher-quality nodes to be traversed earlier. Applied to the various ML tasks, our approach demonstrates a 4% absolute improvement in performance compared to the strong open-source AutoML agents, showcasing its effectiveness in enhancing agentic AutoML systems. Resource available at https://github.com/jokieleung/I-MCTS