AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

TL;DR

AutoMind is an adaptive LLM-based agent framework that integrates expert knowledge, strategic search, and dynamic coding to improve automated data science tasks, outperforming existing methods in benchmarks.

Contribution

AutoMind introduces a novel adaptive framework combining expert knowledge, strategic exploration, and self-tuning code generation for automated data science.

Findings

Outperforms state-of-the-art baselines on benchmarks.

Demonstrates improved efficiency and solution quality.

Proves effective across complex, real-world data science tasks.

Abstract

Large Language Model (LLM) agents have shown great potential in addressing real-world data science problems. LLM-driven data science agents promise to automate the entire machine learning pipeline, yet their real-world effectiveness remains limited. Existing frameworks depend on rigid, pre-defined workflows and inflexible coding strategies; consequently, they excel only on relatively simple, classical problems and fail to capture the empirical expertise that human practitioners bring to complex, innovative tasks. In this work, we introduce AutoMind, an adaptive, knowledgeable LLM-agent framework that overcomes these deficiencies through three key advances: (1) a curated expert knowledge base that grounds the agent in domain expert knowledge, (2) an agentic knowledgeable tree search algorithm that strategically explores possible solutions, and (3) a self-adaptive coding strategy that dynamically tailors code generation to task complexity. Evaluations on two automated data science benchmarks demonstrate that AutoMind delivers superior performance versus state-of-the-art baselines. Additional analyses confirm favorable effectiveness, efficiency, and qualitative solution quality, highlighting AutoMind as an efficient and robust step toward fully automated data science. Code is at https://github.com/innovatingAI/AutoMind.