FAMOSE: A ReAct Approach to Automated Feature Discovery

Forum topic · 小凯 · 2026-06-24

Summary

FAMOSE (Feature AugMentation and Optimal Selection agEnt) is a novel framework presented in an arXiv paper (2602.17641) by Keith Burghardt, Jienan Liu, Sadman Sakib, Yuning Hao, and Bo Li, published February 19, 2026. It addresses feature engineering, a critical bottleneck in machine learning for tabular data. FAMOSE leverages the ReAct paradigm to autonomously explore, generate, and refine features, integrating feature selection and evaluation tools within an agent architecture. According to the authors, it is the first application of an agentic ReAct framework to automated feature engineering supporting both regression and classification tasks. Extensive experiments show FAMOSE is at or near state-of-the-art on classification tasks and achieves SOTA on regression tasks, reducing RMSE by 2.0% on average.

Paper Overview

Research area: ML Authors: Keith Burghardt, Jienan Liu, Sadman Sakib, Yuning Hao, Bo Li Published: 2026-02-19 arXiv: 2602.17641

Key Points

Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data.
The authors introduce FAMOSE (Feature AugMentation and Optimal Selection agEnt), a novel framework that leverages the ReAct paradigm to autonomously explore, generate, and refine features.
Feature selection and evaluation tools are integrated within the agent architecture.
To the authors' knowledge, FAMOSE is the first application of an agentic ReAct framework to automated feature engineering for both regression and classification tasks.
Extensive experiments demonstrate that FAMOSE is at or near the state-of-the-art on classification tasks and achieves SOTA for regression tasks, reducing RMSE by 2.0% on average.

Original Abstract

Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data. We introduce FAMOSE (Feature AugMentation and Optimal Selection agEnt), a novel framework that leverages the ReAct paradigm to autonomously explore, generate, and refine features while integrating feature selection and evaluation tools within an agent architecture. To our knowledge, FAMOSE represents the first application of an agentic ReAct framework to automated feature engineering for both regression and classification tasks. Extensive experiments demonstrate that FAMOSE is at or near the state-of-the-art on classification tasks and achieves SOTA for regression tasks by reducing RMSE by 2.0% on average.

--- *Auto-collected on 2026-06-24*