DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data

2026-08-05

AI Summary

This work addresses the challenge of efficiently constructing reliable and interpretable machine learning pipelines from small-scale, heterogeneous, and temporally complex clinical data, a setting where conventional AutoML methods struggle due to their reliance on exhaustive search. To overcome this limitation, the authors propose DoctorAgents, a novel framework that reframes AutoML as an iterative, reasoning- and memory-driven optimization process. Leveraging a multi-agent large language model architecture, DoctorAgents orchestrates collaborative generation, validation, and refinement of pipelines, augmented by a natural language feedback–guided textual gradient descent mechanism to enable goal-directed, end-to-end AutoML pipeline distillation. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art AutoML baselines across diverse clinical tasks while producing more interpretable, task-specific representations.

Abstract

Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but reliable deployment is often constrained by scarce, heterogeneous, and temporal complexity. Developing effective ML pipelines for such data remains time-consuming and error-prone, while existing automated machine learning (AutoML) systems only partially address this challenge because they largely rely on brute-force search over predefined spaces and lack explicit reasoning and memory. We therefore reformulate AutoML for small clinical data from exhaustive search to reasoning-driven refinement. We propose DoctorAgents, an agentic AI framework that autonomously constructs and optimizes end-to-end ML pipelines through specialized large language model (LLM) agents for generation, validation, and refinement. DoctorAgents backpropagates natural-language feedback through textual gradient descent to perform targeted updates without exhaustive search. Experiments across diverse clinical tasks show that DoctorAgents consistently outperforms established AutoML baselines while producing more interpretable task-specific representations.

Problem

• clinical temporal data
• AutoML
• small data
• machine learning pipeline
• medical decision-making

Innovation

• agentic AI
• AutoML
• clinical temporal data
• reasoning-driven refinement
• textual gradient descent