# A Process-Centric Survey of AI for Scientific Discovery Through the EXHYTE Framework

## TL;DR

This paper introduces the EXHYTE framework, a structured approach to understanding how AI contributes to scientific discovery through iterative cycles of exploration, hypothesis generation, and testing.

## Contribution

The paper introduces the EXHYTE cycle, a novel framework that unifies AI-driven scientific discovery into a structured process.

## Key findings

- The EXHYTE cycle identifies mature and underexplored substages in AI-driven discovery.
- The framework reveals how AI methods can complement human researchers in a structured workflow.
- A website with paper summaries and an interactive survey is provided to support the EXHYTE framework.

## Abstract

Large language models (LLMs) and agent systems are increasingly transforming scientific discovery, driving progress across chemistry, biology, materials science, and physics. Yet most existing work and surveys remain fragmented, focusing on isolated tasks such as idea generation or experiment design without addressing how these components fit within the broader discovery process. To bridge this gap, we introduce the EXHYTE cycle, an iterative framework that formalizes scientific discovery as a sequence of Exploration, Hypothesis generation, and Testing. We assembled a corpus of recent studies, distilled recurring strategies that characterize how AI methods contribute to each EXHYTE substage, and organized the literature accordingly to representative strategies and domain-specific advances. This process-centric perspective unifies diverse methodologies under a single structured workflow, identifies substages that are mature versus underexplored, and reveals complementarities that enable closed-loop discovery systems. It also clarifies the evolving division of labor between human researchers and AI systems, offering a roadmap for developing adaptive, autonomous frameworks for AI-driven scientific discovery. An accompanying website with paper summaries and an LLM-powered interactive survey based on EXHYTE is available at https://webapps.crc.pitt.edu/exhyte/