Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions

TL;DR

This survey analyzes the rise of agentic AI in scientific discovery, clarifying foundational concepts and contrasting autonomous versus human-AI collaborative paradigms. It catalogs current frameworks, tools, datasets, and evaluation metrics across chemistry, biology, and materials science, and examines literature-review and discovery workflows. The authors identify progress alongside challenges in trustworthiness, ethics, and reliability, with literature review remaining a persistent hurdle. They advocate for calibrated, human-in-the-loop approaches and standardized benchmarks to ensure reliable, responsible, and scalable scientific automation.

Abstract

The integration of Agentic AI into scientific discovery marks a new frontier in research automation. These AI systems, capable of reasoning, planning, and autonomous decision-making, are transforming how scientists perform literature review, generate hypotheses, conduct experiments, and analyze results. This survey provides a comprehensive overview of Agentic AI for scientific discovery, categorizing existing systems and tools, and highlighting recent progress across fields such as chemistry, biology, and materials science. We discuss key evaluation metrics, implementation frameworks, and commonly used datasets to offer a detailed understanding of the current state of the field. Finally, we address critical challenges, such as literature review automation, system reliability, and ethical concerns, while outlining future research directions that emphasize human-AI collaboration and enhanced system calibration.

Figures (2)

• Figure 1: Agentic AI workflow for scientific discovery.
• Figure 2: AI Agents frameworks for scientific discovery.