From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

TL;DR

This survey explores the evolution of AI into autonomous agents capable of conducting scientific research across various domains, highlighting capabilities, frameworks, and future challenges in Agentic Science.

Contribution

It unifies fragmented perspectives into a comprehensive framework, models discovery as a four-stage workflow, and reviews applications and challenges in autonomous scientific discovery.

Findings

Identification of five core capabilities for scientific agency

Development of a four-stage discovery workflow model

Comprehensive review across multiple scientific domains

Abstract

Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within the broader AI for Science paradigm, where AI systems progress from partial assistance to full scientific agency. Enabled by large language models (LLMs), multimodal systems, and integrated research platforms, agentic AI shows capabilities in hypothesis generation, experimental design, execution, analysis, and iterative refinement -- behaviors once regarded as uniquely human. This survey provides a domain-oriented review of autonomous scientific discovery across life sciences, chemistry, materials science, and physics. We unify three previously fragmented perspectives -- process-oriented, autonomy-oriented, and mechanism-oriented -- through a comprehensive framework that connects foundational capabilities, core processes, and domain-specific realizations. Building on this framework, we (i) trace the evolution of AI for Science, (ii) identify five core capabilities underpinning scientific agency, (iii) model discovery as a dynamic four-stage workflow, (iv) review applications across the above domains, and (v) synthesize key challenges and future opportunities. This work establishes a domain-oriented synthesis of autonomous scientific discovery and positions Agentic Science as a structured paradigm for advancing AI-driven research.