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

2025-08-18

AI Summary

This paper addresses the pivotal transition of AI from a research-assistance tool to an autonomous scientific discovery agent, proposing the “Agentic Science” paradigm. Methodologically, it introduces the first unified framework integrating process, autonomy, and mechanistic principles; distills five core capabilities of scientific agents; defines a four-stage dynamic research workflow; and implements hypothesis generation, experimental design, execution and analysis, and iterative optimization via large language models, multimodal systems, and domain-specific knowledge modeling. Contributions include: (1) establishing the first interdisciplinary taxonomy for autonomous scientific discovery; (2) systematically synthesizing advances across life sciences, chemistry, materials science, and physics; and (3) identifying critical technical and epistemological challenges while charting concrete future research directions—thereby providing both theoretical foundations and actionable pathways for AI-driven scientific paradigm transformation.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Transitioning AI from scientific tools to autonomous research partners
• Establishing a unified framework for autonomous scientific discovery processes
• Reviewing applications and challenges of agentic AI across scientific domains

Innovation

• Agentic AI systems with full scientific agency
• Multimodal systems and integrated research platforms
• Dynamic four-stage workflow for discovery