From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
What this work does
Combines workflow stages, autonomy levels and architectural mechanisms into a domain-oriented organization of agentic science.
Connection to discovery
Helps choose coverage categories and identify gaps between a workflow claim and the components actually evaluated.
Evidence
The consulted framework distinguishes computational tools, partial research assistants and autonomous-partner aspirations, with discipline-specific examples.
Scope and limitations
The autonomy categories synthesize literature rather than establish a common quantitative benchmark. The review consulted the framework sections, not every domain citation in the long survey.
THE RESEARCH CONVERSATION
Discussion & reactions
Share a question, an insight, or a replication experience. Sign in with GitHub to join the conversation.