Agentic Drug Discovery Requires a Scientific Constitution for Autonomous Planning, Tool Selection, Experimentation, and Human Intervention
Year: 2025
Type: article
Abstract: Artificial intelligence in drug discovery is moving from bounded prediction toward systems that can formulate plans, select computational and laboratory tools, revise strategies, and initiate experiments. This transition changes the scientific governance problem because an agent may influence not only what is predicted but also which evidence is gathered, which hypotheses are pursued, and which physical actions are undertaken. Conventional evaluation based on predictive accuracy, task completion
Source: Pharmacophore
DOI: 10.51847/aolckzpo1a
Authors: Michael O'Donnell, Emma Byrne, Nora O'Connor, Aisling Kelly
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7202085622