The rise of agentic AI in drug discovery from static tools to autonomous virtual scientists

Checked 15 Oct 2026. Non-commercial or no-derivatives license: full text kept internally; only metadata and abstract are indexed and used.

Driven by large language models, AI agents are transforming drug discovery, enabling AI to break free from task-specific tools and advance toward the vision of autonomous virtual scientists. This perspective reviews applications across the R&D lifecycle. To evaluate system maturity, we introduce a 6-level "Spectrum of Agentic Autonomy." We advocate for novel evaluation paradigms centered on full-chain traceability and outline adoption barriers, positioning AI agents as pragmatic scientist-in-the-loop co-pilots.

• Multiple 2026 perspectives are converging on staged autonomy taxonomies as the way to measure agentic-science maturity: Zhao et al. 2026 introduce a 6-level "Spectrum of Agentic Autonomy" for drug discovery, while Hebenstreit et al. 2026 synthesize four prior frameworks into a biomedical framework distinguishing cognitive from physical capabilities. Trace →
• Within drug discovery, developers stake out opposed autonomy positions for similar lifecycles: Ghareeb et al. 2026 describe Robin as the first system to fully automate hypothesis generation and data analysis, whereas Huynh et al. 2026 build RepurAgent explicitly around a human-in-the-loop design and Zhao et al. 2026 position agents as pragmatic scientist-in-the-loop co-pilots. Trace →
• Three independent 2026 efforts converge on 'scientist-in-the-loop' as the pragmatic deployment form for research agents: Jeon 2026 prescribes strict boundaries in plant pathology under which a human sets goals, reviews AI output before it is treated as evidence, and approves consequential actions; Zhao et al. 2026 advocate 'pragmatic scientist-in-the-loop co-pilots' for drug discovery; and Huynh et al. 2026 built the drug-repurposing system RepurAgent around a human-in-the-loop design. Trace →
• The levels-of-autonomy schema familiar from engineering standards is being imported into AI-for-science governance by two independent 2026 papers: Zhao et al. 2026 introduce a 6-level 'Spectrum of Agentic Autonomy' for drug discovery, and Hebenstreit et al. 2026 synthesize AGI and engineering-autonomy frameworks into a biomedical framework distinguishing cognitive from physical capabilities. Trace →
• The full-chain traceability that Zhao et al. 2026 demand as a new evaluation paradigm is already being practiced: Yoon et al. 2026 used session transcripts to attribute their agent's discovery to the model directly examining DNA sequences and recognizing atypical repeats, a behavior they trace to specific internal signals responding to repeated DNA. Trace →

• AI for science and agentic research