The field has shifted from automating narrow, isolated tasks toward general-purpose systems that span much of the research life cycle. Lu et al. 2026's AI Scientist runs from ideation to peer review, Gottweis et al. 2026 frame Co-Scientist as a general collaborator for scientists, and Huang et al. 2025 present Biomni as a general-purpose biomedical agent rather than a specialist workflow.
E1 explicitly contrasts earlier narrow-task AI with the AI Scientist's ideation-to-peer-review pipeline, E4 frames Co-Scientist as a collaborator to scientists, and E8 introduces Biomni as a general-purpose biomedical agent executing a wide spectrum of research tasks.
Written by Kimi K3 via Ollama Cloud · checked by GLM-5.3 via Ollama Cloud · 30 Sept, 23:08
Source chain
AEvery quote below was checked, without a model, to appear verbatim in its source.
- 01
“perform ideation, literature search, experiment planning and implementation, result analysis, manuscript writing, and peer review to produce complete, new papers”
Full-text passage · no page number · evidence E1
Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.
- 02
“designed to act as a collaborator to scientists and help accelerate the scientific discovery process”
Full-text passage · no page number · evidence E4
Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.
- 03
“Here, we introduce Biomni, a general-purpose biomedical AI agent”
Full-text passage · p. 2 · evidence E8
Abstract1 Biomedical research underpins progress in our understanding of human health and disease,2 drug discovery, and clinical care. However, with the growth of complex lab experiments,3 large datasets, many analytical tools, and expansive literature, biomedical research is in-4 creasingly constrained by repetitive and fragmented workflows that slow discovery and limit5 innovation, underscoring the need for a fundamentally new way to scale scientific exper-6 tise. Here, we introduce Biomni, a general-purpose biomedical AI agent designed to au-7 tonomously execute a wide spectrum of research tasks across diverse biomedical subfields.8 To systematically map the biomedical action space, Biomni first employs an action discov-9 ery agent to create the first unified agentic environment – mining essential tools, databases,10 and protocols from tens of thousands of publications across 25 biomedical domains.
Passage read from www.biorxiv.org, which may be a preprint rather than the published version.