Back to search

Article

A Persistent Fleet of AI Scientists Exhibits Cooperative and Autopoietic Behavior

2026-08-18

Abstract excerpt

Scientific work depends on memory, provenance, and continuity across projects, yet most agentic scientist systems are evaluated in bounded workflows or short benchmark runs. We describe a persistent fleet of cooperative AI scientist agents that operated continuously for nearly six months using shared memory, tools, and cross-agent communication. Critically, failures identified during longitudinal scientific resear...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
7b15ea06-522c-5067-87ef-285a52dbf2a2
DOI
10.64898/2026.08.16.745122
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
A Persistent Fleet of AI Scientists Exhibits Cooperative and Autopoietic BehaviorDOI 10.64898/2026.08.16.745122
The One-Person Laboratory Should Be a First-Class Unit of Evaluation in Dry-Lab AI ResearchSemantic proximity
Trustworthy Agentic AI: A Rapid, PRISMA-Informed Evidence Review of Safety, Explainability, Alignment, and Human Oversight in Autonomous AI SystemsSemantic proximity
ClaroAI-Bench: Evaluating Agentic Scientific Reproducibility on Real Biomedical PapersSemantic proximity
Towards Human-Led, Agent-Driven Autonomous Laboratories for the Life SciencesSemantic proximity
The AutoResearch Moment: From Experimenter to Research DirectorSemantic proximity
Closed-Loop Quality Assurance for Production Clinical AI DocumentationSemantic proximity
Autonomous Scientific Discovery Through Hierarchical AI Scientist SystemsSemantic proximity
A Survey of Human-AI Collaboration for Scientific DiscoverySemantic proximity
A Survey of Human-AI Collaboration for Scientific DiscoverySemantic proximity
Synergy, Not Substitution. Responsible Human–AI Collaboration in Academic ResearchSemantic proximity
Trust as a Trajectory Property: An Epistemic Dynamics Framework for AI EvaluationSemantic proximity
BiomniBench: Process-level Evaluation of LLM Agents for Real-world Biomedical ResearchSemantic proximity
Select a neighboring publication to make it the new centre.