Abstract

We present Denario, an AI multi-agent system designed to serve as a scientific research assistant. Denario can perform many different tasks, such as generating ideas, checking the literature, developing research plans, writing and executing code, making plots, and drafting and reviewing a scientific paper. The system has a modular architecture, allowing it to handle specific tasks, such as generating an idea, or carrying out end-to-end scientific analysis using cmbagent as a deep-research backend. In this work, we describe Denario and its modules in detail and illustrate its capabilities by presenting multiple AI-generated papers generated by it. These papers cover many scientific disciplines, such as astrophysics, biology, biophysics, biomedical informatics, chemistry, material science, mathematical physics, medicine, and planetary science. Denario can also perform research combining ideas from different disciplines, and we illustrate it by showing a paper that applies methods from quantum physics and machine learning with astrophysical data. We report the evaluations performed on these papers by domain experts, who provided both numerical scores and qualitative feedback. We analyze these results to highlight the strengths, weaknesses, and limitations of the current system. Finally, we discuss the ethical implications of AI-driven research and reflect on how such technology relates to the philosophy of science. We publicly release the code at Github. A Denario demo can also be run directly on the web at HugginFace Spaces, and the full app will be deployed on the cloud.

News

End to End Research Demo

Denario - MIT Talk


Example papers

Here are some example papers generated by Denario in different scientific fields.

Astrophysics

Biology

Chemistry

Material Science

Medicine

Physics

BibTeX

@software{Denario,
      author = {Denario Authors},
      title = {The Denario Project: Modular Automation of Scientific Research with Multi-Agent Systems},
      month = {October},
      year = {2025},
      url = {https://astropilot-ai.github.io/DenarioPaperPage/}
      }