The Denario project: Deep knowledge AI agents for scientific discovery
Francisco Villaescusa-Navarro, Boris Bolliet, Pablo Villanueva-Domingo, Adrian E. Bayer, Aidan Acquah, Chetana Amancharla, Almog Barzilay-Siegal, Pablo Bermejo, Camille Bilodeau, Pablo Cárdenas Ramírez, Miles Cranmer, Urbano L. França, ChangHoon Hahn, Yan-Fei Jiang, Raul Jimenez, Jun-Young Lee, Antonio Lerario, Osman Mamun, Thomas Meier, Anupam A. Ojha, Pavlos Protopapas, Shimanto Roy
2025-11-03
Summary
This paper introduces Denario, a new AI system built to act as a helper for scientists doing research. It's designed to handle many parts of the research process, from brainstorming ideas to actually writing up the final paper.
What's the problem?
Scientific research is a complex process that requires a lot of different skills and time. Researchers often spend significant effort on tasks like reviewing existing studies, developing experimental plans, and writing code, which can slow down the pace of discovery. There's a need for tools that can assist with these tasks and help scientists focus on the core creative aspects of their work.
What's the solution?
The creators of this paper built Denario, an AI system with different modules that can each handle a specific research task. It can generate new research ideas, search through scientific literature, create research plans, write and run computer code for experiments, create graphs and charts, and even draft and review scientific papers. They used a system called Cmbagent to power the deeper research aspects. They tested Denario by having it write papers in many different scientific fields, and then had experts in those fields evaluate the quality of the AI-generated work.
Why it matters?
Denario represents a significant step towards using AI to accelerate scientific progress. It shows that AI can not only assist with individual tasks but can also potentially conduct entire research projects. The ability to combine ideas from different fields, as demonstrated by the paper applying quantum physics to astrophysics, is particularly exciting. Furthermore, the public release of the code allows other researchers to build upon this work and explore the ethical implications of AI in science.
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 in detail Denario and its modules, and illustrate its capabilities by presenting multiple AI-generated papers generated by it in many different scientific disciplines such as astrophysics, biology, biophysics, biomedical informatics, chemistry, material science, mathematical physics, medicine, neuroscience and planetary science. Denario also excels at combining ideas from different disciplines, and we illustrate this by showing a paper that applies methods from quantum physics and machine learning to astrophysical data. We report the evaluations performed on these papers by domain experts, who provided both numerical scores and review-like feedback. We then 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 https://github.com/AstroPilot-AI/Denario. A Denario demo can also be run directly on the web at https://huggingface.co/spaces/astropilot-ai/Denario, and the full app will be deployed on the cloud.