The Denario project: Deep knowledge AI agents for scientific discovery
🤖 AI Summary
To address the challenges of high task heterogeneity and cross-disciplinary collaboration in scientific research, this paper introduces Denario—a modular multi-agent system powered by deep domain knowledge AI. Denario integrates domain-specific agents (e.g., for quantum physics and machine learning), NLP and code generation models, and scientific computing toolchains to automate the entire research workflow: from topic ideation and literature review to experimental design, code execution, visualization generation, manuscript drafting, and peer review simulation. Its core innovation is the Cmbagent end-to-end analytical framework, enabling fusion of heterogeneous, multi-source knowledge and cross-domain reasoning. Evaluated across over ten disciplines—including astrophysics, biology, chemistry, and medicine—Denario has generated high-quality AI-authored papers validated by domain experts for scientific validity and practical utility. The full source code and interactive demo are publicly released under an open-source license.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Developing AI agents for automated scientific discovery tasks
Creating modular system for end-to-end research assistance
Addressing interdisciplinary knowledge integration across scientific fields
Innovation
Methods, ideas, or system contributions that make the work stand out.
Modular multi-agent system for scientific tasks
Deep-research backend enables end-to-end analysis
Generates interdisciplinary papers across scientific fields
🔎 Similar Papers
No similar papers found.
