Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research

Computer Science > Artificial Intelligence [Submitted on 18 Mar 2026] Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research Thomas Borrett, Licong Xu, Andy Nilipour, Boris Bolliet, Sebastien Pierre, Erwan Allys, Celia Lecat, Biwei Dai, Po-Wen Chang, Wahid Bhimji We present an agent-driven approach to the construction of parameter inference pipelines for scientific data analysis. Our method leverages a multi-agent system, Cmbagent (the analysis system of the AI scientist Denario), in which specialized agents collaborate to generate research ideas, write and execute code, evaluate results, and iteratively refine the overall pipeline. As a case study, we apply this approach to the FAIR Universe Weak Lensing Uncertainty Challenge, a competition under time constraints focused on robust cosmological parameter inference with realistic observational uncertainties. While the fully autonomous exploration initially did not reach expert-level performance, the integration of human intervention enabled our agent-driven workflow to achieve a first-place result in the challenge. This demonstrates that semi-autonomous agentic systems can compete with, and in some cases surpass, expert solutions. We describe our workflow in detail, including both the autonomous and semi-autonomous exploration by Cmbagent. Our final inference pipeline utilizes parameter-efficient convolutional neural networks, likelihood calibration over a known parameter grid, and multiple regularization techniques. Our results suggest that agent-driven research workflows can provide a scalable framework to rapidly explore and construct pipelines for inference problems. Comments: 12 pages, 4 figures Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.09621 [cs.AI]   (or arXiv:2604.09621v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.09621 Focus to learn more Submission history From: Thomas Borrett [view email] [v1] Wed, 18 Mar 2026 10:32:20 UTC (285 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)