AI Insight
DarkAgents is a multi-agent AI system that combines large language models with established scientific code to automate complex computational pipelines in theoretical astroparticle physics. The researchers applied this framework to study cosmological phase transitions, analyzing data from the NANOGrav gravitational wave observations and producing best-fit parameters for particle physics models while auditing the assumptions underlying these calculations. The system identified inconsistencies in existing published analyses and generated novel fits using alternative gravitational wave templates.
Why it matters
This approach could accelerate theoretical physics research by automating labor-intensive computational workflows while maintaining transparency about underlying assumptions. The ability to audit priors and constraints systematically may improve reproducibility in astrophysics and help identify errors in existing literature.
arXiv:2606.11157v1 Announce Type: cross
Abstract: We present DarkAgents: a multi-agent system that leverages the reasoning and code-generation capabilities of large language models (LLMs), together with deterministic tested human-written code, to build orchestrated pipelines for theoretical astroparticle physics research. While related approaches have been proposed in collider physics and cosmology, DarkAgents targets the specific challenges of this domain, such as model building, complex pipeline computations, multiple constraints and assumption auditing. The framework can be powered by different agentic command-line tools, including Mistral’s, Anthropic’s, OpenAI’s and local LLMs via Ollama. As first implementation, we apply DarkAgents to the study of cosmological first order transitions, starting from a classically scale-invariant particle-physics model and ending with the fit to the NANOGrav nanohertz gravitational-waves spectrum. DarkAgent-PT provides as output i) the best-fit values of model parameters, ii) their existing experimental and observational constraints, iii) an audit report of the assumptions and priors entering both i) and ii), of particular relevance for astroparticle physics. Our test runs identify inconsistencies in some fits in the literature and produce novel ones based on the dissipative bulk-flow GW template. The code is publicly available at https://github.com/PhysicsZandi/DarkAgents.
Source: DarkAgents