An End-to-end Architecture for Collider Physics and Beyond
This addresses the problem of manual, error-prone processes in high-energy physics research, offering a scalable and reproducible approach for physicists, though it is incremental as it builds on existing tools.
The paper tackles the challenge of automating collider physics workflows by introducing ColliderAgent, a language-driven system that executes tasks from theoretical Lagrangians to final outputs using natural-language prompts, validated through reproductions of scenarios like leptoquarks and axion-like particles.
We present, to our knowledge, the first language-driven agent system capable of executing end-to-end collider phenomenology tasks, instantiated within a decoupled, domain-agnostic architecture for autonomous High-Energy Physics phenomenology. Guided only by natural-language prompts supplemented with standard physics notation, ColliderAgent carries out workflows from a theoretical Lagrangian to final phenomenological outputs without relying on package-specific code. In this framework, a hierarchical multi-agent reasoning layer is coupled to Magnus, a unified execution backend for phenomenological calculations and simulation toolchains. We validate the system on representative literature reproductions spanning leptoquark and axion-like-particle scenarios, higher-dimensional effective operators, parton-level and detector-level analyses, and large-scale parameter scans leading to exclusion limits. These results point to a route toward more automated, scalable, and reproducible research in collider physics, cosmology, and physics more broadly.