An End-to-end Architecture for Collider Physics and Beyond

TL;DR

This paper introduces a novel language-driven agent system for end-to-end collider physics tasks, enabling automated, scalable, and reproducible phenomenological analysis from theoretical models to experimental outputs.

Contribution

The work presents the first domain-agnostic, language-guided agent architecture for collider phenomenology that operates without package-specific code, integrating reasoning and execution layers.

Findings

Successfully reproduces literature results in various collider scenarios.

Handles complex workflows from Lagrangian to phenomenological outputs.

Enables large-scale parameter scans and exclusion limit calculations.

Abstract

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.