Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shi Qiu, Zeyu Cai, Jiashen Wei, Zeyu Li, Yixuan Yin, Qing-Hong Cao, Chang Liu, Ming-xing Luo, Xing-Bo Yuan, Hua Xing Zhu

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.

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

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.
Paper Structure (23 sections, 9 equations, 3 figures)

This paper contains 23 sections, 9 equations, 3 figures.

Table of Contents

  1. Specialized Sub-agents.
  2. Execution Backend.
  3. Validation and Self-Correction.
  4. I. Implementation of ColliderAgent
  5. Skill-Based Multi-Agent Implementation
  6. ADK-based Reference Implementation
  7. The Magnus Execution Backend
  8. II. Details on physics validation and additional benchmarks
  9. Additional Benchmarks
  10. Heavy Majorana Neutrino.
  11. General $Z'$ Benchmark.
  12. KK Graviton at a Lepton Collider.
  13. $U_1$ Leptoquark at a Muon Collider.
  14. Details on Physics Validation
  15. III. Installation and Usage
  16. ...and 8 more sections

Figures (3)

  • Figure 1: Decoupled architecture of ColliderAgent. A hierarchical cognitive reasoning engine assigns phenomenological tasks to specialized sub-agents equipped with dedicated Agent Skills, which communicate through a standardized CLI with Magnus, the unified execution backend hosting the underlying HEP tools. The framework translates natural-language input and standard physics notation into final phenomenological outputs such as kinematic distributions and exclusion limits.
  • Figure 2: Representative literature reproductions by ColliderAgent. (a) $m_{ej}$ distribution for $pp \to \text{LQ} \to e \, j$ at the LHC in the minimal scalar LQ model. (b) Normalized missing transverse energy distribution for $pp \to a W^\pm \gamma$ with $W^\pm \to \ell^\pm \nu$ at the LHC in the ALP EFT. (c) Expected $2\,\sigma$ exclusion contours for a $Z^\prime$ model from Drell-Yan production at the LHC. (d) $2\,\sigma$ exclusion contour for the $U_1$ LQ from the LHC mono-$\tau$ search. Panels (a)-(d) reproduce Refs. Buonocore:2020erbBrivio:2017ijeAccomando:2016sgeGreljo:2018tzh, respectively. See text for details.
  • Figure S1: Additional literature reproductions by ColliderAgent. (a) Production cross section for $pp \to \mu^\pm N$ at the LHC as a function of $m_N$. (b) Dilepton production cross section for a general $Z^\prime$ benchmark at the $13~\mathrm{TeV}$ LHC as a function of $M_{Z^\prime}$ for the SSM and $Z^\prime_\psi$ scenarios. (c) Cross section for $e^+e^- \to \mu^+\mu^-$ as a function of $\sqrt{s}$ in the Randall--Sundrum model, showing the resonant structure of the KK graviton tower. (d) 95% CL exclusion and $5\sigma$ discovery contours for the $U_1$ leptoquark benchmark from $\mu^+\mu^- \to b\bar{b}$ at a muon collider. Panels (a)-(d) reproduce Refs. Dev:2013wbaCMS:2021cttDavoudiasl:1999tfAsadi:2021gah, respectively. See text for details.