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

• URL: http://arxiv.org/abs/2603.14553v1
• Date: Sun, 15 Mar 2026 19:00:52 GMT
• Title: An End-to-end Architecture for Collider Physics and Beyond
• Abstract summary: We present the first language-driven agent system capable of executing end-to-end phenomenology tasks.<n>The system is instantiated within a decoupled, domain-agnostic architecture for autonomous High-Energy Physics Colliderenology.<n>We validate the system on representative literature reproductions spanning leptoquark and axion-like-particle scenarios, higher-language effective operators, parton-level and detector-level analyses, and large-scale parameter scans.
• Score: 7.810285080897267
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation [68.13035350819901]
  PhysAgent is a framework that closes the loop among physical program generation, physics simulation, stage-specific verification, and targeted program repair.<n>Our framework produces more physically plausible videos, achieves better prompt alignment, and generalizes more effectively across diverse physical scenarios.
  arXiv  Detail & Related papers  (2026-07-17T08:55:09Z)
• An LLM System for Autonomous Variational Quantum Circuit Design [0.0]
  We introduce an autonomous agentic framework that employs large language models (LLMs) to conduct iterative quantum circuit designs.<n>We evaluate the framework on two tasks: quantum feature map construction for quantum machine learning and ansatz generation for variational quantum eigensolver applications in quantum chemistry.
  arXiv  Detail & Related papers  (2026-06-11T14:08:00Z)
• Experiments in Agentic AI for Science [0.005439329219803859]
  This paper details two novel frameworks for developing autonomous, agentic AI in scientific research.<n>The first agent, DeepTS/DeepCollector, automates the large-scale, extraction, and deduplication of time-series datasets.<n>The second, DeepScribe, is an autonomous presentation that converts visually dense, mathematically complex physics lectures into structured scientific reports.
  arXiv  Detail & Related papers  (2026-05-25T19:57:57Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• From vacuum amplitudes to qubits [0.0]
  High-energy colliders, exemplified by the CERN's Large Hadron Collider (LHC), constitute genuine quantum machines.<n>In alignment with Richard Feynman's foundational vision for quantum computing, collider physics emerge therefore as a prime candidate for quantum simulations.
  arXiv  Detail & Related papers  (2026-03-12T14:14:19Z)
• Perceptual Self-Reflection in Agentic Physics Simulation Code Generation [0.0]
  We present a framework for generating physics simulation code from natural language descriptions.<n>Key innovation is perceptual validation, which analyzes rendered animation frames using a vision-capable language model.<n>We evaluate the system across seven domains including classical mechanics, fluid dynamics, thermodynamics, electromagnetics, wave physics, reaction-diffusion systems, and non-physics data visualization.
  arXiv  Detail & Related papers  (2026-02-12T15:48:33Z)
• Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale [50.33952894976367]
  We use context-free grammars to generate synthetic corpora that are faithful and computationally efficient proxies for web-scale text corpora.<n>We investigate the emergence of three mechanistic phenomena: induction heads, function vectors, and the Hydra effect, under our designed data generation process.<n>Our findings suggest that hierarchical structures in the data generation process serve as the X-factor in explaining the emergence of these phenomena.
  arXiv  Detail & Related papers  (2026-02-04T14:49:13Z)
• Generalizable Geometric Prior and Recurrent Spiking Feature Learning for Humanoid Robot Manipulation [90.90219129619344]
  This paper presents a novel R-prior-S, Recurrent Geometric-priormodal Policy with Spiking features.<n>To ground high-level reasoning in physical reality, we leverage lightweight 2D geometric inductive biases.<n>For the data efficiency issue in robotic action generation, we introduce a Recursive Adaptive Spiking Network.
  arXiv  Detail & Related papers  (2026-01-13T23:36:30Z)
• Physics-Informed Tree Search for High-Dimensional Computational Design [1.7499338683160512]
  High-dimensional design spaces underpin a wide range of physics-based modeling computational tasks in science and engineering.<n> Conventional global engines and robustnesss struggle in such settings due to the exponential scaling of design spaces.<n>We present a physics-informed Monte Tree Tree (MCTS) framework for continuous search scientific design.
  arXiv  Detail & Related papers  (2026-01-10T06:01:57Z)
• Seismology modeling agent: A smart assistant for geophysical researchers [14.28965530601497]
  This paper proposes an intelligent, interactive workflow powered by Large Language Models (LLMs)<n>We introduce the first Model Context Protocol (MCP) server suite for SPECFEM.<n>The framework supports both fully automated execution and human-in-the-loop collaboration.
  arXiv  Detail & Related papers  (2025-12-16T14:18:26Z)
• Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects [59.51185639557874]
  We introduce Kinematify, an automated framework that synthesizes articulated objects directly from arbitrary RGB images or textual descriptions.<n>Our method addresses two core challenges: (i) inferring kinematic topologies for high-DoF objects and (ii) estimating joint parameters from static geometry.
  arXiv  Detail & Related papers  (2025-11-03T07:21:42Z)
• Agentic AI for Multi-Stage Physics Experiments at a Large-Scale User Facility Particle Accelerator [0.26097841018267615]
  Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans.<n>In a representative machine physics task, we show that preparation time was reduced by two orders of magnitude relative to manual scripting.<n>Results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies.
  arXiv  Detail & Related papers  (2025-09-21T22:11:03Z)
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN [51.02649432050852]
  PELICAN is a novel permutation equivariant and Lorentz invariant aggregator network. We present a study of the PELICAN algorithm architecture in the context of both tagging (classification) and reconstructing (regression) Lorentz-boosted top quarks. We extend the application of PELICAN to the tasks of identifying quark-initiated vs.gluon-initiated jets, and a multi-class identification across five separate target categories of jets.
  arXiv  Detail & Related papers  (2023-07-31T09:08:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.