Towards Agentic AI on Particle Accelerators

• URL: http://arxiv.org/abs/2409.06336v4
• Date: Tue, 02 Sep 2025 19:53:40 GMT
• Title: Towards Agentic AI on Particle Accelerators
• Authors: Antonin Sulc, Thorsten Hellert, Raimund Kammering, Hayden Hoschouer, Jason St. John,
• Abstract summary: This paper envisions a decentralized multi-agent framework for accelerator control powered by Large Language Models (LLMs)<n>We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components.
• Score: 0.26097841018267615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show three examples, where we demonstrate the viability of such architecture.

Related papers

• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• Toward a Fully Autonomous, AI-Native Particle Accelerator [0.342658286826597]
  We propose that future facilities be designed through artificial intelligence (AI) co-design.<n>Rather than retrofitting AI onto human-centric systems, we envision facilities designed from the ground up as AI-native platforms.<n>This roadmap aims to guide the accelerator community toward a future where AI-driven design and operation deliver unprecedented science output and reliability.
  arXiv  Detail & Related papers  (2026-02-19T16:49:36Z)
• AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent [57.10083973844841]
  AgentArk is a novel framework to distill multi-agent dynamics into the weights of a single model.<n>We investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios.<n>By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents.
  arXiv  Detail & Related papers  (2026-02-03T19:18:28Z)
• AgentEvolver: Towards Efficient Self-Evolving Agent System [51.54882384204726]
  We present AgentEvolver, a self-evolving agent system that drives autonomous agent learning.<n>AgentEvolver introduces three synergistic mechanisms: self-questioning, self-navigating, and self-attributing.<n>Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines.
  arXiv  Detail & Related papers  (2025-11-13T15:14:47Z)
• 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)
• Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities [117.49715661395294]
  Data structurization can play a promising role by transforming intricate and disorganized data into well-structured forms.<n>This survey presents a first systematic review of how graphs can empower AI agents.
  arXiv  Detail & Related papers  (2025-06-22T12:59:12Z)
• SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence [28.042768995386037]
  We propose SwarmAgentic, a framework for fully automated agentic system generation.<n>SwarmAgentic constructs agentic systems from scratch and jointly optimize agent functionality and collaboration.<n>We evaluate our method on six real-world, open-ended, and exploratory tasks involving high-level planning, system-level coordination, and creative reasoning.
  arXiv  Detail & Related papers  (2025-06-18T17:54:55Z)
• OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis [70.39500621448383]
  Open-world mobile manipulation task remains a challenge due to the need for generalization to open-ended instructions and environments.<n>We propose a novel multi-modal agent architecture that maintains multi-view scene frames and agent states for decision-making and controls the robot by function calling.<n>We highlight our fine-tuned OWMM-VLM as the first dedicated foundation model for mobile manipulators with global scene understanding, robot state tracking, and multi-modal action generation in a unified model.
  arXiv  Detail & Related papers  (2025-06-04T17:57:44Z)
• Toward Super Agent System with Hybrid AI Routers [19.22599167969104]
  Super agents can fulfill diverse user needs, such as summarization, coding, and research.<n>This paper presents a design of the Super Agent System powered by the hybrid AI routers.<n>With advances in multi-modality models and edge hardware, we envision that most computations can be handled locally, with cloud collaboration only as needed.
  arXiv  Detail & Related papers  (2025-04-11T00:54:56Z)
• Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems [0.0]
  A multi-agent AI model is used to automate the discovery of new metallic alloys. We focus on the NbMoTa family of body-centered cubic (bcc) alloys, modeled using an ML-based interatomic potential. By synergizing the predictive power of GNNs with the dynamic collaboration of LLM-based agents, the system autonomously navigates vast alloy design spaces.
  arXiv  Detail & Related papers  (2024-10-17T17:06:26Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [117.94654815220404]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine. G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)
• GAIA: A General AI Assistant for Intelligent Accelerator Operations [0.0]
  Large-scale machines like particle accelerators are usually run by a team of experienced operators. In case of a particle accelerator, these operators possess suitable background knowledge on both accelerator physics and the technology comprising the machine. In this work the reasoning and action (ReAct) prompting paradigm is used to couple an open-weights large language model (LLM) with a high-level machine control system framework.
  arXiv  Detail & Related papers  (2024-05-02T15:06:18Z)
• Agent AI: Surveying the Horizons of Multimodal Interaction [83.18367129924997]
  "Agent AI" is a class of interactive systems that can perceive visual stimuli, language inputs, and other environmentally-grounded data. We envision a future where people can easily create any virtual reality or simulated scene and interact with agents embodied within the virtual environment.
  arXiv  Detail & Related papers  (2024-01-07T19:11:18Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)
• A Comprehensive Performance Study of Large Language Models on Novel AI Accelerators [2.88634411143577]
  Large language models (LLMs) are being considered as a promising approach to address some of the challenging problems. Specialized AI accelerator hardware systems have recently become available for accelerating AI applications.
  arXiv  Detail & Related papers  (2023-10-06T21:55:57Z)
• GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models [20.844806635710526]
  GPT4AIGChip is a framework intended to democratize AI accelerator design by leveraging human natural languages. This work is the first to demonstrate an effective pipeline for LLM-powered automated AI accelerator generation.
  arXiv  Detail & Related papers  (2023-09-19T16:14:57Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  Diffusion model (DM) recently achieved huge success in various scenarios including offline reinforcement learning. We propose MADiff, a novel generative multi-agent learning framework to tackle this problem. Our experiments show the superior performance of MADiff compared to baseline algorithms in a wide range of multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)
• Autonomous Control of a Particle Accelerator using Deep Reinforcement Learning [2.062593640149623]
  We describe an approach to learning optimal control policies for a large, linear particle accelerator. The framework consists of an AI controller that uses deep neural nets for state and action-space representation. Initial results indicate that we can achieve better-than-human level performance in terms of particle beam current and distribution.
  arXiv  Detail & Related papers  (2020-10-16T04:02:01Z)
• CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion [0.0]
  We present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. We use Generative Adrial Networks to adapt high-level controls, such as speed and heading, to action distributions that correspond to the original animations. Further fine-tuning through the deep reinforcement learning enables the agent to recover from unseen external perturbations while producing smooth transitions.
  arXiv  Detail & Related papers  (2020-05-07T07:18:57Z)
• Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous [66.6895109554163]
  Underlying the human ability to align goals with other agents is their ability to predict the intentions of others and actively update their own plans. We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous.
  arXiv  Detail & Related papers  (2020-03-15T19:49:20Z)

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.