Description
Zoom Link, ID: 934 7906 6977, Code: 522727
We will describe progress along simulation based inference in the precision era.
Artificial intelligence has rapidly become an integral part of high-energy physics, evolving from specialized machine-learning tools for individual analysis tasks toward increasingly general and large-scale models for scientific data. As this field enters a new stage, an important question is not only how to build more powerful models, but also what we can learn from the models themselves. In...
This talk introduces LQCDMaster, an AI agent framework that turns natural-language physics requests into executable lattice QCD workflows. Combining physics planning, PyQUDA code generation, automated debugging, and GPU execution, it supports a range of hadronic observables. We present its architecture and assess its reliability through numerical validation against expert-written reference programs.
This talk provides an overview of recent advances in agentic AI and deep learning at BESIII. I will introduce DrSai, a multi-agent system designed for autonomous end-to-end physics analysis—from natural-language goals to data selection, statistical inference, and systematic evaluation—with emphasis on reliability, traceability, and human-AI collaboration. I will also overview our deep-learning...
Modern particle-physics detectors require continuous monitoring, rapid anomaly detection, and timely expert response. This contribution presents an Agentic AI framework for intelligent detector operations, integrating sensor information, automated anomaly detection, contextual interpretation, and decision support.
Environmental and operational sensor data are analysed using Agentic AI tools...
Recent coding agents can execute increasingly complex scientific workflows, but realistic high-energy physics (HEP) analyses remain nonlinear and require domain expertise, systematic validation, reproducible evidence, and human scientific judgment. We present a human-governed, skill-oriented workflow for agent-assisted HEP analysis. Native coding agents perform planning, coding, computation,...
