http://english.cas.cn/newsroom/cas-in-media/202607/t20260723_1178934.shtml

At the 2026 World Artificial Intelligence Conference in Shanghai, a technical road map that natively embeds artificial intelligence across the full life cycle of advanced nuclear energy systems was unveiled.

The “AI for ADANES” road map was released at a forum themed “AI and Advanced Nuclear Energy for a Sustainable Intelligent Future”, organized by the CAS Institute of Modern Physics. It was the first WAIC forum dedicated to integrating AI with nuclear energy, bringing together discussions on AI, advanced nuclear systems, zero-carbon computing and energy security.

ADANES, short for Accelerator-Driven Advanced Nuclear Energy System, is a CAS-developed platform that integrates nuclear fuel breeding, spent fuel transmutation and power generation. Its subcritical operating mode fundamentally changes the safety logic of conventional nuclear reactors, while introducing new challenges in system coupling and long-term stable operation. CiADS, a national major science and technology infrastructure currently under construction, serves as the engineering verification platform for ADANES. Against this backdrop, the road map establishes a “triple-driving” paradigm that combines data, physics-based models and expert knowledge.

The AI architecture consists of five layers — a unified data infrastructure, physics-native world models, physical-system control, intelligent-agent coordination and continuous evolution — embedding AI throughout the system’s full life cycle, from design and commissioning to operation and maintenance.

The AI for ADANES Alliance was also launched at the forum, bringing together research institutes, nuclear enterprises, AI companies and financial institutions to jointly develop intelligent solutions and bridge the gap between scientific validation and industrial deployment.