ePubs

The open archive for STFC research publications

Full Record Details

Persistent URL http://purl.org/net/epubs/work/64997511
Record Status Checked
Record Id 64997511
Title Agentic AI for Simulations Workflows
Contributors
Abstract Workflows play critical role in science and engineering. Develop- ment of robust simulations workflows is challenging due to the need to link multiple models, often coming from different sources and in absence of data exchange standards. We propose an agentic AI framework for building simulation workflows using large lan- guage models (LLMs) with domain knowledge driving algorithms discovery and code generation. We believe that such approach can achieve significant reduction in workflows development time and more generally be used in automated and autonomous scientific discovery.
Organisation STFC , HC
Keywords multi-scale simulation , code generation , generative AI , AI for code , agentic workflow , foundation models , natural language generation , workflows , LLM
Funding Information
Related Research Object(s):
Licence Information:
Language English (EN)
Type Details URI(s) Local file(s) Year
Presentation Presented at The International Conference for High Performance Computing, Networking, Storage, and Analysis 2025 (SC25), St. Louis, MO, USA, 16-21 Nov 2025. https://sc25.conf…rksa101&sess=sess208 2025