Workshop: AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC
Authors: Kartik Shinde (Predii Inc.), Tirthankar Ghosal (Oak Ridge National Laboratory), Sreekantam Sai Venkat and Siddhant Senapati (Predii Inc.), Sanjay Das (Oak Ridge National Laboratory), Tilak Kasturi (Predii Inc.), Khaled Ibrahim (Lawrence Berkeley National Laboratory), Hugo Hernandez (spinTwo LLC), Kanad Basu (Rensselaer Polytechnic Institute), and Sukumar Rangan (AMD)
Abstract: Agentic systems answer operational queries over HPC telemetry for domain scientists who cannot verify the responses. Trustworthiness requires recovering the facts telemetry supports and refusing the questions it does not, since no facility instruments everything it runs. Existing architectures are built for capability on the assumption that reliability follows, and inference remains untested. We compare five configurations, one tool-using agent and four multi-agent designs varying only in inter-agent communication and shared-state structure, on EPIQ, a new benchmark of 55 multi-intent queries over Fugaku job telemetry with 119 verifiable facts and 25 unanswerable sub-questions. The single agent recovers the most facts (84.9%) but refuses least. Pairing peer messaging with typed dialogue-act fields refuses most (92.0%) while matching single-agent recall within noise, at 2.5 times the tokens. Refusal follows whether agents exchange results at all; typing those exchanges recovers recall. Agent count explains neither. Recall and refusal must be designed for separately.
Back to AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC Archive Listing
Back to Full Workshop Archive Listing