Research and ACM SRC Posters Archive

VisKnacks: Agentic ParaView Visualization on HPC


Poster Type: Research Posters

Author: Nicholas Synovic (Loyola University Chicago), George K. Thiruvathukal (Loyola University Chicago), Manish Mathai (University of Oregon), Mangjiao Han (Argonne National Laboratory), Joseph Insley (Argonne National Laboratory), Janet Knowles (Argonne National Laboratory), Victor Mateevitsi (Argonne National Laboratory), Silvio Rizzi (Argonne National Laboratory), Michael E. Papka (Argonne National Laboratory)

Abstract: Artificial intelligence can assist in prototyping scientific visualizations. To assist visualization experts, we introduce VisKnacks, an autonomous ParaView visualization agent enabled by large language models (LLMs). VisKnacks integrates multi-agent orchestration, retrieval-augmented generation, and containerized rendering services for high performance computing (HPC) systems while remaining compatible with existing agent harnesses. The system supports hybrid workflows in which ParaView rendering is distributed to HPC resources while pipeline creation and iterative refinement remain local. We present the system overview, initial benchmarks, visualization quality benchmarks, and lessons learned from deploying this system.

Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF


Back to Poster Archive Listing