2025_12_10.html

---
layout: talk
title: "For Provenance and with Provenance: The Role of Provenance Data in Agentic Workflows."
authors: Renan Souza  (Oak Ridge National Laboratory)
event_date: December 10, 2025
times: 11:00am PST / 2:00pm EST / 20:00 CEST
talk_number: 9
speakers: [renan_souza]
given: true
image: /images/talks/souza-banner.png
presentation: /files/talks/20251210-ProvenanceAgents-WCI.pdf
video: https://www.youtube.com/embed/TPAz4bbmW_0?si=JO3ARdoIYRji-TKl
---

The convergence of HPC, AI, and edge instrumentation is enabling "Autonomous 
Science," a paradigm shift capable of compressing discovery cycles from years to 
months. However, shifting to agent-driven workflows introduces risks regarding 
non-determinism and "dataflow contamination," which threaten scientific 
reproducibility. In this presentation, we argue that robust provenance data 
management is the critical enabler for trustworthy autonomous systems.

<br /><br />

We introduce a dual framework: "Provenance of Agents," which enforces accountability 
by systematically capturing agent decisions for root cause analysis, and 
"Provenance with Agents," which leverages Large Language Models (LLMs) as 
interfaces to democratize access to complex runtime data. Showcasing the Flowcept 
architecture and real-world applications in computational chemistry and adaptive 
additive manufacturing at Oak Ridge National Laboratory, we demonstrate how 
provenance safeguards the scientific method within autonomous loops. By ensuring 
transparency and enabling real-time human steering across the Edge-Cloud-HPC 
continuum , this approach removes manual bottlenecks, significantly reducing 
time-to-solution and accelerating the pace of trusted scientific discovery.