2nd Workshop on Workflows, Intelligent Scientific Data, and Optimization for Automated Management
WISDOM 2026
Scientific automation is at the forefront of enabling faster, more reproducible discoveries in AI, exascale computing, and distributed environments. The WISDOM workshop provides a platform for researchers, developers, and practitioners to discuss advances in autonomous workflow design, intelligent data management, and scalable and agentic automation techniques. We are especially interested in innovative methods that integrate AI/ML to enhance the flexibility, efficiency, and reliability of scientific processes across heterogeneous environments.
Topics of interest include, but are not limited to:
- AI/ML-Driven & Agentic Workflow Automation
- Autonomous Experimental Control and Self-Driving Labs
- Multi-Facility Agentic Workflow Orchestration
- Digital Twins and Simulation-Based Workflows
- Workflow Performance Optimization and Fault Tolerance
- Time-Sensitive and Real-Time Scientific Workflows
- Human-on-the-Loop Automation
- Active Decision-Making
- Domain-Specific Scientific Workflow Applications
- Convergence of AI and Scientific Simulations
- Heterogeneous Computing for Workflow Automation
Important Dates
- Paper Submission Deadline:
July 31, 2026 - Camera-Ready Deadline:
August 21, 2026 - Workshop Date: September 29, 2026
Program
| Time (PDT) | Event |
|---|---|
| 9:00-9:05 | Welcome and Introduction to WISDOM 2026 |
| 9:05-10:05 | Keynote: Invited Talk Sagar Dolas (SURF) |
| 10:05-10:25 | Paper: Instrumentation vs. Observability: Provenance Capture Trade-offs in Agentic Workflows |
| 10:25-10:45 | Paper: Provenance-aware Scientific Workflow Management: the Copernicus MedFS Use Case |
| 10:45-11:00 | Session Wrap-up |
| 11:00-11:30 | Coffee Break |
| 11:30-11:50 | Paper: An AI-Assisted Migration Framework for Transforming Legacy Scientific Applications into Reusable Cloud-Based Workflows |
| 11:50-12:10 |
Paper:
An AI-Assisted Migration Framework for Transforming Legacy Scientific Applications into Reusable Cloud-Based Workflows
|
| 12:10-13:00 | Open Discussion |
| 13:00-14:00 | Lunch Break |
| 14:00-14:30 | Community Road Map : 15m for presentation + 15 min for discussion |
| 14:30-14:50 | Paper: ASH: Agent-Synthesized Hypotheses for Adversarial Scheduler Analysis |
| 14:50-15:10 | Paper: LLM-assisted Rule-based Policy Evaluation in Compute-to-Data Federated Workflows |
| 15:10-15:55 | Invited Talk: Anirban Mandal (RENCI) |
| 15:55-16:00 | Wrap-Up |
| 16:00-16:30 | Coffee Break |
Submission Guidelines
Submissions should be 8 pages (full papers including references), or 4 pages (short papers including references) following the IEEE Conference format found at: https://www.ieee.org/conferences/publishing/templates.
All submissions will receive at least three reviews. All submissions will be single-blind peer reviewed.
Selected full papers will receive a slot for an oral presentation. We strongly encourage authors to share code, data, and artifacts alongside their papers.
Program Committee
- Hena Ahmed (University of California, San Diego)
- Jared Coleman (Loyola Marymount University)
- Brian Etz (Oak Ridge National Laboratory)
- Amal Gueroudji (Argonne National Laboratory)
- Ketan Maheshwari (Oak Ridge National Laboratory)
- Spyro Nita (Edinburgh Parallel Computing Centre)
- Loïc Pottier (Lawrence Livermore National Laboratory)
- Raül Sirvent (Barcelona Supercomputing Center)
- Renan Souza (Oak Ridge National Laboratory)
Organizers
Steering Committee
