AI4SE & SE4AI Workshop 2026

• Edward Balleisen, Provost and Executive Vice President for Academic Affairs, The George Washington University

• Rocio Bauer, Assistant Deputy, Acquisition and Systems Management (Data, Engineering & Software), Office of the Assistant Secretary of the Army (Acquisition, Logistics and Technology)

• Tom McDermott, Chief Technical Officer, Systems Engineering Research Center

Followed by a networking break from 10:45 am – 11:00 am

• Case Study: Speed and Innovation Through Spec-Driven Development: Building an Agentic ISO 15288 Platform at Lockheed Martin, Melissa Bradshaw, Lockheed Martin
• Swarm-Engineered Ontologies for Systems Engineering: A Multi-Agent Pipeline Across SE Knowledge-Engineering Projects, Paul Wach and Joe Gregory, University of Arizona
• Workflow Architecture: A New Construct in the Age of AI-enabled Systems, Bryce Huffman, The George Washington University 
• Mediagents: Leveraging System of Systems Engineering Mediators to Inhibit Unwanted Emergent Behavior in AI Pipelines, Luke Douglas, The George Washington University
• From Autonomous Agents to Agentic Enterprises: A Systems Engineering Framework for Trust, Governance and Progressive Assurance, Carlo Lipizzi, Stevens Institute of Technology
• Insight Session: Automating Systems Simulation at Scale: An LLM Pipeline for Multi-Framework Modeling, Raz Saremi, Stevens Institute of Technology

• Case Study: Enhancing Risk-Informed Decision Making Through LLM-Based Concern Analysis in the Human Landing System Program, Nipa Phojanamongkolkij, National Aeronautics and Space Administration
• Establishing a Learned Operational Reference Environment (LORE): A Knowledge Repository and Process Improvement Testbed Using GenAI.mil, Allison Ledford, Auburn University
• Simulating Stakeholder Engagement: A Virtual Human Approach to Upskilling the Systems Engineering Workforce, Bryant Baldwin and Neel Parekh, University of South Alabama and University of Florida
• The MESH Environment: Multi-level Evaluation of Sociotechnical HAI-workflows, Zoe Szajnfarber, The George Washington University
• STOIC Road to a Hive Operating System: ZynWorld as the Operational Testbed, Paul Wach, University of Arizona
• Insight Session: Speed and Innovation in AI4SE: Using an LLM-Enabled Virtual Systems Engineering Workshop to Architect a Complex Testbed in One Day, Keith Godwin, Torch Technologies

• Case Study: Risk Trace: Human-in-the-Loop AI for Requirements-to-Risk-Control Traceability in Medical Device Systems Engineering, Esteban Solorzano Zeledon, Boston Scientific
• A Digital Engineering Ecosystem Chatbot based on Semantically Rich Knowledge Graphs, Thomas Hagedorn, Systems Engineering Research Center
• AI-Enabled Mission Engineering, Michael Pennock, MITRE
• AI Cognitive Assistant for Traceable Interaction with MBSE Behavior Models, Lance Sherry, George Mason University
• Learning for Mission Resilience: A Digital Engineering Framework for Intelligent System-of-Systems Coordination, Taylan Topcu, Virginia Tech
• Insight Session: Human-AI Workflows for MBSE Translation, John Materum, Nick Noonan and David Ruddell, David Ruddell Sandia National Laboratories

• Mary Chasko, Chief Medical Information Officer, Mid-Atlantic Permanente Medical Group
• Melissa Koide, Chief Executive Officer and Director, FinRegLab
• Amanda Muller, Northrop Grumman and Mission Systems AI Lead, Northrop Grumman
• Moderator: Zoe Szajnfarber, Chief Scientist, Systems Engineering Research Center 

Followed by a networking break from 2:45 pm – 2:55 pm

• Case Study: Assessing Consistency with the AI Ethical Principles, Benjamin Werner, Army DEVCOM Armaments Center
• Oversight Coupling and Appropriate Reliance in Agentic AI Systems, Sarah Starr, The George Washington University
• Beyond Adoption: How Adaptive AI Feedback Shapes Trust and Design Improvement, Ting Liao, Stevens Institute of Technology
• Contract-Based Agentic Systems Engineering: Delegation as Quotient for Trusted Cyber-Physical System Design, Ryan Matheu, University of Maryland
• Accounting for Uncertainty in Safety & Reliability of AI-enabled Systems, Lance Sherry, George Mason University
• Insight Session: The Vibe Coding Epidemic and Spec Driven Development As a Remedy, Melissa Bradshaw, Lockheed Martin

• Case Study: AI Circuite Breaker, Paul Wach, University of Arizona
• AI as the Semantic Bridge in the Model-Based Quality Digital Thread, Priya Sukumaran, Boeing
• Privacy-aware Multi-Agents for System of Systems, Nil Hande Ergin, Pennsylvania State University
• Understanding Human-AI Interactions in Complex AI-Driven Autonomous Systems: Implications of Trust, Interpretability, and Ethical Reliability in Critical Missions, Bryan Mesmer, The University of Alabama in Huntsville
• Common-Cause Analysis of Fault Trees with AI-Based Systems, John Shortle, George Mason University

• Case Study: Field Level Maintenance Archietecture (FLMA): A Lifecycle Systems Engineering Framework for AI-Enabled Army Field Maintenance, James Parham, Army Strong PM Consultants
• AI-Enabled Modeling and Simulation for Airspace Safety Analysis: A Digital Framework for Synthetic Flight Track Generation, Validation, and Collision Risk Assessment, Shahab Aref, George Mason University
• From AI Tools to AI Teammates: Situating and Evaluating Scheduling Capability for Small and Medium-Sized Manufacturers, Peter Denno, National Institute of Standards and Technology
• Does One Model Fit All? Personalized vs. Generalized Machine Learning Models for Workload Prediction in Human-in-the-Loop Systems, Md Doulotuzzaman Xames, Virginia Tech
• Reinforcement Learning for Autonomous Equipment Optimization via Digital Twins: A Comprehensive Framework for Industry 4.0, Priya Sukumaran, Boeing
• Insight Session: CRISP: A Systems Design Thinking Approach for Prompt Engineering, Robert Riley, Air Force Research Laboratory

Demo Sessions

• Assistive and Agentic AI for Git-Native SysML v2 Modeling with SysGit, Charles “Zeke” Brechtel, SysGit
• Integrating AI4SE Methods to Enhance Synthesis of System Architectures, Eric Dano, The George Washington University
• insightLM: An MCP-Native Desktop Workbench for LLM-Assisted Systems Engineering, John DeHart, Avian
• Looking Glass: the Key to Digital Transformation, Isaac Gang, George Mason University
• AIR Tool: An Automated Causal Discovery and Inference Pipeline for Software Analytics, Linda Parker Gates, Carnegie Mellon University Software Engineering Institute
• Davinci: Live Demonstration of Agentic AI Operating Directly on a Systems Engineering Knowledge Graph, Chris Helmerich, Celedon Solutions
• AEGIS: A Prototype Environment for Turning Structurally Opaque Systems of Systems into Computable Governability, Mohamed Mogahed, Stevens Institute of Technology
• GenGroves: An AI Copilot That Lowers the Barrier to SysML v2 and Digital Engineering, Mary Nerayo, Virginia Tech National Security Institute
• AI-Native MBSE Platform for Accelerating Systems Engineering Workflows with SysMLv2, Sebastian Völkl, Dalus

Poster Presentations

• A Mechanistic Digital Twin for Predicting Physiological and Cognitive Performance to Support Operational Decision-Making, Oyshik Bhowmik, George Mason University
• Systems Engineering for Trustworthy Embedded AI in Autonomous Systems of Systems: A Resilient-by-Design Architecture for Contested Environments, Jaewon Kim, Texas A&M University
• The Important Role of “Context” in the Practical Design and Operation of Systems that Mix Human and Artificial Intelligence, Lance Sherry, George Mason University
• Digital Twins for AI/ML Training and Testing: A Systematic Review, Ana Wooley, The University of Alabama in Huntsville

• Tara Sinclair, Professor and Chair of the Department of Economics, The George Washington University

• Cynthia Perazzo, SES, Executive Director, Enterprise & Systems Integration Center, Army DEVCOM Armaments Center

Followed by a networking break from 10:30 am – 10:45 am

• Case Study: Understanding Department of War Responsible AI Needs & Requirements: An examination of DoW’s AI Ethics, Policies, and Directives for the Safe, Secure, and Trustworthy Adoption of AI-Enabled Systems, Logan Mailloux and Vincent Santore, Lockheed Martin
• What is Different About AI? Understanding the Nature of Risk for Stronger Operational Capability, Valerie Sitterle, Systems Engineering Research Center
• Why AI Risk Frameworks Are Hard to Adopt: A NIST AI RMF Stress Test of Governance Translation in AI-Enabled Decision Systems, Joseph Simons, The George Washington University
• Demonstrating Justified Confidence in Autonomous Weapon Systems for DoD Directive 3000.09 Approvals, Benjamin Schumeg, Army DEVCOM Armaments Center
• Beyond the Model: A Layer-by-Layer Map of AI Governance Mechanisms, Inducted from Safety-Critical Domains (Aviation, Pharmaceuticals, Food Safety), Zoe Szajnfarber, The George Washington University
• Insight Session: Systems Architecture Modeling for Human-AI Intensive Systems, Heidi Perry, Massachusetts Institute of Technology Lincoln Laboratory

• Case Study: MLQP Card Wizard: Guided Qualification Cards for ML Dataset and Model TEVV, Haley Green, ARiA
• From Data-to-Model to Model-to-Model: Systems Engineering and T&E Velocity in the Era of Foundation-Model-Based AI, Tyler Cody, University of Virginia
• Evaluating Methods to Generate Mission-Relevant Small Language Models, Emma Meno, Virginia Tech National Security Institute
• Metadata-Driven Test and Evaluation of LLM Agents, Nil Hande Ergin, Pennsylvania State University
• Mission-Aligned Large Language Models, Ethan Thorley, United States Military Academy
• Insight Session: Native AI Integration For Model-Based Systems Engineering: Lessons Learned from an LSP and Knowledge-grounded Experimentation Platform, Colin Dempsey, Carnegie Mellon University Software Engineering Institute

• Case Study: AI-Assisted Transformation of Operational Recordings into Reviewable Evidence, Robert DeMarco, Army DEVCOM Armaments Center
• Dependency Graph Topology and Classical Compressibility Diagnostics for AI Value in Systems Engineering Models, Bob Hill, The George Washington University
• An AI Based Sectionalized Semantic Traceability Framework for Policy Documents with Applications to Department of Defense Problems, Jose Ramirez Marquez, Stevens Institute of Technology
• Assessing the Impact of AI-Based Summarization on Information Relevance and Engagement, Donald Koban, United States Military Academy
• Data Interoperability Foundations for Being AI-Ready, Valerie Sitterle, Systems Engineering Research Center
• Insight Session: From Structural Opacity to Computable Architectures: Recognizing Emergent Systems of Systems for AI-Assisted Systems Engineering, Mohamed Mogahed, Stevens Institute of Technology

• Daniel Brookshier, Solutions Architect, Dassault 3DS
• Chris Helmerich, Chief Technical Officer, Celedon Solutions
• Dale Ormond, Senior Advisor, Kompozition
• Benjamin Schumeg, Software Quality Technical Lead, Army DEVCOM Armaments Center  
• Moderator: Tom McDermott, Chief Technical Officer, Systems Engineering Research Center

Followed by a networking break from 2:40 pm – 2:55 pm

• Benchmarking of LLM-Based Requirement Quality Evaluation and a Knowledge-Based Hybrid Prototype for Pushing the Boundary of Trustworthiness, Jannatul Shefa, Virginia Tech
• Absent by Design: A Review of AI-Assisted Requirements Engineering in ERP Implementations, Navendu Bhatt, Stevens Institute of Technology

• Evaluating Engineering Knowledge Leakage in AI-Assisted Systems Engineering Workflows, Yinchien Huang, Purdue University
• Governing AI-Supported Design and Verification Boundaries in Systems Engineering: A Three-Axis Interpretation of the V-Model, Toshiyasu Watanabe, Waseda University

• Introducing Automation to Reform The Model Change Request Process, Salvatore Latella, Army DEVCOM Armaments Center
• An Agentic System for Cyber Resilience, Mary Nerayo, Virginia Tech National Security Institute