Johns Hopkins APL Develops AI-Driven Wargaming to Accelerate Military Mission Analysis

Written by Jeremy Werner

Jeremy is an experienced journalist, skilled communicator, and constant learner with a passion for storytelling and a track record of crafting compelling narratives. He has a diverse background in broadcast journalism, AI, public relations, data science, and social media management.
Posted on 03/18/2025
In News

The Johns Hopkins Applied Physics Laboratory (APL) has unveiled a groundbreaking AI-driven wargaming capability designed to automate key aspects of military and government strategic exercises. The effort aims to significantly enhance the efficiency and impact of wargames, allowing decision-makers to test mission scenarios in a fraction of the time traditionally required.  

 

Wargames have long been used by military and national security agencies to simulate potential conflicts, improve preparedness, and refine decision-making processes. These exercises typically involve human analysts writing and coding various operational concepts into modeling tools such as the Advanced Framework for Simulation, Integration, and Modeling. APL researchers have now integrated large language models into this process, demonstrating that AI can successfully assume the analyst’s role, engaging dynamically with modeling simulations.  

 

“This work is a major step forward in wargaming,” said Andrew Mara, head of APL’s National Security Analysis Department. “Senior leaders in the Department of Defense have been seeking something like this for more than a decade, and I think we are finally at the point where the demand signal and the technology are in alignment.”  

 

APL has already tested the system in a three-player scenario featuring two friendly (blue) forces and one enemy (red) force, each making strategic decisions on troop movements, technology deployment, and operational tactics. The AI-driven approach has demonstrated the ability to set up new military scenarios in under two weeks, a dramatic improvement from the months-long preparation wargames traditionally require.  

 

The long-term vision for this capability is to develop a tool that can be used across different levels of decision-making, making wargaming insights more accessible. “Instead of a full-blown exercise that takes months of planning, we want to create a tool that allows decision-makers to run multiple wargame repetitions on their personal computers in a short time,” said APL analyst Kevin Mather.  

 

Beyond just expediting wargames, APL’s AI-driven platform is being developed to provide deeper insights by analyzing and explaining player decisions. This feature draws from another APL initiative, which is creating an AI assistant for human fighter pilots. The system interprets a pilot’s reasoning in real-time to enhance decision-making, and the same principle is being applied to wargaming.  

 

“The AI co-pilot has to form a model of what the pilot is trying to accomplish and why,” Mather explained. “We’re trying to apply that principle to wargaming so that stakeholders can better evaluate strategy.”  

 

Bob Chalmers, technical lead for the project, envisions a future where AI can generate thousands of strategic variations, providing commanders with an unprecedented range of options. “You can imagine an AI playing the role of a strategic planner, but instead of generating a handful of options, it could explore thousands,” Chalmers said. “Explainability will be key, so commanders can trust their AI subordinates.”  

 

The AI-powered wargaming capability will be demonstrated at APL’s ADEC conference on September 9-10, where experts will showcase its potential for military applications.

 

 

Need Help?

 

If you have questions or concerns about any global guidelines, regulations and laws, don’t hesitate to reach out to BABL AI. Their Audit Experts can offer valuable insight, and ensure you’re informed and compliant.

Subscribe to our Newsletter

Keep up with the latest on BABL AI, AI Auditing and
AI Governance News by subscribing to our news letter