Description
The Decentralized Artificial Intelligence through Controlled Emergence (DICE) program aims to develop the theory and algorithms for decentralized coordination and local inference control to enable a scalable, adaptive, and resilient collective of heterogeneous AI agents. The program seeks to harness the scalability and adaptability of self-organizing systems while minimizing risks and ensuring that the collective behavior remains predictable and aligned with intended outcomes. The DICE program will use simulation environments to demonstrate DICE architectures in Department of War-relevant use-cases, targeting measurable gains in scalability, adaptability, and resilience against both benign failures and adversarial attacks.
Key aspects of the program include:
• Developing a decentralized AI architecture suitable for rapidly evolving, unpredictable, and contested environments
• Enabling AI agents to dynamically form teams using peer-to-peer coordination to execute complex missions
• Ensuring local inference control on each AI agent to maintain alignment with commander’s intent over the long term
• Expanding and leveraging the theory of self-organizing systems and distributed consensus algorithms
• Controlling the internal reasoning and inference of AI foundation models at inference-time