Research Agenda
My long-term research goal is to build adaptive AI systems that can persist, coordinate, and remain steerable in complex human environments. I approach this through AI agent infrastructure, multi-agent simulation, reinforcement learning, and social dynamics.
Persistent AI Agents
- How should agents represent memory, skills, tasks, and long-horizon context?
- How can tool-use agents operate safely under explicit user permissions and recover from failure?
- What infrastructure is needed for agents that collaborate across sessions, tools, and people?
Multi-Agent Coordination
- How do coordination protocols shape emergent behavior?
- How should agents communicate uncertainty, negotiate task allocation, and avoid harmful interference?
- How can simulations reveal failure modes before deployment?
Adaptive Systems and Social Dynamics
- How do learned policies interact with human-like behavior?
- How do beliefs, incentives, and local interactions produce collective outcomes?
- How can adaptive systems remain transparent and controllable?