USC Institute for Creative Technologies

Human-inspired
Adaptive Teaming Systems

We build autonomous synthetic characters and intelligent agents for military training simulations — teammates that perceive, reason, and adapt the way people do.

Multi-Agent RL Cognitive Architectures LLM Agents Human-AI Teaming Scenario Generation Simulation Environments

Research

Multi-Agent Reinforcement Learning

Training teams of agents that coordinate, navigate, and fight as a unit — from graph-based terrain reasoning and GNN policies to organizational hierarchies and emergent tactical behaviors like ambush and cover.

Cognitive Architectures & Human-like Behavior

Synthetic characters grounded in how people actually think — theory of mind, cognitive modeling with Sigma and PySigma, and decision-making that remains believable to the humans training alongside it.

LLM-driven Agents & Evaluation

Language models as reasoning engines for embodied agents — and rigorous benchmarks for what they can and cannot do, from gameplay understanding to deception detection and egocentric tactical reasoning.

Simulation & Scenario Generation

The environments where it all comes together — the RIDE rapid integration and development environment, geo-specific terrain, and automated generation of training scenarios.

News

Apr 2026

GamePlayQA paper is accepted to the ACL 2026 Main Conference

Apr 2026

Volkan Ustun presented our paper titled 'Egocentric Team AI: Enabling Tactical Reasoning from the Operator's View' at the Advances in AI-Enabled Tactical Autonomy: From Sensing to Execution workshop, AAAI Spring Symposium

Dec 2025

DECOY was presented at the Winter Simulation Conference

Dec 2025

We presented our work on Scenario Generation at I/ITSEC