Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents

Researchers propose Traversal-as-Policy, a method that distills AI agent execution logs into Gated Behavior Trees (GBTs) to create safer, more efficient autonomous agents. The approach significantly improves success rates while reducing safety violations and computational costs across multiple benchmarks.