AI RESEARCH
Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents
arXiv CS.AI
•
ArXi:2603.05517v1 Announce Type: cross Autonomous LLM agents fail because long-horizon policy remains implicit in model weights and transcripts, while safety is retrofitted post hoc. We propose Traversal-as-Policy: distill sandboxed OpenHands execution logs into a single executable Gated Behavior Tree (GBT) and treat tree traversal -- rather than unconstrained generation -- as the control policy whenever a task is in coverage.