Jul 2026
World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
Adversarial World Modeling (AWM) is proposed, a theoretically grounded multi-agent self-play fine-tuning framework that generates transferable adversarial interactions and yields a robust planner that achieves competitive closed-loop performance in both nominal and highly interactive long-tail scenarios.
Tong Nie, Yuewen Mei, Jun-Lin He et al.
· arXiv.org · 1 citation