Dual-Frontier: When Can an Agent Trust Its World Model?
Learned world models are becoming essential to general-purpose agents: by predicting action consequences, they support planning and decision-making while reducing reliance on costly trial and error. This reliance creates a fundamental ambiguity: when a world-model-guided decision fails, the trajectory alone may not rev...
Hua-Tai Zhu, Qiang Chen, Zi-Qian Kou et al.
· 0 citations