PACE: Policy-Native Adaptive Decision Timing for Long-Horizon Reasoning
This work proposes PACE, a model-native VLM policy that jointly predicts what to execute and for how long under a hard decision budget, and evaluates PACE on four long-horizon environments spanning fully and partially observable settings and visual and textual modalities.
Chen Li, Zhan-Tao Yang, Fangyi Chen et al.
· 0 citations