Preprint
Aug 2026
Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks
Behavior-Skill is presented, a benchmark that reformulates the learning and evaluation of long-horizon tasks around executable constituent skills and introduces trajectory-level and skill-level metrics to characterize policy capability beyond aggregate task success.
Chun-Yun Ma, Lun Luo, Xing-Jian Luo et al.
· 0 citations