Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks
技术动态
来源：arXiv cs.RO发布时间待核实
arXiv:2608.30536v1 Announce Type: new Abstract: Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of multiple constituent skills. Existing benchmarks, however, still rely primarily on full-task rollouts and aggregate task-level metrics, making intermediate failures difficult to observe and analyze.