SOURCE-LINKED INTELLIGENCE

Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

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. We present Behavior-Skill, a benchmark that reformulates the learning and evaluation of long-horizon tasks around executable constituent skills. It contains 235,492 skill instances from 10,000 demonstrations across 50 household tasks and 34 semantic s

Read original source ↗ Open in workspace

recordType

paper

region

Global