Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision), making failures difficult to localize and attribute. Existing testing methods are largely system-level and provide limited insight into which capability deficiencies cause task failures. We propose a capability-oriented testing approach that enables failure detection and attribution by combining (1) adaptive test case generation via seed selection and mutation, (2) capability oracles for identifying capability-specific errors, and (3) a feedback mechanism that attributes failures to capabilities and guides further test generation. Experiments show that our method discovers more failure cases and more accurately pinpoints capability-level deficiencies than state-of-the-art baselines, providing more interpretable and actionable guidance for improving embodied agents.
@article{arxiv.2604.25161,
title = {Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents},
author = {Jianming Chen and Yawen Wang and Junjie Wang and Xiaofei Xie and Shoubin Li and Qing Wang and Fanjiang Xu},
journal= {arXiv preprint arXiv:2604.25161},
year = {2026}
}