Detecting Non-Optimal Decisions of Embodied Agents via Diversity-Guided Metamorphic Testing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Wenzhao, Tang, Yahui, Cheng, Mingfei, Tang, Wenbing, Zhou, Yuan, Liu, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915692333236224
author Wu, Wenzhao
Tang, Yahui
Cheng, Mingfei
Tang, Wenbing
Zhou, Yuan
Liu, Yang
author_facet Wu, Wenzhao
Tang, Yahui
Cheng, Mingfei
Tang, Wenbing
Zhou, Yuan
Liu, Yang
contents As embodied agents advance toward real-world deployment, ensuring optimal decisions becomes critical for resource-constrained applications. Current evaluation methods focus primarily on functional correctness, overlooking the non-functional optimality of generated plans. This gap can lead to significant performance degradation and resource waste. We identify and formalize the problem of Non-optimal Decisions (NoDs), where agents complete tasks successfully but inefficiently. We present NoD-DGMT, a systematic framework for detecting NoDs in embodied agent task planning via diversity-guided metamorphic testing. Our key insight is that optimal planners should exhibit invariant behavioral properties under specific transformations. We design four novel metamorphic relations capturing fundamental optimality properties: position detour suboptimality, action optimality completeness, condition refinement monotonicity, and scene perturbation invariance. To maximize detection efficiency, we introduce a diversity-guided selection strategy that actively selects test cases exploring different violation categories, avoiding redundant evaluations while ensuring comprehensive diversity coverage. Extensive experiments on the AI2-THOR simulator with four state-of-the-art planning models demonstrate that NoD-DGMT achieves violation detection rates of 31.9% on average, with our diversity-guided filter improving rates by 4.3% and diversity scores by 3.3 on average. NoD-DGMT significantly outperforms six baseline methods, with 16.8% relative improvement over the best baseline, and demonstrates consistent superiority across different model architectures and task complexities.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20083
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detecting Non-Optimal Decisions of Embodied Agents via Diversity-Guided Metamorphic Testing
Wu, Wenzhao
Tang, Yahui
Cheng, Mingfei
Tang, Wenbing
Zhou, Yuan
Liu, Yang
Software Engineering
Robotics
As embodied agents advance toward real-world deployment, ensuring optimal decisions becomes critical for resource-constrained applications. Current evaluation methods focus primarily on functional correctness, overlooking the non-functional optimality of generated plans. This gap can lead to significant performance degradation and resource waste. We identify and formalize the problem of Non-optimal Decisions (NoDs), where agents complete tasks successfully but inefficiently. We present NoD-DGMT, a systematic framework for detecting NoDs in embodied agent task planning via diversity-guided metamorphic testing. Our key insight is that optimal planners should exhibit invariant behavioral properties under specific transformations. We design four novel metamorphic relations capturing fundamental optimality properties: position detour suboptimality, action optimality completeness, condition refinement monotonicity, and scene perturbation invariance. To maximize detection efficiency, we introduce a diversity-guided selection strategy that actively selects test cases exploring different violation categories, avoiding redundant evaluations while ensuring comprehensive diversity coverage. Extensive experiments on the AI2-THOR simulator with four state-of-the-art planning models demonstrate that NoD-DGMT achieves violation detection rates of 31.9% on average, with our diversity-guided filter improving rates by 4.3% and diversity scores by 3.3 on average. NoD-DGMT significantly outperforms six baseline methods, with 16.8% relative improvement over the best baseline, and demonstrates consistent superiority across different model architectures and task complexities.
title Detecting Non-Optimal Decisions of Embodied Agents via Diversity-Guided Metamorphic Testing
topic Software Engineering
Robotics
url https://arxiv.org/abs/2512.20083