Research

Paper

TESTING March 12, 2026

Chunk-Boundary Artifact in Action-Chunked Generative Policies: A Noise-Sensitive Failure Mechanism

Authors

Rui Wang

Abstract

Action chunking has become a central design choice for generative visuomotor policies, yet the execution discontinuities that arise at chunk boundaries remain poorly understood. In a frozen pretrained action-chunked policy, we identify chunk-boundary artifact as a noise-sensitive failure mechanism. First, artifact is strongly associated with task failure (p < 1e-4, permutation test) and emerges during the rollout rather than only as a post-hoc symptom. Second, under a fixed observation context, changing only latent noise systematically modulates artifact magnitude. Third, by identifying artifact-related directions in noise space and applying trajectory-level steering, we reliably alter artifact magnitude across all evaluated tasks. In hard-task settings with remaining outcome headroom, the success/failure distribution shifts accordingly; on near-ceiling tasks, positive gains are compressed by policy saturation, while the negative causal effect remains visible. Overall, we recast boundary discontinuity from an unavoidable execution nuisance into an analyzable, noise-dominated, and intervenable failure mechanism.

Metadata

arXiv ID: 2603.11642
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-12
Fetched: 2026-03-13 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11642v1</id>\n    <title>Chunk-Boundary Artifact in Action-Chunked Generative Policies: A Noise-Sensitive Failure Mechanism</title>\n    <updated>2026-03-12T08:10:19Z</updated>\n    <link href='https://arxiv.org/abs/2603.11642v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11642v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Action chunking has become a central design choice for generative visuomotor policies, yet the execution discontinuities that arise at chunk boundaries remain poorly understood. In a frozen pretrained action-chunked policy, we identify chunk-boundary artifact as a noise-sensitive failure mechanism. First, artifact is strongly associated with task failure (p &lt; 1e-4, permutation test) and emerges during the rollout rather than only as a post-hoc symptom. Second, under a fixed observation context, changing only latent noise systematically modulates artifact magnitude. Third, by identifying artifact-related directions in noise space and applying trajectory-level steering, we reliably alter artifact magnitude across all evaluated tasks. In hard-task settings with remaining outcome headroom, the success/failure distribution shifts accordingly; on near-ceiling tasks, positive gains are compressed by policy saturation, while the negative causal effect remains visible. Overall, we recast boundary discontinuity from an unavoidable execution nuisance into an analyzable, noise-dominated, and intervenable failure mechanism.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <published>2026-03-12T08:10:19Z</published>\n    <arxiv:comment>13 pages, 5 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Rui Wang</name>\n    </author>\n  </entry>"
}