π0.5 在 BEHAVIOR-1K 上的推理设置配对评估：哪些策略真正有效

What Actually Matters? A Paired Evaluation of Inference Settings for $\pi_{0.5}$ on BEHAVIOR-1K

AI 导读

研究对基于 2025 BEHAVIOR Challenge 冠军方案微调的 π0.5 模型，在 BEHAVIOR-1K 全部 100 个任务上做了推理与数据采集策略的系统配对评估，该模型在公开测试集上 Q-score 为 0.39。结果显示，此前在小规模场景中提出的策略并不能均匀迁移到新环境和新任务。

正文 · 原文

View PDF HTML (experimental)

Abstract:Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been deployed in smaller-scale settings do not necessarily generalize to large-scale, diverse task suites. To address this gap, we conduct a systematic, paired evaluation of previously proposed inference and data-collection strategies across all 100 tasks. Our evaluation uses a fine-tuned $\pi_{0.5}$ model based on the 2025 BEHAVIOR Challenge winner, which achieves a Q-score of 0.39 on the public test set. These results show that proposed strategies do not transfer uniformly to new environments and tasks. Project page, videos, and detailed analysis: this https URL

Subjects:	Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as:	arXiv:2610.37917 [cs.RO]
	(or arXiv:2610.37917v1 [cs.RO] for this version)
	https://doi.org/10.48550/arXiv.2610.37917 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Samira Huber [view email]
[v1] Tue, 27 Oct 2026 19:59:45 UTC (18 KB)

来源：arXiv cs.AI · arxiv.org