WAMJET：面向世界动作模型加速的智能体框架

View PDF HTML (experimental)

Abstract:World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive. Although existing acceleration techniques offer many ways to reduce this cost, selecting and composing them requires substantial engineering for each model and hardware platform. To tackle this bottleneck, we present WAMJET, an agentic harness that accelerates WAM inference by equipping coding agents with reusable optimization guidance and measurement and validation tools. WAMJET follows a bottleneck-driven workflow where the agent profiles inference, modifies targeted code, validates effects, and iteratively refines the acceleration stack as bottlenecks shift, while preserving action quality. Experiments span six WAMs, three coding agents, and two GPU architectures. WAMJET achieves up to 9.95x lossless speedup over upstream implementations. Approximation and hardware-aware optimization yield additional latency reductions, with comparable success rates. The results show that WAMJET can produce effective acceleration stacks for WAM deployment.

Comments:	8 pages, 3 figures, project page: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
Cite as:	arXiv:2610.03797 [cs.CV]
	(or arXiv:2610.03797v3 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.03797 arXiv-issued DOI via DataCite

Submission history

From: Lixin Liu [view email]
[v1] Thu, 1 Oct 2026 04:26:18 UTC (251 KB)
[v2] Tue, 6 Oct 2026 08:03:34 UTC (251 KB)
[v3] Wed, 7 Oct 2026 09:58:37 UTC (256 KB)