跳到正文
arXiv cs.AI· Junyi Shen, Yao Lu·· 2 小时前AI 评分42

CodeReel:用精确帧复用与阻塞感知调度加速代码生成视频 Agent

CodeReel: Accelerating Code-to-Video Agents with Exact Frame Reuse and Blocking-Aware Scheduling

AI 导读

arXiv 论文提出 CodeReel,一个无需训练的执行层,通过按绘制命令为帧建立精确键实现复用,并以阻塞感知调度优先运行检查、并行启动渲染,加速编程 Agent 的代码到视频流程。

正文 · 原文

View PDF HTML (experimental)

Abstract:Coding agents make videos by writing and refining programs in a build--inspect--edit loop. A finished film costs a median of $2.85 in model calls and 11 minutes, over a third of that time in builds that block the agent. We find that much of this time is avoidable, for two reasons. First, 37.5% of the frames of a session's later films were drawn before, many shifted in time or inside an edited scene. Second, half of the builds stop at a check, where the agent needs only the verdict, but which builds stop is unknown until the checks finish. We present CodeReel, a training-free execution layer behind agents' existing commands. Exact frame reuse keys each frame by its drawing commands, regardless of its position in time, and reuses each frame whose key recurs. Blocking-aware scheduling runs the checks first and starts the render alongside them, at idle priority, unless the session's recent builds make a pass unlikely. Scheduling spends CPU to answer sooner and reuse returns it; exact keys let later versions use frames rendered for a failed one as the agent thinks. We introduce EditLoop, a benchmark of replayable agent sessions whose films are checked against renders from scratch. On it, CodeReel cuts the agent's wait by 36.3% against Rebuild, a warm pipeline with parallel rendering, and by 57.9% against Sequential, today's step-by-step pipeline. On time-shifting edits its reuse renders 43.9%, close to the 43.0% whose pixels are new, while Manim-style caching renders 99.8%. With real agents, the median wait per build is 0.62x Rebuild's in Claude Code, on topics never used in development, and 0.67x in Codex CLI. The gain holds for five models and two frameworks.
Comments: 19 pages, 8 figures, 14 tables
Subjects: Multimedia (cs.MM); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC)
Cite as: arXiv:2611.22967 [cs.MM]
  (or arXiv:2611.22967v1 [cs.MM] for this version)
  https://doi.org/10.48550/arXiv.2611.22967

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Junyi Shen [view email]
[v1] Tue, 17 Nov 2026 15:52:15 UTC (636 KB)

来源:arXiv cs.AI · arxiv.org