个性化即逆规划：通过结构去噪学习自主幻灯片生成的潜在设计意图

摘要

幻灯片设计需要同时个性化定制的演示文稿主题和页面布局。然而，当前基于AI智能体的方法难以处理细粒度的页面级设计。这些方法完全依赖预设模板或用户冗长指令，无法捕捉潜在的设计意图，导致页面级幻灯片个性化（PSP）问题尚未解决。为填补这一空白，本文提出将PSP形式化为逆向规划问题。我们提出一种无需假设具体执行工具（如PowerPoint、Beamer）知识的设计意图学习方法。然而，放弃对这些工具的控制使得端到端优化问题变得棘手。为此，我们提出SPIRE——一种近似求解PSP的原理性框架。通过人为破坏干净幻灯片的视觉结构，SPIRE构建了一个可验证的去噪任务，使得两个智能体通过强化学习（RL）协作改进可执行设计方案。我们证明结构去噪是PSP的一致替代性方法，且多智能体公式严格降低了RL中策略梯度的方差。大量实验表明SPIRE的优越性。

English

Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespecified templates or user verbose instructions, they fail to capture latent design intents, leaving Page-level Slide Personalization (PSP) unresolved. To close this gap, this work formulates PSP as an inverse planning problem. We propose to learn a design intent without assuming any knowledge of the specific executing tools (e.g., PowerPoint, Beamer) being used. However, relinquishing control over these tools makes the problem intractable to optimize end-to-end. To overcome this, we propose SPIRE, a principled framework to solve PSP approximately. By intentionally corrupting the visual structures of clean slides, SPIRE creates a verifiable task to denoise the corruption, whereby two agents learn to collaboratively refine executable designs via reinforcement learning (RL). We present a proof that structural denoising is a consistent surrogate for PSP, and that the multi-agent formulation strictly reduces policy gradient variance in RL. Extensive experiments demonstrate the superiority of SPIRE.