將個性化視為逆向規劃：透過結構化去噪學習潛在設計意圖以實現自主投影片生成

摘要

投影片設計需要同時個性化投影片主題與頁面佈局。然而，現有的基於AI代理的方法在處理細粒度的頁面級設計時仍面臨挑戰。這些方法過度依賴於預先指定的範本或使用者詳細的指令，因而無法捕捉到潛在的設計意圖，導致頁面級投影片個性化（PSP）問題仍未獲解決。為填補此缺口，本研究將PSP形式化為一個反向規劃問題。我們提出在不假設任何特定執行工具（如PowerPoint、Beamer）知識的情況下學習設計意圖。然而，放棄對這些工具的控制使得問題難以透過端到端方式進行最佳化。為克服此困難，我們提出SPIRE，一個近似求解PSP的原則性框架。透過刻意破壞乾淨投影片的視覺結構，SPIRE建立一個可驗證的去噪任務，在此任務中兩個代理經由強化學習（RL）共同學習逐步修正可執行的設計。我們證明了結構去噪是PSP的一個一致替代目標，且多代理公式能嚴格降低RL中的策略梯度變異數。大量實驗結果展現了SPIRE的優越性。

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.