Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
Quick Answer
This study introduces SPIRE, a framework for Page-level Slide Personalization (PSP) that formulates design intent learning as an inverse planning problem.
Quick Take
By employing structural denoising and reinforcement learning, SPIRE effectively refines slide designs without relying on specific tools, demonstrating superior performance in experiments.
Key Points
- SPIRE addresses the challenge of fine-grained slide design personalization.
- It formulates Page-level Slide Personalization as an inverse planning problem.
- The framework uses structural denoising to refine slide designs collaboratively.
- Reinforcement learning is employed to optimize the design process.
- Extensive experiments validate SPIRE's superior performance over existing methods.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | ECCV 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.00407 [cs.AI] |
| (or arXiv:2607.00407v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.00407 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianci Liu [view email]
[v1]
Wed, 1 Jul 2026 04:05:47 UTC (8,725 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.