| title | Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising |
|---|---|
| authors | Tianci Liu, Zihan Dong, Linjun Zhang, Haoyu Wang, jing Gao, Emre Kiciman, Ranveer Chandra, Wei-Ting Chen |
| date | 2026-07-01 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.00407 |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | 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. |
cite
@misc{liu2026personalization,
title={Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising},
author={Tianci Liu and Zihan Dong and Linjun Zhang and Haoyu Wang and jing Gao and Emre Kiciman and Ranveer Chandra and Wei-Ting Chen},
year={2026},
eprint={2607.00407},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.00407}
}