Saved in:
Bibliographic Details
Main Authors: Gao, Bo, Liu, Chang, Miao, Yuyang, Ma, Siyuan, Lim, Ser-Nam
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16541
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913041754357760
author Gao, Bo
Liu, Chang
Miao, Yuyang
Ma, Siyuan
Lim, Ser-Nam
author_facet Gao, Bo
Liu, Chang
Miao, Yuyang
Ma, Siyuan
Lim, Ser-Nam
contents Recent advancements in Large Generative Models (LGMs) have revolutionized multi-modal generation. However, generating illustrated storybooks remains an open challenge, where prior works mainly decompose this task into separate stages, and thus, holistic multi-modal grounding remains limited. Besides, while safety alignment is studied for text- or image-only generation, existing works rarely integrate child-specific safety constraints into narrative planning and sequence-level multi-modal verification. To address these limitations, we propose BookAgent, a safety-aware multi-agent collaboration framework designed for high-quality, safety-aware visual narratives. Different from prior story visualization models that assume a fixed storyline sequence, BookAgent targets end-to-end storybook synthesis from a user draft by jointly planning, scripting, illustrating, and globally repairing inconsistencies. To ensure precise multi-modal grounding, BookAgent dynamically calibrates page-level alignment between textual scripts and visual layouts. Furthermore, BookAgent calibrates holistic consistency from the temporal dimension, by verifying-then-rectifying global inconsistencies in character identity and storytelling logic. Extensive experiments demonstrate that BookAgent significantly outperforms current methods in narrative coherence, visual consistency, and safety compliance, offering a robust paradigm for reliable agents in complex multi-modal creation. The implementation will be publicly released at https://github.com/bogao-code/BookAgent/tree/main.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16541
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration
Gao, Bo
Liu, Chang
Miao, Yuyang
Ma, Siyuan
Lim, Ser-Nam
Computer Vision and Pattern Recognition
Recent advancements in Large Generative Models (LGMs) have revolutionized multi-modal generation. However, generating illustrated storybooks remains an open challenge, where prior works mainly decompose this task into separate stages, and thus, holistic multi-modal grounding remains limited. Besides, while safety alignment is studied for text- or image-only generation, existing works rarely integrate child-specific safety constraints into narrative planning and sequence-level multi-modal verification. To address these limitations, we propose BookAgent, a safety-aware multi-agent collaboration framework designed for high-quality, safety-aware visual narratives. Different from prior story visualization models that assume a fixed storyline sequence, BookAgent targets end-to-end storybook synthesis from a user draft by jointly planning, scripting, illustrating, and globally repairing inconsistencies. To ensure precise multi-modal grounding, BookAgent dynamically calibrates page-level alignment between textual scripts and visual layouts. Furthermore, BookAgent calibrates holistic consistency from the temporal dimension, by verifying-then-rectifying global inconsistencies in character identity and storytelling logic. Extensive experiments demonstrate that BookAgent significantly outperforms current methods in narrative coherence, visual consistency, and safety compliance, offering a robust paradigm for reliable agents in complex multi-modal creation. The implementation will be publicly released at https://github.com/bogao-code/BookAgent/tree/main.
title BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.16541