Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
This work addresses the challenge of real-world image generation involving culturally significant and long-tail factual concepts for applications requiring external knowledge grounding, representing an early exploration of agent-based modeling in this domain.
The paper tackles the problem of generating images for long-tail and knowledge-intensive concepts by introducing Unify-Agent, a unified multimodal agent that reframes image synthesis as an agentic pipeline, resulting in substantial improvements over its base model across diverse benchmarks and approaching the world knowledge capabilities of top closed-source models.
Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, they still rely primarily on frozen parametric knowledge, which makes them struggle with real-world image generation involving long-tail and knowledge-intensive concepts. Inspired by the broad success of agents on real-world tasks, we explore agentic modeling to address this limitation. Specifically, we present Unify-Agent, a unified multimodal agent for world-grounded image synthesis, which reframes image generation as an agentic pipeline consisting of prompt understanding, multimodal evidence searching, grounded recaptioning, and final synthesis. To train our model, we construct a tailored multimodal data pipeline and curate 143K high-quality agent trajectories for world-grounded image synthesis, enabling effective supervision over the full agentic generation process. We further introduce FactIP, a benchmark covering 12 categories of culturally significant and long-tail factual concepts that explicitly requires external knowledge grounding. Extensive experiments show that our proposed Unify-Agent substantially improves over its base unified model across diverse benchmarks and real world generation tasks, while approaching the world knowledge capabilities of the strongest closed-source models. As an early exploration of agent-based modeling for world-grounded image synthesis, our work highlights the value of tightly coupling reasoning, searching, and generation for reliable open-world agentic image synthesis.