Abstract
Positive and negative space is a fundamental principle in visual composition, supporting visually coherent forms and layered semantic relationships. Generating such compositions is challenging because it requires coordinated control over two semantic concepts that share a common boundary. Although recent text-to-image models and multimodal large language models (MLLMs) have achieved strong performance in image generation and visual understanding, positive-negative space generation remains difficult, particularly under direct single-pass prompting. In this work, we present the \textbf{F}orm \textbf{a}nd \textbf{V}oid \textbf{A}gent (\textbf{FaV-A}), a multimodal agent designed for staged positive-negative space generation. FaV-A follows a progressive workflow: it first generates a base object, then analyzes its shape and spatial structure to identify candidate negative-space semantics, and finally produces compositional instructions for the final image generation stage. Experimental results and ablation analyses suggest that FaV-A provides a more effective framework than direct zero-shot MLLM baselines for producing visually coherent and semantically aligned positive-negative space compositions.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wang, S., Yang, J., Wang, X., Wang, X., & Dong, W. (2026). Form and Void: Entangled Composition through an Autonomous AI Agent. https://omanscience.com/en/articles/form-and-void-entangled-composition-through-an-autonomous-ai-agent
MLA 9
Wang, Shiwen, et al. "Form and Void: Entangled Composition through an Autonomous AI Agent." https://omanscience.com/en/articles/form-and-void-entangled-composition-through-an-autonomous-ai-agent.
Chicago (author–date)
Wang, Shiwen, Jian Yang, Xu Wang, Xincan Wang, and Weiming Dong. 2026. "Form and Void: Entangled Composition through an Autonomous AI Agent." https://omanscience.com/en/articles/form-and-void-entangled-composition-through-an-autonomous-ai-agent.
Harvard
Wang, S., Yang, J., Wang, X., Wang, X. and Dong, W. (2026) 'Form and Void: Entangled Composition through an Autonomous AI Agent', Available at: https://omanscience.com/en/articles/form-and-void-entangled-composition-through-an-autonomous-ai-agent.
Vancouver
Wang S, Yang J, Wang X, Wang X, Dong W. Form and Void: Entangled Composition through an Autonomous AI Agent. https://omanscience.com/en/articles/form-and-void-entangled-composition-through-an-autonomous-ai-agent
IEEE
S. Wang, J. Yang, X. Wang, X. Wang, and W. Dong, "Form and Void: Entangled Composition through an Autonomous AI Agent," https://omanscience.com/en/articles/form-and-void-entangled-composition-through-an-autonomous-ai-agent.