Form and Void: Entangled Composition through an Autonomous AI Agent

arXiv:2610.02045v1 Announce Type: new 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 extbf{F}orm extbf{a}nd extbf{V}oid extbf{A}gent (extbf{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.

Related

• Less Is More: Balancing Positive and Negative Space in Visual Concept Blending
• Instance-Enriched Semantic Maps for Visual Language Navigation
• PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps

Source: arXiv cs.CV | 2026-10-02