SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
For researchers and practitioners in text-to-image generation, this work addresses the challenge of faithfully realizing complex visual intents by maintaining persistent commitment tracking.
The paper tackles the problem of complex image generation where multiple requirements (semantic commitments) must be tracked across the generation lifecycle. The proposed SCOPE framework achieves 0.60 EGIP on the Gen-Arena benchmark, outperforming all baselines, and also achieves strong results on WISE-V (0.907) and MindBench (0.61).
While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many requirements must be tracked across grounding, generation, and verification. We refer to these requirements as semantic commitments and formalize their lifecycle discontinuity as the Conceptual Rift, where commitments may be locally resolved or checked but fail to remain identifiable as the same operational units throughout the generation lifecycle. To address this, we propose SCOPE, a specification-guided skill orchestration framework that maintains semantic commitments in an evolving structured specification and conditionally invokes retrieval, reasoning, and repair skills around unresolved or violated commitments. To evaluate commitment-level intent realization, we introduce Gen-Arena, a human-annotated benchmark with entity- and constraint-level specifications, together with Entity-Gated Intent Pass Rate (EGIP), a strict entity-first pass criterion. SCOPE substantially outperforms all evaluated baselines on Gen-Arena, achieving 0.60 EGIP, and further achieves strong results on WISE-V (0.907) and MindBench (0.61), demonstrating the effectiveness of persistent commitment tracking for complex image generation.