Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation

Generating complete, coherent, and usable 3D indoor scenes from natural language requires strong $\mathbf{\text{design}}\mathbf{\text{intelligence}}$: the ability to design high-quality scenes and critique their quality. However, existing approaches either rely on general-purpose models lacking domain-specific design experience or learn from static scenes. In this work, we introduce $\mathbf{\text{Scene-Designer}}$, an agentic framework that learns design intelligence through complementary design and critique experiences. We construct two datasets: $\mathbf{\text{Scene-OTA-35K}}$, which provides Observation–Thought–Action supervision for learning scene design and efficient error correction, and $\mathbf{\text{Scene-OTC-15K}}$, which provides Observation–Thought–Critic supervision for learning scene quality critique across physical validity, functional correctness, and layout coherence. Based on these experiences, we propose $\mathbf{\text{Scene-GRPO}}$, a Critic-guided GRPO framework that improves design decisions and reduces unnecessary trial-and-error corrections. Extensive experiments demonstrate that Scene-Designer achieves superior performance in physical validity, functional correctness, and layout coherence, while the learned Scene-Critic significantly outperforms general-purpose models in scene critique. Moreover, test-time Critic guidance further improves scene generation, showing that the Critic can provide useful guidance beyond training. Additional analysis suggests a trend of mutual enhancement between scene design and critique abilities.