arXiv 2606.13679 introduces InterleaveThinker, a dual-Agent pipeline that adds "interleaved generation" capability to any image generation model. The standout: with the InterleaveThinker pipeline, smaller image models match the quality of Nano Banana and GPT-5 on interleaved image-text generation.
The "interleaved generation" problem: "interleaved" image-text generation means the model produces a mix of text and images, where the text and images reference each other (e.g., "the first image shows X, then the text says Y, then the next image shows Z"). This is a hard task — most image models can only produce images in response to text prompts, not interleave text and images.
The InterleaveThinker fix: a dual-Agent pipeline with a "Planner" and a "Critic." The Planner decides the structure of the interleaved output (how many images, what text, what order), and the Critic checks the output for consistency and quality. The two Agents iterate until the output is good.
The benchmark: on the "interleaved generation" benchmark, InterleaveThinker-augmented SD3.5 scores 78.4, on par with Nano Banana (79.2) and GPT-5 (81.3). The base SD3.5 scores only 51.2 on the same benchmark, so the dual-Agent pipeline provides a 27-point improvement.
The bigger takeaway: "Agent pipelines" are the right way to add capabilities to existing models. The "one model does everything" approach is wasteful, and the "specialist Agent pipeline" approach is significantly more flexible. For the industry, this means the next round of model improvements will come from "Agent pipelines" that orchestrate existing models, not from "bigger models" that do everything internally.