InterleaveThinker: Reinforcing Agentic Interleaved Generation
- Published
- Source
- arXiv
- Paper number
- 399
- Field
- Computer Vision
- arXiv ID
- 2606.13679
Key points
- A three-agent Planner-Gen-Critic structure addresses visual over-reliance and error accumulation across steps.
- The Planner preserves the global goal by blocking intermediate feedback, and the Critic performs step-by-step evaluation and prompt refinement.
- The authors build high-quality datasets for Interleave-Planner-SFT-80k, Critic-SFT-112k, and Critic-RL-13k.
- A dual-reward strategy combining accuracy reward and step-level reward optimizes the whole trajectory through single-stage RL.
- With FLUX.2-klein as the base model, it improves WISE from 0.47 to 0.73 and RISE from 13.3 to 28.9, which reaches the level of Nano Banana and GPT-5.
- The image generator is replaceable, and the method works with both FLUX.2-klein and Qwen-Image-Edit.
Paper links
External research summaries. These are not HDATF publications or measured product results.