GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- Published
- Source
- arXiv
- Paper number
- 212
- Field
- Computer Vision
- arXiv ID
- 2605.21605
Key points
- Failure memory is a lesson about how to avoid failure.
- The prompt pool divides 20,000 requests into knowledge-anchored categories, such as facts and events, and quality-anchored categories, such as spatial composition and text layout.
- Teacher trajectories are created by using a strong model to generate initial successful trajectories and then having a VLM judge inspect them for correctness.
Paper links
External research summaries. These are not HDATF publications or measured product results.