RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation

RSIgen is a task‑centric reciprocal self‑improvement framework for agentic visual generation that coordinates learning allocation, supervision refresh, and recursive curriculum construction. It employs Dynamic Responsibility Routing (DRR) to match interventions on evidence, inputs, and actions, selecting learning recipients and building compatible training targets. After generator updates, RSIgen re‑evaluates action utility with fixed branch inputs to refresh agent supervision, then constructs the next curriculum, yielding measurable gains on benchmarks and real‑user evaluations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• agents
• multimodal