EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses

EvoGen-Harness is a generator‑agnostic framework that enables multi‑responsibility evolution of image‑generation harnesses, allowing multiple external components to adapt around frozen generators. It introduces Trace, a method that aggregates evidence across stochastic runs, uses failure attribution as a search prior, and progressively re‑attributes residual failures to guide efficient evolution. The approach achieves significant performance gains on GenEval2, T2I‑CompBench++, and WISE, with high attribution recall, No‑Patch accuracy, and low regression rates.

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 Machine Learning.

• diffusion