Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation
Read the original on arXiv AI →The paper introduces Diffusion On-Policy Context Distillation (D-OPCD), a method that internalizes the benefits of an agentic harness—such as memory, skills, and iterative prompt refinement—into the weights of a diffusion model. By treating the agent‑improved prompt as privileged context, D-OPCD distills harness knowledge into the model, raising direct‑generation scores from 60.52 to 65.09 across four benchmarks. This internalization allows the harness to shed saturated skills and continue evolving, enabling a second round of skill evolution that further improves performance by 1.83 points.
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 AI.