Wenxuan Wang

The authors propose Diffusion On-Policy Context Distillation (D-OPCD), which treats the agent-harness-produced prompt as privileged teacher context and supervises a student conditioned only on the original query at states along the student's own denoising trajectory, thereby writing prompt-mediated harness gains into the diffusion model's weights; paired with the Auto Skill Evolver (ASE), direct generation improves from 60.52 to 65.09 averaged over four benchmarks, and the updated generator under a skill-free harness slightly exceeds the original skill-equipped agent on average.

The authors propose Diffusion On-Policy Context Distillation (D-OPCD), which treats the agent-harness-produced prompt as privileged teacher context and supervises a student conditioned only on the original query at states along the student's own denoising trajectory, thereby writing prompt-mediated harness gains into the diffusion model's weights; paired with the Auto Skill Evolver (ASE), direct generation improves from 60.52 to 65.09 averaged over four benchmarks, and the updated generator under a skill-free harness slightly exceeds the original skill-equipped agent on average.