# Harness–Model Co-Evolution

The work introduces CoTrace, a harness-aware data recipe for alternating model–harness co-evolution that explicitly governs trajectory routing, provenance matching, and curriculum refresh: execution failures are routed to harness synthesis while policy supervision uses only verified successes matched to the adopted runtime. On the 102-task Tmax promotion split, Qwen3.5-9B advances from 78 to 88 solved tasks under supervised fine-tuning and reaches 90 with an online reinforcement variant, whereas much larger corpora pooled across sibling harnesses yield no accepted model update.

The work introduces CoTrace, a harness-aware data recipe for alternating model–harness co-evolution that explicitly governs trajectory routing, provenance matching, and curriculum refresh: execution failures are routed to harness synthesis while policy supervision uses only verified successes matched to the adopted runtime. On the 102-task Tmax promotion split, Qwen3.5-9B advances from 78 to 88 solved tasks under supervised fine-tuning and reaches 90 with an online reinforcement variant, whereas much larger corpora pooled across sibling harnesses yield no accepted model update.

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.