draft-training

TraceSpec is a framework linking LLM agent trajectory evaluation with adaptive draft training for speculative decoding, introducing a TraceSpec-Traj corpus and improving replay throughput by 12.5% to 22.6% over its DSpark base across multiple model sizes.

This paper shows that regenerating target model responses shrinks the gains that draft-training objectives like knowledge distillation provide in speculative decoding, replicating findings across vision-language (Qwen3-VL-8B) and text (Qwen3-4B) settings with multiple controls.