On a paper published January 21, 2026 researchers from MIT and NVIDIA explain how they have have developed a new system called Taming the Long Tail (TLT) to solve computational inefficiencies in training reasoning-heavy large language models. During standard training, many processors sit idle while waiting for the longest text sequences to finish generating, creating a massive resource bottleneck. The TLT system captures this wasted time by automatically training a secondary, lightweight drafter model on the fly to predict the primary model's outputs. This adaptive speculative decoding approach allows the larger model to verify multiple tokens at once, effectively doubling training speeds without losing any mathematical accuracy. By optimizing hardware usage, this method significantly reduces the energy and financial costs associated with developing advanced AI capable of complex logic and self-reflection. Source: January 21, 2026 Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter MIT, ETH Zurich, NVIDIA, UMass Amherst Qinghao Hu, Shang Yang, Junxian Guo, Xiaozhe Yao, Yujun Lin, Yuxian Gu, Han Cai, Chuang Gan, Ana Klimovic, Song Han https://arxiv.org/pdf/2511.16665 https://news.mit.edu/2026/new-method-could-increase-llm-training-efficiency-0226