AI tutoring outperforms in-class active learning: an RCT introducing a novel research-based design in an authentic educational setting

Which beliefs it touches

• C5 Step-based tutoring pushes against it

  Structured GPT-4 tutor (step-by-step scaffolding, pre-written solutions) vs in-class active learning, crossover RCT, Harvard physics: post-test effect 0.63 SD (regression; 0.73–1.3 quantile), immediate test only, not vs human tutoring. Points against C5's bound that LLM tutors have not been shown to reach this level; queued for the nightly run, not a verdict.