Gemini 1.5などで可能になったMany shot（500 shotなど）などの効果の分析。性能が上がる例が多いが「On some tasks (e g , code verifier, planning), we did observe slight performance deterioration beyond a certain number of shots.」とのこと。Reinforced ICL、Unsupervised ICL という人間を介さないICLも検証していて「We found that, for problem-solving domains where human-generated rationales are expensive to obtain, Reinforced and Unsupervised ICL can obtain strong performance when compared to ICL with human data.」とのこと。