Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

ArXi:2605.13511v1 Announce Type: cross In-context learning (ICL) adapts large language models (LLMs) to new tasks by conditioning on nstrations in the prompt without parameter updates. With long-context models, many-shot ICL can use dozens to hundreds of examples and achieve performance comparable to fine-tuning, yet current understanding of its scaling behavior is largely derived from non-reasoning tasks. We study many-shot chain-of-thought in-context learning (CoT-ICL) for reasoning and show that standard many-shot rules do not transfer.