Auto-CoT writes its own chain-of-thought demos — cluster the questions, pick one per cluster, and diversity beats similarity

1Key Takeaways

• Few-shot chain-of-thought is the reliable way to get a model to reason: show it a handful of worked examples and it copies the habit.
• The catch is where those demonstrations come from.
• Manual few-shot CoT (the hand-crafted kind) makes you author each step-by-step example — slow to write, doesn't scale to new task families, and it quietly bakes in one person's phrasing and blind spots.
• Auto-CoT (Zhang et al., 2022) keeps the accuracy and throws out the hand-labour, by having the model build its….