Buffer of Thoughts: keep a library of reusable thought-templates, not past answers — retrieve, instantiate, distil back

1Key Takeaways

• Ask a language model a fresh word problem and plain chain-of-thought works it out from zero every single time, re-deriving the same method and re-making the same slips.
• Few-shot does a little better — it pastes a couple of look-alike question→answer pairs — but it transfers surface form, not method, so a problem that reads differently yet needs the same reasoning slips right past the match.
• Buffer of Thoughts (Yang et al., 2024) keeps a meta-buffer of reusable thought-templates distilled from….