[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"glossary-least-to-most-prompting::en":3,"gloss-cluster-least-to-most-prompting::en":23,"gloss-next-least-to-most-prompting::en":9},{"slug":4,"category":5,"name":6,"definition":7,"meta_desc":8,"faq":9,"schema_markup":9,"related":10},"least-to-most-prompting","prompt-eng","Least-to-Most Prompting","Least-to-most prompting tackles a hard problem by explicitly breaking it into a chain of simpler sub-problems, then solving them in order so each answer feeds the next. Introduced by Zhou et al. (2022), it differs from plain chain-of-thought in two ways: decomposition is a distinct first stage, and the sub-problems are solved sequentially with earlier solutions inserted into later prompts. The payoff shows up on tasks that require \"compositional generalization\" — where the test cases are harder or longer than anything in your examples, like multi-step word problems, symbolic manipulation, or applying a policy with several nested conditions. For SaaS builders, it's a good pattern when a single prompt keeps skipping steps or collapsing under complexity: instead of one mega-instruction, you have the model list the sub-questions, then answer them one at a time. The cost is more tokens and more calls, so reserve it for genuinely multi-step logic rather than simple lookups where zero-shot already works.","Least-to-most prompting decomposes a hard problem into simpler sub-problems, then solves them in order so each answer feeds the next.",null,[11,14,17,20],{"slug":12,"name":13},"chain-of-thought-prompting","Chain-of-Thought Prompting",{"slug":15,"name":16},"plan-and-solve-prompting","Plan-and-Solve Prompting",{"slug":18,"name":19},"prompt-chaining","Prompt Chaining",{"slug":21,"name":22},"self-ask-prompting","Self-Ask Prompting",[24,28,31,34,36,39,42,45,48,51,54,57],{"slug":25,"category":5,"name":26,"updated_at":27},"analogical-prompting","Analogical Prompting","2026-08-24T02:46:37+00:00",{"slug":29,"category":5,"name":30,"updated_at":27},"automatic-prompt-optimization","Automatic Prompt Optimization",{"slug":32,"category":5,"name":33,"updated_at":27},"chain-of-density","Chain of Density (CoD)",{"slug":12,"category":5,"name":13,"updated_at":35},"2026-08-24T02:46:36+00:00",{"slug":37,"category":5,"name":38,"updated_at":27},"chain-of-verification","Chain-of-Verification",{"slug":40,"category":5,"name":41,"updated_at":35},"chunking","Chunking",{"slug":43,"category":5,"name":44,"updated_at":35},"constrained-decoding","Constrained Decoding",{"slug":46,"category":5,"name":47,"updated_at":35},"context-stuffing","Context Stuffing",{"slug":49,"category":5,"name":50,"updated_at":35},"delimiter","Delimiter",{"slug":52,"category":5,"name":53,"updated_at":27},"directional-stimulus-prompting","Directional Stimulus Prompting",{"slug":55,"category":5,"name":56,"updated_at":27},"emotion-prompting","Emotion Prompting",{"slug":58,"category":5,"name":59,"updated_at":35},"few-shot-prompting","Few-Shot Prompting"]