# Decomposed Prompting

> Decomposed prompting breaks a complex task into simpler sub-tasks, each delegated to its own prompt, model call, or symbolic function, with a controller prompt that decides which handler to call next.

- Identifier: PTL-0114
- Category: Reasoning Elicitation
- Canonical URL: https://protologue.com/t/decomposed-prompting/
- Also known as: DecomP, modular prompting
- Introduced: 2022

## Description

Each sub-task handler can be optimized, given its own examples, or replaced with code, and handlers can call further decompositions recursively. Compared with a single chain-of-thought prompt, this modularity helps on tasks with steps that models do poorly in one pass, such as long-input processing or symbolic manipulation.

## Related terms

- [Least-to-Most Prompting](https://protologue.com/t/least-to-most-prompting/)
- [Prompt Chaining](https://protologue.com/t/prompt-chaining/)
- [Orchestrator-Workers](https://protologue.com/t/orchestrator-workers/)
- [Program-Aided Language Models](https://protologue.com/t/program-aided-language-models/)

## Sources

- Khot et al. (2022). Decomposed Prompting: A Modular Approach for Solving Complex Tasks. https://arxiv.org/abs/2210.02406

## Cite this entry

Protologue. (2026). Decomposed Prompting. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0114). https://protologue.com/t/decomposed-prompting/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)