# MapReduce for Agents

> Split an oversize task into independent chunks, process each in parallel, then aggregate.

- **Category**: Agentic AI
- **Subcategory**: Planning & Control Flow
- **Canonical URL**: https://designpattern.fyi/patterns/map_reduce/

---

## Description
**Intent**: Split an oversize task into independent chunks, process each in parallel, then aggregate.
**Context**: A team needs to apply a language model to an input that is too large for a single call — twelve hundred pages of vendor contracts, a million-row table, hundreds of documents to summarise — or to a task that decomposes naturally into independent pieces (per row, per document, per section). Per-piece work is short; what is hard is the scale.
**Solution**: - Map: split the input into chunks; process each independently with a per-chunk LLM call. - Reduce: aggregate intermediate answers via a structured information protocol that surfaces cross-chunk dependencies, plus a confidence-calibration step to resolve conflicting answers between chunks.


## Use Cases
- Input is too large for any single context window to handle well.
- Chunks are mostly independent and a structured reducer can resolve cross-chunk dependencies.
- A confidence-calibration step can reconcile conflicting per-chunk answers.





## Trade-offs


### Advantages

- Scales to inputs orders of magnitude larger than the context window.

- Embarrassingly parallel; latency scales with longest chunk, not total input size.




### Considerations & Drawbacks

- Cross-chunk dependencies must be modelled explicitly in the reduce step.

- Reduce stage can become the new bottleneck at very high chunk counts.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/map-reduce-for-agents/)