Corpus Agentis
The field book to agent ecosystems
The field book to agent ecosystems
Design · Topologies

Map-Reduce

Fan-out across data partitions in parallel; a reduce node aggregates the outputs. Built-in parallelism.

Map-Reduce agent topology diagram

A map-reduce agent splits a job across partitions, processes each in parallel, then aggregates the partial results in a reduce step. It is the classic parallel shape: the same operation applied independently to many pieces, then combined, so throughput scales with the number of workers. It suits embarrassingly-parallel work over large inputs, where the pieces do not depend on each other. In anatomy terms it is a coordinator that fans work out to identical scoped cores and folds their outputs back together.

In the anatomy

A coordinator maps the input across N identical worker cores in parallel, then a reduce core aggregates their outputs; workers are independent and hold no shared state; the perimeter gates the coordinator's writes.

At a glance
PatternMap-Reduce
State modelstateless
Common use cases
  • ·Processing large document or data sets in parallel.
  • ·Fan-out extraction or summarisation over many sources, then merge.
  • ·Any embarrassingly-parallel workload with an aggregation step.
Strengths
  • ·Throughput scales with the worker count.
  • ·Simple, well-understood shape.
  • ·Workers are independent: no cross-talk.
  • ·Bounded lifecycle: map, reduce, done.
Weaknesses
  • ·Only fits work that partitions cleanly.
  • ·The reduce step can become the bottleneck.
  • ·Stragglers slow the whole job.
  • ·No cross-partition reasoning during the map phase.
Basis
  • Internal research (Scalarity), Agents vs Operators / Agent Archetypes v2 · unvalidated

Description, use cases and trade-offs: Field Book analysis, synthesised from established agent-architecture literature.