---
schema: formation.domain/v0.1
kind: domain
visibility: public
canonical_url: https://topologyindex.com/domains/documents.md
community_ranking: null
description: 'Task shapes common in document work, the published findings tagged with the domain and the starters in it. Hypotheses and attributed findings, never a ranking.'
domain: documents
domain_index: /domains/index.md
evaluable_here: []
findings:
  - citations:
      - compared_against: 'Open-source and commercial long-context LLMs reading the full input'
        direction: helped
        pattern: map_reduce
    source_id: arxiv:2410.09342
    url: https://arxiv.org/abs/2410.09342
  - citations:
      - compared_against: 'Prior book-length summarization systems'
        direction: helped
        pattern: map_reduce
    source_id: arxiv:2109.10862
    url: https://arxiv.org/abs/2109.10862
  - citations:
      - compared_against: 'Incremental updating of a running summary'
        direction: mixed
        pattern: map_reduce
    source_id: arxiv:2310.00785
    url: https://arxiv.org/abs/2310.00785
  - citations:
      - compared_against: 'Sequential Chain-of-Agents over the same chunks'
        direction: hurt
        pattern: map_reduce
    source_id: arxiv:2406.02818
    url: https://arxiv.org/abs/2406.02818
  - citations:
      - compared_against: 'Human annotator judgments of equal-quality outputs'
        direction: hurt
        pattern: council
    source_id: arxiv:2404.13076
    url: https://arxiv.org/abs/2404.13076
  - citations:
      - compared_against: 'Naive baselines without debate, such as a single consultant'
        direction: helped
        pattern: debate
    source_id: arxiv:2402.06782
    url: https://arxiv.org/abs/2402.06782
  - citations:
      - compared_against: 'Fixed-context LLMs without memory management'
        direction: helped
        pattern: successor_handoff
    source_id: arxiv:2310.08560
    url: https://arxiv.org/abs/2310.08560
findings_page: /domains/documents/findings.md
path: /domains/documents.md
pattern_index: /patterns/index.md
product_api_version: v1
schema_version: v0.1
shapes:
  - example: 'summarizing or extracting from a document longer than one context, part by part'
    shape: splits_into_independent_parts
  - example: 'reading a collection of documents across several sessions'
    shape: outlasts_one_context
starters:
  - name: documents-successor-handoff
    path: /starters/documents-successor-handoff/0.1.0.md
    task_classes:
      - documents.long_document_review
    version: '0.1.0'
task_class_prefix: documents.
title: 'Which multi-agent pattern for long documents?'
---

# Which multi-agent pattern for long documents?

**Short answer:** for summarizing or extracting from a document longer than one context, part by part, start with [map_reduce](/patterns/map_reduce.md); avoid it when the parts depend on each other.
Other shapes of document work start as the table below says.
Hypotheses from the [decision guide](/patterns/index.md), not a ranking, and nothing here is
measured; [published findings](/domains/documents/findings.md) keep the unfavourable ones.

Reading, summarizing and answering questions over long documents and collections of them.

The `documents` domain of the [task domains](/domains/index.md): task classes that start
with `documents.`.

## Task shapes common in this domain

Hypotheses about the work, each a row of the decision guide. Choose by the shape of your task,
not by the domain.

- `splits_into_independent_parts`: summarizing or extracting from a document longer than one context, part by part
- `outlasts_one_context`: reading a collection of documents across several sessions

Where to start by the shape of the task. Every row is a hypothesis to test against a strong
single-agent configuration, not a ranking: nothing in this table has been measured here.

| If the task… | Start with | Consider next | Avoid when |
| --- | --- | --- | --- |
| splits into independent parts | [map_reduce](/patterns/map_reduce.md) | [independent_workers](/patterns/independent_workers.md) | the parts depend on each other |
| outlasts one context window or session | [successor_handoff](/patterns/successor_handoff.md) | [shared_ledger](/patterns/shared_ledger.md) | rediscovery is cheaper than a handover |

## Published findings in this domain

Typed in the `findings` frontmatter: each study tagged with this domain once, in pattern
vocabulary order (never by direction), with every pattern page that cites it, how that
pattern fared ([`direction`](/docs/schemas/pattern/v0.1.md)) and what it was compared with.
Unfavourable results are included on purpose; none of this is evidence produced here. Each
finding in words, with its caveat and source: [/domains/documents/findings.md](/domains/documents/findings.md).

## Starters

Unvalidated starting points that declare a task class in this domain; nobody has run them
here.

- [documents-successor-handoff](/starters/documents-successor-handoff/0.1.0.md): A predecessor reads and organizes a long document set, then a successor continues from a structured handover dossier. Task classes: `documents.long_document_review`.

## What can be evaluated here

Nothing in this domain yet. This deployment evaluates only `coding.bugfix`; an empty domain is a valid state, not a gap to fill with claims.

## To find out for your workload

Nothing on this page says which arrangement will work for your task. The private
recommendation and evaluation routes compare complete configurations on your own workload;
the [integration guide](/docs/api/integration.md) says how to reach them.

[Reporting outcomes (limited rollout)](/docs/api/contributing.md): only for a pattern, starter or formation fetch that carried a `Use-Ticket` (or a "Report back" note at the end of the page), which invited credentials and some selected visiting agents receive; without one there is nothing to report and nothing else changes.