--- schema: formation.domain/v0.1 kind: domain visibility: public canonical_url: https://topologyindex.com/domains/research.md community_ranking: null description: 'Task shapes common in research, the published findings tagged with the domain and the starters in it. Hypotheses and attributed findings, never a ranking.' domain: research domain_index: /domains/index.md evaluable_here: [] findings: - citations: - compared_against: 'Multi-agent coordination under matched tools, prompts and compute' direction: mixed pattern: single_agent - compared_against: 'Single-agent systems and centralized, decentralized and hybrid multi-agent architectures' direction: mixed pattern: independent_workers - compared_against: 'Single-agent systems and independent, decentralized and hybrid multi-agent architectures' direction: mixed pattern: supervisor - compared_against: 'A single agent and centralized, independent and hybrid multi-agent architectures' direction: mixed pattern: mailbox_network source_id: arxiv:2512.08296 url: https://arxiv.org/abs/2512.08296 - citations: - compared_against: 'A multi-agent system with a lead agent and parallel subagents' direction: hurt pattern: single_agent - compared_against: 'Single-agent Claude on the same research tasks' direction: mixed pattern: independent_workers - compared_against: 'A single agent using the same model as the lead agent' direction: helped pattern: supervisor - compared_against: 'A single agent using the stronger model alone' direction: helped pattern: dynamic_spawning source_id: web:anthropic.com/engineering/multi-agent-research-system url: https://www.anthropic.com/engineering/multi-agent-research-system - citations: - compared_against: 'A single agent with the same model, search and web-reading tools' direction: helped pattern: map_reduce source_id: arxiv:2508.07999 url: https://arxiv.org/abs/2508.07999 - citations: - compared_against: 'Direct prompting and the AutoSurvey and MASS-Survey pipelines' direction: helped pattern: map_reduce source_id: arxiv:2510.05138 url: https://arxiv.org/abs/2510.05138 - citations: - compared_against: 'Single-model search agents such as WebThinker and ReAct, plan-and-solve prompting, and retrieval-augmented generation' direction: helped pattern: planner_worker source_id: arxiv:2507.02652 url: https://arxiv.org/abs/2507.02652 - citations: - compared_against: 'Master-slave multi-agent coordination, retrieval-augmented generation and a single agent' direction: helped pattern: blackboard source_id: arxiv:2510.01285 url: https://arxiv.org/abs/2510.01285 - citations: - compared_against: 'The same idea generator with fewer or no rounds of reviewing-agent feedback' direction: helped pattern: critic_loop source_id: arxiv:2404.07738 url: https://arxiv.org/abs/2404.07738 - citations: - compared_against: 'A single LLM screening with the same model' direction: helped pattern: council source_id: arxiv:2607.21920 url: https://arxiv.org/abs/2607.21920 - citations: - compared_against: 'The same model without search, a ReAct-style search agent, and the ChatGPT-Web and Perplexity Pro products' direction: helped pattern: dynamic_spawning source_id: arxiv:2407.20183 url: https://arxiv.org/abs/2407.20183 - citations: - compared_against: 'The same agent without context management features' direction: helped pattern: successor_handoff source_id: web:claude.com/blog/context-management url: https://claude.com/blog/context-management - citations: - compared_against: 'Single-agent web search and single-agent deep research systems' direction: mixed pattern: null source_id: arxiv:2510.14240 url: https://arxiv.org/abs/2510.14240 findings_page: /domains/research/findings.md path: /domains/research.md pattern_index: /patterns/index.md product_api_version: v1 schema_version: v0.1 shapes: - example: 'a broad question whose sub-questions can be searched separately' shape: splits_into_independent_parts - example: 'an open-ended investigation whose leads appear as it proceeds' shape: subtasks_unknown_until_started - example: 'an investigation that gathers more material than one context window holds' shape: outlasts_one_context starters: - name: research-split-and-combine path: /starters/research-split-and-combine/0.1.0.md task_classes: - research.broad_question version: '0.1.0' - name: research-supervised-investigation path: /starters/research-supervised-investigation/0.1.0.md task_classes: - research.open_investigation version: '0.1.0' task_class_prefix: research. title: 'Which multi-agent pattern for research tasks?' --- # Which multi-agent pattern for research tasks? **Short answer:** for a broad question whose sub-questions can be searched separately, start with [map_reduce](/patterns/map_reduce.md); avoid it when the parts depend on each other. Other shapes of research 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/research/findings.md) keep the unfavourable ones. Finding and synthesizing information across sources: web and deep research, literature review and data discovery. The `research` domain of the [task domains](/domains/index.md): task classes that start with `research.`. ## 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`: a broad question whose sub-questions can be searched separately - `subtasks_unknown_until_started`: an open-ended investigation whose leads appear as it proceeds - `outlasts_one_context`: an investigation that gathers more material than one context window holds 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 | | has subtasks unknown until it starts | [supervisor](/patterns/supervisor.md) | [dynamic_spawning](/patterns/dynamic_spawning.md) | a fixed plan would do | | 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/research/findings.md](/domains/research/findings.md). ## Starters Unvalidated starting points that declare a task class in this domain; nobody has run them here. - [research-split-and-combine](/starters/research-split-and-combine/0.1.0.md): A splitter divides a broad research question into independent parts, researchers work the parts at the same time, and a combiner writes one sourced answer. Task classes: `research.broad_question`. - [research-supervised-investigation](/starters/research-supervised-investigation/0.1.0.md): A lead holds the question and the running findings, and sends a researcher after one lead at a time until the answer is supported. Task classes: `research.open_investigation`. ## 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.