--- schema: formation.domain/v0.1 kind: domain visibility: public canonical_url: https://topologyindex.com/domains/operations.md community_ranking: null description: 'Task shapes common in operations, the published findings tagged with the domain and the starters in it. Hypotheses and attributed findings, never a ranking.' domain: operations 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 - compared_against: 'A single agent under matched tools, prompts and compute' direction: mixed pattern: null source_id: arxiv:2512.08296 url: https://arxiv.org/abs/2512.08296 - citations: - compared_against: 'Single-agent solo setups' direction: mixed pattern: lane_swarm - compared_against: 'A single agent' direction: mixed pattern: dynamic_spawning source_id: arxiv:2308.10848 url: https://arxiv.org/abs/2308.10848 - citations: - compared_against: 'Published state-of-the-art agent systems on each benchmark' direction: no_clear_gain pattern: supervisor - compared_against: 'The full Magentic-One orchestrator with task and progress ledgers' direction: hurt pattern: blackboard - compared_against: 'The same agents coordinated by a basic group chat without ledgers' direction: helped pattern: shared_ledger source_id: arxiv:2411.04468 url: https://arxiv.org/abs/2411.04468 - citations: - compared_against: 'Single-agent approaches' direction: helped pattern: supervisor source_id: arxiv:2412.05449 url: https://arxiv.org/abs/2412.05449 - citations: - compared_against: 'ReAct-style sequential function calling' direction: helped pattern: planner_worker source_id: arxiv:2312.04511 url: https://arxiv.org/abs/2312.04511 - citations: - compared_against: 'Executor-only agents and planners without targeted training' direction: mixed pattern: planner_worker source_id: arxiv:2503.09572 url: https://arxiv.org/abs/2503.09572 - citations: - compared_against: 'ReAct, Reflexion, and the tree-search methods Tree of Thoughts and RAP' direction: helped pattern: tree_search source_id: arxiv:2310.04406 url: https://arxiv.org/abs/2310.04406 - citations: - compared_against: 'The same web agent without search' direction: helped pattern: tree_search source_id: arxiv:2407.01476 url: https://arxiv.org/abs/2407.01476 - citations: - compared_against: 'Handcrafted and automated multi-agent systems' direction: helped pattern: architecture_search source_id: arxiv:2502.04180 url: https://arxiv.org/abs/2502.04180 findings_page: /domains/operations/findings.md path: /domains/operations.md pattern_index: /patterns/index.md product_api_version: v1 schema_version: v0.1 shapes: - example: 'a workflow whose steps can be planned before acting' shape: needs_plan_before_editing - example: 'multi-step tool use whose next step depends on what the last one returned' shape: subtasks_unknown_until_started - example: 'requests that need different tools, such as a browser, files or a terminal' shape: specialist_per_input - example: 'a long-running operation that continues across sessions' shape: outlasts_one_context starters: - name: board-coordinated-collective path: /starters/board-coordinated-collective/0.1.0.md task_classes: - operations.shared_project version: '0.1.0' - name: operations-specialist-router path: /starters/operations-specialist-router/0.1.0.md task_classes: - operations.tool_workflow version: '0.1.0' task_class_prefix: operations. title: 'Which multi-agent pattern for tool use and operations?' --- # Which multi-agent pattern for tool use and operations? **Short answer:** for a workflow whose steps can be planned before acting, start with [planner_worker](/patterns/planner_worker.md); avoid it when the plan cannot be written without touching the work. Other shapes of operations 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/operations/findings.md) keep the unfavourable ones. Acting on an environment through tools: web navigation, desktop and terminal work, workplace tools and function calling. The `operations` domain of the [task domains](/domains/index.md): task classes that start with `operations.`. ## 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. - `needs_plan_before_editing`: a workflow whose steps can be planned before acting - `subtasks_unknown_until_started`: multi-step tool use whose next step depends on what the last one returned - `specialist_per_input`: requests that need different tools, such as a browser, files or a terminal - `outlasts_one_context`: a long-running operation that continues across 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 | | --- | --- | --- | --- | | needs a plan before editing | [planner_worker](/patterns/planner_worker.md) | [supervisor](/patterns/supervisor.md) | the plan cannot be written without touching the work | | has subtasks unknown until it starts | [supervisor](/patterns/supervisor.md) | [dynamic_spawning](/patterns/dynamic_spawning.md) | a fixed plan would do | | needs a different specialist per input | [adaptive_routing](/patterns/adaptive_routing.md) | [supervisor](/patterns/supervisor.md) | the routing condition is not observable | | 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/operations/findings.md](/domains/operations/findings.md). ## Starters Unvalidated starting points that declare a task class in this domain; nobody has run them here. - [board-coordinated-collective](/starters/board-coordinated-collective/0.1.0.md): A coordinator assigns lanes on a shared board, with mailboxes, signed control messages and a successor hand-off. Task classes: `operations.shared_project`. - [operations-specialist-router](/starters/operations-specialist-router/0.1.0.md): A router classifies each incoming operation and hands it to the specialist with the matching tool or procedure. Task classes: `operations.tool_workflow`. ## 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.