Multi‑Agent Systems

/pattern/agentic/cognitive/

Functional group

Cognitive · Reasoning

The Cognitive phase stabilizes the quality of step-by-step decision-making. It is where goals are prioritised, decomposed, and matched to actions with deliberate intent. This phase matters because no amount of foundation or execution repairs a bad plan — a perfect executor running a flawed plan simply reaches the wrong destination faster. Its absence causes drift: goals compete without resolution, complex tasks collapse under one-shot reasoning, and actions are chosen on instinct rather than context. The three ADPs here form a hierarchy: Selector picks *which* goal, Planner decomposes *how*, and Deliberator chooses *what* action at each step.

Selector

Dynamic prioritization of goals — the tactical step-selector that picks the next action from competing demands.

Addresses
Goal-selection under multiple competing demands.
When it stabilizes
When an agent receives simultaneous requests, when user intent is ambiguous, or when resource constraints force trade-offs.
Example
A priority queue ranks pending tasks by deadline and confidence, surfacing the highest-urgency item to the planner.
Guards against
Shows up in
  • Routingrouting is the selector pattern in flow form.

Planner

Strategic decomposition of complex goals into ordered sub-goals that can be executed sequentially or in parallel.

Addresses
Reasoning depth — the failure mode where one-shot reasoning collapses for tasks needing many steps.
When it stabilizes
When a task requires more than three sequential decisions, when failure at one step demands backtracking, or when parallel workstreams must be coordinated.
Example
A ReWoo-style plan-first module emits a DAG of sub-tasks before any tool is called, making the execution path inspectable.
Guards against
Shows up in
  • Plan-and-Executeexplicit plan first, then execute against it.
  • ReWOOplan-first decomposition before any tool call.

Deliberator

Selection of the optimal action per planning step — the local choice given the local context, not a global default.

Addresses
Action quality at each step.
When it stabilizes
When multiple valid actions exist for a given state, when the cost of a wrong action is high, or when the context changes between steps.
Example
A Tree-of-Thoughts branch evaluates three candidate actions against a reward model before committing to the best one.
Guards against
Shows up in
  • ReActthe thought step is a mini-deliberation before action.
  • Tree of Thoughtsbranching evaluation of candidate actions.

Where to next

More functional groups.

PatternsFoundationalWorld Modeling & StateOpen PatternsExecutionActionOpen PatternsAgentic PatternsAll twelve patterns across four phases.Back to the loop

Search

Search patterns, frameworks, and pages.