Literature review
AuraScore 81/100

Multi-Agent Coordination Topology Selection Framework

Transform multi-agent literature into a definitive topology selection and workflow chain orchestration framework.

Use this template when evaluating academic research on multi-agent collaboration patterns to establish an organizational design framework for complex workflow chains.

Template

Role: Senior Research Director in Multi-Agent Systems and Distributed Workflow Engineering.

Context

  • Topologies under analysis: {{coordination_topologies}}
  • Corpus publication window: {{academic_sources_date_range}}
  • Known cascading fault modes: {{error_propagation_modes}}
  • Target domain task complexity: {{domain_workflow_complexity}}
  • Token consumption constraints: {{context_window_budgets}}
  • Communication protocol specifications: {{inter_agent_communication_protocols}}

Task

Review the academic research across {{academic_sources_date_range}} to create a formal decision framework that guides the selection, topology configuration, and orchestration guardrails of {{coordination_topologies}} for {{domain_workflow_complexity}}.

Method

  1. Synthesize empirical findings from {{academic_sources_date_range}} regarding state synchronization and message pass overhead across {{coordination_topologies}}.
  2. Map documented failure cascades from {{error_propagation_modes}} to specific network structural properties (e.g., cyclic dependencies, hierarchical bottlenecks).
  3. Establish comparative efficiency frontiers balancing task success rates against {{context_window_budgets}}.
  4. Design a topology classification taxonomy based on delegation authority, feedback loop latency, and consensus mechanisms.
  5. Standardize messaging contracts and state payloads leveraging {{inter_agent_communication_protocols}} to prevent drift between chained agents.
  6. Formulate a multi-criteria scoring algorithm to match sub-tasks within {{domain_workflow_complexity}} to the optimal topology pattern.
  7. Develop dynamic topology reconfiguration rules when an agent node fails or encounters deadlocks.

Constraints

  • MUST establish formal mathematical or logic-based scoring criteria for topology selection.
  • MUST NOT include subjective or qualitative-only recommendations without anchoring in {{academic_sources_date_range}}.
  • Ensure communication overhead calculations adhere to {{context_window_budgets}}.
  • Enforce mitigation strategies for every item identified in {{error_propagation_modes}}.

Output format

Produce the complete framework formatted in four structured modules:

  1. Literature Comparative Synthesis (detailed markdown matrix contrasting each topology's token overhead, recovery cost, and max task depth)
  2. Topology Selection Scoring Rubric (weighted criteria equation and evaluation parameters)
  3. Orchestration Protocol Specification (state machines and message schemas for {{inter_agent_communication_protocols}})
  4. Fault-Tolerant Reconfiguration Playbook (step-by-step state transition framework under 500 words)

Self-review

  • Confirm all context variables ({{coordination_topologies}}, {{academic_sources_date_range}}, {{error_propagation_modes}}, {{domain_workflow_complexity}}, {{context_window_budgets}}, {{inter_agent_communication_protocols}}) are directly referenced.
  • Verify constraints contain at least two MUST/MUST NOT directives.
  • Ensure the output strictly provides a multi-agent architectural decision framework.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-literature
autonomous-agents-workflows
multi-agent
orchestration
literature-review