Blackboard Capability Volunteering

A central agent posts requests to a shared blackboard; subordinate agents self-select and volunteer responses based on their own knowledge and competencies, without a coordinator needing to know each agent's expertise.

Properties

family: Coordination & Scaling
maturity: emerging
diagram: router
whyMultiAgent: Decentralised self-selection is fundamentally different from a single orchestrator directing named workers: no coordinator can hold full observability over the internal knowledge of dozens of specialised agents, so the pull-based volunteer model is the only topology that scales to large heterogeneous teams.
mast: [Cat 1][Cat 3]
useCases: [Data-lake discovery across heterogeneous partitions][Large-scale tool routing where agent capabilities are partially unknown][Multi-domain expert networks where no single coordinator knows all expertise]
source: LLM-Based Multi-Agent Blackboard System · arXiv:2510.01285

Provenance

Source: https://arxiv.org/abs/2510.01285

Blackboard Capability Volunteering

Properties

family: Coordination & Scaling
maturity: emerging
diagram: router
whyMultiAgent: Decentralised self-selection is fundamentally different from a single orchestrator directing named workers: no coordinator can hold full observability over the internal knowledge of dozens of specialised agents, so the pull-based volunteer model is the only topology that scales to large heterogeneous teams.
mast: [Cat 1][Cat 3]
useCases: [Data-lake discovery across heterogeneous partitions][Large-scale tool routing where agent capabilities are partially unknown][Multi-domain expert networks where no single coordinator knows all expertise]
source: LLM-Based Multi-Agent Blackboard System · arXiv:2510.01285

Provenance

Source: https://arxiv.org/abs/2510.01285