The shared blackboard pattern is back and it's solving multi-agent context loss

Description and use

The blackboard pattern effectively mitigates context loss in multi‑agent LLM systems, improving accuracy and efficiency, but requires scoped projections and governance.

Problem

Agents in a multi‑agent system were unable to see shared context, causing repetitive loops and loss of information across handoffs.

Outcome

The blackboard pattern improved information fidelity at the coder stage by 62%, correct file targeting by 27.5 percentage points, and achieved 100% ledger accuracy versus 0% in a production system, with 26× lower latency and 29× lower token consumption.

Workflow

• 1. Agents publish messages with optional references to prior messages.
• 2. Agents search the board by content, receiving at most k relevant messages.
• 3. Agents visit specific messages by address.
• 4. A Supervisor LLM orchestrates agent turns based on board state.
• 5. Governance policies enforce scoped retrieval, temporal supersession, provenance tracking, and policy‑governed propagation.

Evidence

The shared blackboard wasn't shared.

Source

Information Fidelity Score at the Coder stage: 0.586 vs. 0.362 — a 62% improvement

Source

100% ledger accuracy versus 0% for the debate panel.

Source