VI · Multi-AgentEmerging★

Communicative Dehallucination

also known as Instructor-Reversal Clarification, Inter-Agent Clarifying Question

When an instructed agent would have to invent missing context to comply, have it reverse roles and ask the instructor for the missing detail before answering.

This pattern helps complete certain larger patterns —

  • specialisesDisambiguation★★— Have the agent ask a clarifying question before acting on an ambiguous request.

Context

Two agents are communicating in an instructor-and-assistant shape — an orchestrator telling a coding sub-agent what to do, a planner handing work to an executor — and the instruction arrives with a decisive detail missing. The missing piece might be a specific class name, an API version, an ambiguous unit of measure, or which of several plausible interpretations the instructor actually meant.

Problem

Without a way for the assistant to ask back, it complies by inventing a plausible value for the missing detail and proceeds as if it had been told. The fabricated choice gets baked into the next artefact and is hard to spot at the hand-off boundary, where it looks like a confident answer rather than a guess. By the time the wrong assumption surfaces — in a downstream failure or a user complaint — the trail back to the original gap is buried.

Forces

  • Speed of completion vs. fidelity of context.
  • Adding a clarification round costs latency and tokens.
  • Asking too eagerly degrades into chatter; not asking at all produces hallucinated outputs.

Example

An orchestrator agent tells a coding sub-agent 'add the new field to the user model'. The sub-agent doesn't know whether 'field' means database column, API contract, or both, but it would normally just pick one and start editing. Under Communicative Dehallucination, the sub-agent reverses roles and asks back: 'do you mean the database schema, the GraphQL type, or both?' Only after the orchestrator answers does it act, so the wrong choice never propagates downstream where it would be expensive to detect.

Diagram

Solution

Therefore:

Define an explicit role-reversal protocol: when the assistant detects that the instruction is missing a deciding piece of context, it pivots and emits a focused question back to the instructor ("the precise name of the dependency, please"). The instructor answers, and only then does the assistant produce its conclusion. Bound the depth (one or two reversals) to prevent infinite ping-pong.

What this pattern forbids. The assistant may not produce a final answer when a designated context slot is unfilled; it must instead emit a clarifying question.

The smaller patterns that complete this one —

  • usesInter-Agent Communication★— Define a protocol for agents to exchange tasks, capabilities, and results across process or vendor boundaries.

And the patterns that stand alongside it, or against it —

  • alternative-toHuman-in-the-Loop★★— Require explicit human approval at defined points before the agent performs an action.
  • alternative-toDebate·— Have multiple agents argue different positions on a question and converge through structured exchange.
  • conflicts-withInfinite Debate✕— Anti-pattern: launch multi-agent debate without a termination rule and watch the agents loop forever.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

Used in frameworks

References

Provenance