Multi-Agent

Epistemic Fault-Domain Quorum

Credit a multi-agent quorum only with the resilience its distinct upstream roots justify, admitting the coalition when the number of independent root faults needed to compromise it clears a declared threshold.

Problem

Members that descend from a common upstream root do not supply independent observations; they relay one observation several times, and the tally cannot tell the difference. Holding a single evidence root fixed while report multiplicity rises from 1 to 32 collapses naive posterior coverage from 0.940 to 0.263, so confidence grows precisely where information does not. The structural version is worse: an arbitrarily large quorum can still have a minimum root-fault cut of one, meaning a single stale feed or a single corrupted document flips a unanimous verdict. Adding voters at a fixed threshold cannot raise that cut, so the usual remedy for a shaky decision buys nothing.

Solution

Treat independence as something measured at admission rather than assumed from headcount. For each member, enumerate the roots it depends on — the source documents it read, the retrieval corpus behind them, the telemetry feed, the tool backends it called, the base model and the generative process that produced it — and record the result as an exposure map built from what ran, not from declared configuration. The resilience the coalition may be credited with is then the smallest set of root faults that would compromise the decision, not the number of members that agreed. Compare that cut against a threshold declared in advance for the class of decision. A coalition below the threshold is repaired by buying a distinct root — a second corpus, a second tool backend, a separate model lineage — or by downgrading the claim to what the evidence supports; enlarging the membership at a fixed threshold is provably not a repair. Keep members from reading each other's complete outputs before they commit, because exchange collapses the very diversity being counted. Store the map and the cut with the decision so an auditor can recompute both.

When to use

  • Several agents must agree before a high-stakes or irreversible action, and the number that agreed is treated as the strength of the result.
  • Members draw on retrieval corpora, telemetry feeds or tool backends that may be shared without anyone having written the dependency down.
  • The decision has to be defended later to a reviewer who will ask what the agreement actually established.

Open the full interactive page

Diagram, neighbourhood map, code examples, related patterns and full provenance.

Related