The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure

Paper · arXiv 2607.16109 · Published July 17, 2026
Multi-Agent Architectures

State machine replication and Byzantine fault-tolerant consensus guarantee agreement despite a bounded number of arbitrary faulty participants; Byzantine participants may coordinate or collude. These guarantees rely on participants outside that set correctly implementing the protocol’s transition or validation semantics. Agentic validators expose a weaker partition: an authenticated, responsive, correctly signed, nonequivocating reasoning participant that is protocol-compliant with the voting protocol may nevertheless endorse a semantically invalid state transition. We call the resulting failure mode an epistemic fault and the collective phenomenon the Honest Quorum Problem; here, honest means protocol-compliant, not semantically correct. Such a quorum can satisfy ordinary protocol checks while forming a well-formed certificate for an invalid transition. We show that agreement alone does not establish semantic certificate validity or execution safety. Agentic validators may share model weights or lineage, training distributions, prompts, retrieval sources, toolchains, evidence, reasoning scaffolds, and provider infrastructure, yielding correlated epistemic faults.

Introduction. An operator proposes an infrastructure state mutation: expand a deployment service account from read-only inspection to write authority over a production namespace. Several reasoning validators inspect the same canonical request, state snapshot, policy context, and evidence package. Each validator authenticates correctly, receives the same request digest, follows the voting protocol, signs the expected message, responds before the timeout, and does not equivocate. A quorum approves the transition, but the transition violates an application invariant: it crosses the intended control-plane isolation boundary. The protocol succeeds in forming agreement, yet the system commits a semantically invalid action. Classical state machine replication (SMR) and Byzantine fault-tolerant (BFT) consensus already permit arbitrary faulty replicas to coordinate, collude, equivocate, and choose adversarial messages [1–3].

Discussion / Conclusion. The threshold theorems in Section 6 mix deterministic protocol assumptions with statistical semantic assumptions. Agreement is the deterministic part: under authenticated channels, partial synchrony, and the assumption that only Byzantine validators equivocate, two conflicting q-certificates cannot both form when the intersection condition holds. Semantic certificate validity and liveness are different. They are conditioned on the events Eδ and Uε: the former bounds protocolcompliant false endorsement of invalid candidates by eδ, and the latter bounds unusable support for a valid candidate by uε. The scope of these events must be stated with the certificate. A pointwise, per-candidate claim applies to one candidate, state, policy, and evidence package. A domain-conditional claim applies only inside a calibrated workload domain D. An average-case claim averages over a task distribution on that domain. A uniform claim must bound every admissible task in the stated class. These are not interchangeable guarantees. In particular, the paper’s statistical claims do not turn semantic correctness into a deterministic property of consensus.

Lines of inquiry this paper opens 24

Research framings built by reading the notes related to this paper — the questions it feeds into.

What coordination failures limit multi-agent LLM systems as they scale? Why do agents confidently report success despite actually failing tasks? Can debate mechanisms prevent silent agreement on wrong answers in multi-agent reasoning? What mechanisms enable AI systems to generate and spread false beliefs? How faithfully do LLMs reflect their actual reasoning in outputs and explanations? How do multi-agent systems achieve genuine cooperation and reasoning? How does test-time aggregation affect reasoning correctness and reliability?