# The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums

arXiv: https://arxiv.org/abs/2609.02925 · HTML: https://mlsanity.com/paper/2609.02925/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 14 of 14)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents](https://mlsanity.com/paper/2607.10487/) (2026)
- [Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows](https://mlsanity.com/paper/2607.00269/) (2026)
- [When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority](https://mlsanity.com/paper/2609.20261/) (2026)
- [The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure](https://mlsanity.com/paper/2607.16109/) (2026)

## Built on by (most cited first, 2 of 2)

- [Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems](https://mlsanity.com/paper/2609.16313/) (2026)
- [Before Agents Act: Assurance-Aware Semantic Scheduling for Evidence Acquisition in Distributed Systems](https://mlsanity.com/paper/2609.34376/) (2026)

## Abstract (arXiv)

Multi-agent quorums are widely used to authorize high-stakes infrastructure and policy mutations, yet distinct reviewers often share upstream telemetry, documents, or tool backends. When upstream inputs fail, multiple votes collapse onto a single corrupted cause: replication does not imply epistemic redundancy. We introduce Epistemic Fault Domains (EFDs) and the Structural Epistemic Cut kappaE, which quantifies the minimum number of modeled root faults whose exposure covers an authorizing coalition relative to an explicit Epistemic Fault Basis. Under closed causal accounting, conservative exposure, and authorization alignment, kappaE lower-bounds the number of roots required for semantic compromise (kappaS). We prove that arbitrarily large quorums can retain kappaE=1, that recognizing shared ancestry never increases credited resilience, and that adding voters at a fixed threshold cannot increase the cut under compatible exposure extensions. Finally, we design the Dependency-Aware Quorum Controller (DAQC) to enforce structural cuts at runtime admission, evaluate its mechanics via analytical derivations and simulations, and provide a frozen 120-task external benchmark suite.