# Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure

arXiv: https://arxiv.org/abs/2604.11759 · HTML: https://mlsanity.com/paper/2604.11759/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models](https://mlsanity.com/paper/2505.22101/) (2025)
- [A Survey on Temporal Knowledge Graph: Representation Learning and Applications](https://mlsanity.com/paper/2403.04782/) (2024)
- [Long Context vs. RAG for LLMs: An Evaluation and Revisits](https://mlsanity.com/paper/2501.01880/) (2024)
- [Long Context RAG Performance of Large Language Models](https://mlsanity.com/paper/2411.03538/) (2024)
- [Signed Graph Representation Learning: A Survey](https://mlsanity.com/paper/2402.15980/) (2024)
- [Uncertainty Management in the Construction of Knowledge Graphs: a Survey](https://mlsanity.com/paper/2405.16929/) (2024)
- [Early Impacts of M365 Copilot](https://mlsanity.com/paper/2504.11443/) (2025)
- [Dealing with Inconsistency for Reasoning over Knowledge Graphs: A Survey](https://mlsanity.com/paper/2502.19023/) (2025)

## Abstract (arXiv)

Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distinguishing binding decisions from abandoned hypotheses, contested claims from settled ones, or known facts from unresolved questions. We argue that the ceiling on organizational AI is not retrieval fidelity but epistemic fidelity--the system's ability to represent commitment strength, contradiction status, and organizational ignorance as computable properties. We present OIDA, a framework that structures organizational knowledge as typed Knowledge Objects carrying epistemic class, importance scores with class-specific decay, and signed contradiction edges. The Knowledge Gravity Engine maintains scores deterministically with proved convergence guarantees (sufficient condition: max degree < 7; empirically robust to degree 43). OIDA introduces QUESTION-as-modeled-ignorance: a primitive with inverse decay that surfaces what an organization does not know with increasing urgency--a mechanism absent from all surveyed systems. We describe the Epistemic Quality Score (EQS), a five-component evaluation methodology with explicit circularity analysis. In a controlled comparison (n=10 response pairs), OIDA's RAG condition (3,868 tokens) achieves EQS 0.530 vs. 0.848 for a full-context baseline (108,687 tokens); the 28.1× token budget difference is the primary confound. The QUESTION mechanism is statistically validated (Fisher p=0.0325, OR=21.0). The formal properties are established; the decisive ablation at equal token budget (E4) is pre-registered and not yet run.