# Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge

arXiv: https://arxiv.org/abs/2606.26511 · HTML: https://mlsanity.com/paper/2606.26511/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (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)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation](https://mlsanity.com/paper/2503.21322/) (2025)
- [A Survey on Temporal Knowledge Graph: Representation Learning and Applications](https://mlsanity.com/paper/2403.04782/) (2024)
- [NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes](https://mlsanity.com/paper/2504.11544/) (2025)

## Built on by (most cited first, 14 of 14)

- [MemTX: Transactional Belief Commit for Stateful Agent Memory](https://mlsanity.com/paper/2607.23929/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings](https://mlsanity.com/paper/2607.21962/) (2026)
- [When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory](https://mlsanity.com/paper/2608.25553/) (2026)
- [Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems](https://mlsanity.com/paper/2609.08258/) (2026)
- [Memory Consolidation Flattens the Temporal Shape of User Facts](https://mlsanity.com/paper/2609.36457/) (2026)
- [ChurnBench: A Drift-Aware Benchmark Demonstrating That Refresh Scheduling, Not Cache Age, Governs Staleness in Agentic AI](https://mlsanity.com/paper/2609.11515/) (2026)
- [Epi-Logic: A Conceptual Framework for Epistemic Runtime Control, Schema Validity Checking, and Controlled Accommodation in Autonomous AI Agents](https://mlsanity.com/paper/2609.24755/) (2026)
- [Impact Is Not Invalidation: Ask About the Claim, Not the Diff](https://mlsanity.com/paper/2609.25130/) (2026)
- [Personalized State-Transition-Aware Memory for Clinical Agents](https://mlsanity.com/paper/2609.38490/) (2026)
- [StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions](https://mlsanity.com/paper/2610.05241/) (2026)
- [MemStrata: 95% and 90.91% Source-Aware Accuracy on LongMemEval-500 and LoCoMo-1540 with a Local Qwen 3.8 27B Q4_K_M Reader](https://mlsanity.com/paper/2610.05343/) (2026)
- [When Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal Memory](https://mlsanity.com/paper/2610.07715/) (2026)
- [Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation](https://mlsanity.com/paper/2610.10265/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is renamed or API restructured), RAG retrieves both the stale and current value with near-identical embedding similarity. The agent then either abstains or serves the superseded fact. We show this is a structural problem: on a calibrated dataset, cosine similarity distinguishes a contradicted fact from a duplicated one with AUROC 0.59 (near chance), as contradictions are often more embedding-similar to the original than rephrased duplicates. We present MemStrata, a retrieval memory maintaining temporal validity. It stores facts like RAG, preserving static recall, but when a fact's value is contradicted, a deterministic (subject, relation, object) supersession rule retires the stale value in a bi-temporal ledger - with no similarity threshold and no LLM call. Across six benchmarks run locally with a 7B model, MemStrata ties RAG on static knowledge and reaches 0.95-1.00 accuracy on evolving knowledge (where RAG reaches 0.20-0.47). The central result is the stale-fact-error rate: when required to answer, RAG serves superseded values 15-40% of the time; MemStrata drives this to ~0%, a failure class RAG cannot avoid. MemStrata achieves this at retrieval latency (~2.1s) versus ~16-18s for LLM-reranking baselines. We release the harness, datasets, and a marker-free evaluation protocol for memory under knowledge evolution.