# MemFail: Stress-Testing Failure Modes of LLM Memory Systems

arXiv: https://arxiv.org/abs/2605.26667 · HTML: https://mlsanity.com/paper/2605.26667/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents](https://mlsanity.com/paper/2506.21605/) (2025)
- [MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems](https://mlsanity.com/paper/2510.17281/) (2025)
- [EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning](https://mlsanity.com/paper/2601.02163/) (2026)
- [MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants](https://mlsanity.com/paper/2409.20163/) (2024)
- [StructMem: Structured Memory for Long-Horizon Behavior in LLMs](https://mlsanity.com/paper/2604.21748/) (2026)
- [Evaluating Memory Structure in LLM Agents](https://mlsanity.com/paper/2602.11243/) (2026)

## Built on by (most cited first, 3 of 3)

- [Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures](https://mlsanity.com/paper/2607.28802/) (2026)
- [What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory](https://mlsanity.com/paper/2609.08279/) (2026)
- [ReplayLens: Auditing Agents' Use of Outcomes](https://mlsanity.com/paper/2609.34177/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empirical work has been done to understand the specific failure modes and design choices that these systems present. Existing benchmarks report aggregate question-answering accuracy and treat memory systems as black boxes, making it impossible to attribute an incorrect answer to a particular failure mode of the system. We introduce MemFail, a diagnostic benchmark that isolates the failure modes of modern LLM memory systems. We begin by formalizing memory systems as the composition of three canonical operations -- summarization, storage, and retrieval -- and identify the potential failure modes induced by each. Based on these hypothesized failure modes, we construct five datasets spanning four tasks, each adversarially designed to test a specific operation of a memory system. Using these datasets, we evaluate four state-of-the-art memory systems on MemFail and demonstrate how MemFail can be used to empirically understand the tradeoffs induced by differences in memory system architectures.