# HaluMem: Evaluating Hallucinations in Memory Systems of Agents

arXiv: https://arxiv.org/abs/2511.03506 · HTML: https://mlsanity.com/paper/2511.03506/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [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)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs](https://mlsanity.com/paper/2502.09597/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models](https://mlsanity.com/paper/2403.06448/) (2024)
- [Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory](https://mlsanity.com/paper/2311.08719/) (2023)
- [Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation](https://mlsanity.com/paper/2401.15449/) (2024)
- [WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback](https://mlsanity.com/paper/2408.15549/) (2024)
- [A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions](https://mlsanity.com/paper/2507.18910/) (2025)
- [A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs](https://mlsanity.com/paper/2505.08200/) (2025)
- [Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation](https://mlsanity.com/paper/2407.12216/) (2024)
- [Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions](https://mlsanity.com/paper/2510.12040/) (2025)

## Built on by (most cited first, 30 of 54)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://mlsanity.com/paper/2601.06966/) (2026)
- [GAM: Hierarchical Graph-based Agentic Memory for LLM Agents](https://mlsanity.com/paper/2604.12285/) (2026)
- [MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization](https://mlsanity.com/paper/2603.25973/) (2026)
- [GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents](https://mlsanity.com/paper/2606.18829/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory](https://mlsanity.com/paper/2601.01280/) (2026)
- [AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment](https://mlsanity.com/paper/2603.26680/) (2026)
- [TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory](https://mlsanity.com/paper/2606.06240/) (2026)
- [From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents](https://mlsanity.com/paper/2608.10502/) (2026)
- [MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval](https://mlsanity.com/paper/2605.06132/) (2026)
- [MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents](https://mlsanity.com/paper/2605.09530/) (2026)
- [WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction](https://mlsanity.com/paper/2605.29341/) (2026)
- [ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents](https://mlsanity.com/paper/2603.00026/) (2026)
- [MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems](https://mlsanity.com/paper/2605.28732/) (2026)
- [MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery](https://mlsanity.com/paper/2606.24595/) (2026)
- [TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory](https://mlsanity.com/paper/2606.25161/) (2026)
- [WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents](https://mlsanity.com/paper/2606.18847/) (2026)
- [MemTrace: Probing What Final Accuracy Misses in Long-Term Memory](https://mlsanity.com/paper/2606.17328/) (2026)
- [MemReader: From Passive to Active Extraction for Long-Term Agent Memory](https://mlsanity.com/paper/2604.07877/) (2026)
- [Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents](https://mlsanity.com/paper/2605.25535/) (2026)
- [MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models](https://mlsanity.com/paper/2605.28009/) (2026)
- [Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence](https://mlsanity.com/paper/2512.20651/) (2025)
- [VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents](https://mlsanity.com/paper/2603.23840/) (2026)
- [DeltaMem: Towards Agentic Memory Management via Reinforcement Learning](https://mlsanity.com/paper/2604.01560/) (2026)
- [MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare](https://mlsanity.com/paper/2605.11814/) (2026)
- [SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory](https://mlsanity.com/paper/2605.12061/) (2026)

## Abstract (arXiv)

Memory systems are key components that enable AI systems such as LLMs and AI agents to achieve long-term learning and sustained interaction. However, during memory storage and retrieval, these systems frequently exhibit memory hallucinations, including fabrication, errors, conflicts, and omissions. Existing evaluations of memory hallucinations are primarily end-to-end question answering, which makes it difficult to localize the operational stage within the memory system where hallucinations arise. To address this, we introduce the Hallucination in Memory Benchmark (HaluMem), the first operation level hallucination evaluation benchmark tailored to memory systems. HaluMem defines three evaluation tasks (memory extraction, memory updating, and memory question answering) to comprehensively reveal hallucination behaviors across different operational stages of interaction. To support evaluation, we construct user-centric, multi-turn human-AI interaction datasets, HaluMem-Medium and HaluMem-Long. Both include about 15k memory points and 3.5k multi-type questions. The average dialogue length per user reaches 1.5k and 2.6k turns, with context lengths exceeding 1M tokens, enabling evaluation of hallucinations across different context scales and task complexities. Empirical studies based on HaluMem show that existing memory systems tend to generate and accumulate hallucinations during the extraction and updating stages, which subsequently propagate errors to the question answering stage. Future research should focus on developing interpretable and constrained memory operation mechanisms that systematically suppress hallucinations and improve memory reliability.