# MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory

arXiv: https://arxiv.org/abs/2404.11672 · HTML: https://mlsanity.com/paper/2404.11672/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 71 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 30 of 58)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)

## Built on by (most cited first, 30 of 35)

- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers](https://mlsanity.com/paper/2603.07670/) (2026)
- [M+: Extending MemoryLLM with Scalable Long-Term Memory](https://mlsanity.com/paper/2502.00592/) (2025)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents](https://mlsanity.com/paper/2502.06975/) (2025)
- [O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents](https://mlsanity.com/paper/2511.13593/) (2025)
- [Logically Consistent Language Models via Neuro-Symbolic Integration](https://mlsanity.com/paper/2409.13724/) (2024)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory](https://mlsanity.com/paper/2509.04439/) (2025)
- [CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension](https://mlsanity.com/paper/2510.05520/) (2025)
- [Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment](https://mlsanity.com/paper/2405.13068/) (2024)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents](https://mlsanity.com/paper/2511.12960/) (2025)
- [Evaluating Memory Structure in LLM Agents](https://mlsanity.com/paper/2602.11243/) (2026)
- [Problem Solving Through Human-AI Preference-Based Cooperation](https://mlsanity.com/paper/2408.07461/) (2024)
- [Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures](https://mlsanity.com/paper/2508.10824/) (2025)
- [ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond](https://mlsanity.com/paper/2502.12845/) (2025)
- [Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents](https://mlsanity.com/paper/2607.13591/) (2026)
- [Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation](https://mlsanity.com/paper/2407.13505/) (2024)
- [AutoMem: Automated Learning of Memory as a Cognitive Skill](https://mlsanity.com/paper/2607.01224/) (2026)
- [OrthoDoc: Multimodal Large Language Model for Assisting Diagnosis in Computed Tomography](https://mlsanity.com/paper/2409.09052/) (2024)
- [Memorization and Knowledge Injection in Gated LLMs](https://mlsanity.com/paper/2504.21239/) (2025)
- [Higher-Order Knowledge Representations for Agentic Scientific Reasoning](https://mlsanity.com/paper/2601.04878/) (2026)
- [The Paradox of Poetic Intent in Back-Translation: Evaluating the Quality of Large Language Models in Chinese Translation](https://mlsanity.com/paper/2504.16286/) (2025)
- [Distilling Feedback into Memory-as-a-Tool](https://mlsanity.com/paper/2601.05960/) (2026)
- [AdMem: Advanced Memory for Task-solving Agents](https://mlsanity.com/paper/2606.06787/) (2026)
- [Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents](https://mlsanity.com/paper/2608.28978/) (2026)
- [MemX: A Local-First Long-Term Memory System for AI Assistants](https://mlsanity.com/paper/2603.16171/) (2026)
- [LANTERN: Layered Archival and Temporal Episodic Retrieval Network for Long-Context LLM Conversations](https://mlsanity.com/paper/2606.05182/) (2026)

## Abstract (arXiv)

While current large language models (LLMs) perform well on many knowledge-related tasks, they are limited by relying on their parameters as an implicit storage mechanism. As a result, they struggle with memorizing rare events and with updating their memory as facts change over time. In addition, the uninterpretable nature of parametric memory makes it challenging to prevent hallucination. Model editing and augmenting LLMs with parameters specialized for memory are only partial solutions. In this paper, we introduce MemLLM, a novel method of enhancing LLMs by integrating a structured and explicit read-and-write memory module. MemLLM tackles the aforementioned challenges by enabling dynamic interaction with the memory and improving the LLM's capabilities in using stored knowledge. Our experiments indicate that MemLLM enhances the LLM's performance and interpretability, in language modeling in general and knowledge-intensive tasks in particular. We see MemLLM as an important step towards making LLMs more grounded and factual through memory augmentation. The project repository is publicly available at https://github.com/amodaresi/MemLLM