# AI-native Memory: A Pathway from LLMs Towards AGI

arXiv: https://arxiv.org/abs/2406.18312 · HTML: https://mlsanity.com/paper/2406.18312/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [Make Your LLM Fully Utilize the Context](https://mlsanity.com/paper/2404.16811/) (2024)
- [Long Context Compression with Activation Beacon](https://mlsanity.com/paper/2401.03462/) (2024)
- [MEMORYLLM: Towards Self-Updatable Large Language Models](https://mlsanity.com/paper/2402.04624/) (2024)
- [Attention Sorting Combats Recency Bias In Long Context Language Models](https://mlsanity.com/paper/2310.01427/) (2023)
- [How Do Large Language Models Acquire Factual Knowledge During Pretraining?](https://mlsanity.com/paper/2406.11813/) (2024)

## Built on by (most cited first, 12 of 12)

- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation](https://mlsanity.com/paper/2510.25536/) (2025)
- [AI-native Memory 2.0: Second Me](https://mlsanity.com/paper/2503.08102/) (2025)
- [Towards LifeSpan Cognitive Systems](https://mlsanity.com/paper/2409.13265/) (2024)
- [Self-Taught Agentic Long Context Understanding](https://mlsanity.com/paper/2502.15920/) (2025)
- [How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants](https://mlsanity.com/paper/2601.16621/) (2026)
- [Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact](https://mlsanity.com/paper/2507.00951/) (2025)
- [Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs](https://mlsanity.com/paper/2602.08563/) (2026)
- [Tuning LLMs by RAG Principles: Towards LLM-native Memory](https://mlsanity.com/paper/2503.16071/) (2025)
- [AGI Enabled Solutions For IoX Layers Bottlenecks In Cyber-Physical-Social-Thinking Space](https://mlsanity.com/paper/2506.22487/) (2025)
- [Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI](https://mlsanity.com/paper/2511.18517/) (2025)
- [Position: Hippocampal Explicit Memory Is the Cornerstone for AGI](https://mlsanity.com/paper/2606.11245/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated the world with the sparks of artificial general intelligence (AGI). One opinion, especially from some startups working on LLMs, argues that an LLM with nearly unlimited context length can realize AGI. However, they might be too optimistic about the long-context capability of (existing) LLMs -- (1) Recent literature has shown that their effective context length is significantly smaller than their claimed context length; and (2) Our reasoning-in-a-haystack experiments further demonstrate that simultaneously finding the relevant information from a long context and conducting (simple) reasoning is nearly impossible. In this paper, we envision a pathway from LLMs to AGI through the integration of memory. We believe that AGI should be a system where LLMs serve as core processors. In addition to raw data, the memory in this system would store a large number of important conclusions derived from reasoning processes. Compared with retrieval-augmented generation (RAG) that merely processing raw data, this approach not only connects semantically related information closer, but also simplifies complex inferences at the time of querying. As an intermediate stage, the memory will likely be in the form of natural language descriptions, which can be directly consumed by users too. Ultimately, every agent/person should have its own large personal model, a deep neural network model (thus AI-native) that parameterizes and compresses all types of memory, even the ones cannot be described by natural languages. Finally, we discuss the significant potential of AI-native memory as the transformative infrastructure for (proactive) engagement, personalization, distribution, and social in the AGI era, as well as the incurred privacy and security challenges with preliminary solutions.