# Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage

arXiv: https://arxiv.org/abs/2602.16192 · HTML: https://mlsanity.com/paper/2602.16192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 18 Feb 2026.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption](https://mlsanity.com/paper/2407.18003/) (2024)
- [Human-inspired Episodic Memory for Infinite Context LLMs](https://mlsanity.com/paper/2407.09450/) (2024)
- [FLEX: Continuous Agent Evolution via Forward Learning from Experience](https://mlsanity.com/paper/2511.06449/) (2025)
- [Contextual Experience Replay for Self-Improvement of Language Agents](https://mlsanity.com/paper/2506.06698/) (2025)
- [General Agentic Memory Via Deep Research](https://mlsanity.com/paper/2511.18423/) (2025)
- [On the generalization of language models from in-context learning and finetuning: a controlled study](https://mlsanity.com/paper/2505.00661/) (2025)
- [INMS: Memory Sharing for Large Language Model based Agents](https://mlsanity.com/paper/2404.09982/) (2024)
- [Do Large Language Models Need a Content Delivery Network?](https://mlsanity.com/paper/2409.13761/) (2024)
- [RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems](https://mlsanity.com/paper/2508.01415/) (2025)
- [Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences](https://mlsanity.com/paper/2509.16189/) (2025)
- [AI-native Memory 2.0: Second Me](https://mlsanity.com/paper/2503.08102/) (2025)
- [ARIA: Training Language Agents with Intention-Driven Reward Aggregation](https://mlsanity.com/paper/2506.00539/) (2025)
- [RoboOS-NeXT: A Unified Memory-based Framework for Lifelong, Scalable, and Robust Multi-Robot Collaboration](https://mlsanity.com/paper/2510.26536/) (2025)
- [Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval](https://mlsanity.com/paper/2506.00041/) (2025)
- [AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information Retrieval](https://mlsanity.com/paper/2404.06004/) (2024)

## Built on by (most cited first, 1 of 1)

- [KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse](https://mlsanity.com/paper/2610.13060/) (2026)

## Abstract (arXiv)

Driven by our mission of "uplifting the world with memory," this paper explores the design concept of "memory" that is essential for achieving artificial superintelligence (ASI). Rather than proposing novel methods, we focus on several alternative approaches whose potential benefits are widely imaginable, yet have remained largely unexplored. The currently dominant paradigm, which can be termed "extract then store," involves extracting information judged to be useful from experiences and saving only the extracted content. However, this approach inherently risks the loss of information, as some valuable knowledge particularly for different tasks may be discarded in the extraction process. In contrast, we emphasize the "store then on-demand extract" approach, which seeks to retain raw experiences and flexibly apply them to various tasks as needed, thus avoiding such information loss. In addition, we highlight two further approaches: discovering deeper insights from large collections of probabilistic experiences, and improving experience collection efficiency by sharing stored experiences. While these approaches seem intuitively effective, our simple experiments demonstrate that this is indeed the case. Finally, we discuss major challenges that have limited investigation into these promising directions and propose research topics to address them.