# The AI Hippocampus: How Far are We From Human Memory?

arXiv: https://arxiv.org/abs/2601.09113 · HTML: https://mlsanity.com/paper/2601.09113/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 14 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Built on by (most cited first, 11 of 11)

- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation](https://mlsanity.com/paper/2604.00131/) (2026)
- [M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks](https://mlsanity.com/paper/2606.05008/) (2026)
- [MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval](https://mlsanity.com/paper/2602.08369/) (2026)
- [Memory as Metabolism: A Design for Companion Knowledge Systems](https://mlsanity.com/paper/2604.12034/) (2026)
- [SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States](https://mlsanity.com/paper/2605.04496/) (2026)
- [DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory](https://mlsanity.com/paper/2605.22411/) (2026)
- [LLM-enabled Social Agents](https://mlsanity.com/paper/2605.02335/) (2026)
- [Learning with a Single Rollout via Pass@k Policy Optimization](https://mlsanity.com/paper/2606.25451/) (2026)
- [From Observation to Intervention: Memory in Brains and Large Language Models](https://mlsanity.com/paper/2608.12377/) (2026)

## Abstract (arXiv)

Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of continual learning and personalized inference, the incorporation of memory mechanisms has emerged as a central theme in their architectural and functional evolution. This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms. Specifically, the survey delineates three primary memory frameworks. Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers, encompassing their capacity for memorization, associative retrieval, and contextual reasoning. Recent work has explored methods to interpret, manipulate, and reconfigure this latent memory. Explicit memory involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations, such as textual corpora, dense vectors, and graph-based structures, thereby enabling scalable and updatable interaction with information sources. Agentic memory introduces persistent, temporally extended memory structures within autonomous agents, facilitating long-term planning, self-consistency, and collaborative behavior in multi-agent systems, with relevance to embodied and interactive AI. Extending beyond text, the survey examines the integration of memory within multi-modal settings, where coherence across vision, language, audio, and action modalities is essential. Key architectural advances, benchmark tasks, and open challenges are discussed, including issues related to memory capacity, alignment, factual consistency, and cross-system interoperability.