# MEMO: A Deep Network for Flexible Combination of Episodic Memories

arXiv: https://arxiv.org/abs/2001.10913 · HTML: https://mlsanity.com/paper/2001.10913/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2020.

## Built on by (most cited first, 21 of 21)

- [PonderNet: Learning to Ponder](https://mlsanity.com/paper/2107.05407/) (2021)
- [TransDreamer: Reinforcement Learning with Transformer World Models](https://mlsanity.com/paper/2202.09481/) (2022)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [The CLRS Algorithmic Reasoning Benchmark](https://mlsanity.com/paper/2205.15659/) (2022)
- [Towards mental time travel: a hierarchical memory for reinforcement learning agents](https://mlsanity.com/paper/2105.14039/) (2021)
- [Embodied AI: From LLMs to World Models](https://mlsanity.com/paper/2509.20021/) (2025)
- [Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold](https://mlsanity.com/paper/2202.00159/) (2022)
- [A Rubric for Human-like Agents and NeuroAI](https://mlsanity.com/paper/2212.04401/) (2022)
- [Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture](https://mlsanity.com/paper/2310.03052/) (2023)
- [Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking](https://mlsanity.com/paper/2112.00086/) (2021)
- [A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information](https://mlsanity.com/paper/2305.07565/) (2023)
- [TransDreamerV3: Implanting Transformer In DreamerV3](https://mlsanity.com/paper/2506.17103/) (2025)
- [Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System](https://mlsanity.com/paper/2207.07827/) (2022)
- [Universal Recurrent Event Memories for Streaming Data](https://mlsanity.com/paper/2307.15694/) (2023)
- [From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers](https://mlsanity.com/paper/2506.19686/) (2025)
- [From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems](https://mlsanity.com/paper/2507.22077/) (2025)
- [Understanding in Artificial Intelligence](https://mlsanity.com/paper/2101.06573/) (2021)
- [DNCs Require More Planning Steps](https://mlsanity.com/paper/2406.02187/) (2024)
- [Learning Model Successors](https://mlsanity.com/paper/2502.00197/) (2025)
- [Graceful forgetting: Memory as a process](https://mlsanity.com/paper/2502.11105/) (2025)
- [Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks](https://mlsanity.com/paper/2502.13918/) (2025)

## Abstract (arXiv)

Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number of tasks requiring reasoning. Here we employed a classic associative inference task from the memory-based reasoning neuroscience literature in order to more carefully probe the reasoning capacity of existing memory-augmented architectures. This task is thought to capture the essence of reasoning -- the appreciation of distant relationships among elements distributed across multiple facts or memories. Surprisingly, we found that current architectures struggle to reason over long distance associations. Similar results were obtained on a more complex task involving finding the shortest path between nodes in a path. We therefore developed MEMO, an architecture endowed with the capacity to reason over longer distances. This was accomplished with the addition of two novel components. First, it introduces a separation between memories (facts) stored in external memory and the items that comprise these facts in external memory. Second, it makes use of an adaptive retrieval mechanism, allowing a variable number of "memory hops" before the answer is produced. MEMO is capable of solving our novel reasoning tasks, as well as match state of the art results in bAbI.