# End-To-End Memory Networks

arXiv: https://arxiv.org/abs/1503.08895 · HTML: https://mlsanity.com/paper/1503.08895/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2015.

## Built on by (most cited first, 6 of 6)

- [Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents](https://mlsanity.com/paper/2502.06975/) (2025)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning](https://mlsanity.com/paper/2310.16731/) (2023)
- [Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?](https://mlsanity.com/paper/2503.07903/) (2025)
- [Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems](https://mlsanity.com/paper/2212.09252/) (2022)
- [The Hitchhiker's Guide to Agentic AI: From Foundations to Systems](https://mlsanity.com/paper/2606.24937/) (2026)

## Abstract (arXiv)

We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network (Weston et al., 2015) but unlike the model in that work, it is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings. It can also be seen as an extension of RNNsearch to the case where multiple computational steps (hops) are performed per output symbol. The flexibility of the model allows us to apply it to tasks as diverse as (synthetic) question answering and to language modeling. For the former our approach is competitive with Memory Networks, but with less supervision. For the latter, on the Penn TreeBank and Text8 datasets our approach demonstrates comparable performance to RNNs and LSTMs. In both cases we show that the key concept of multiple computational hops yields improved results.