# SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms

arXiv: https://arxiv.org/abs/2410.13553 · HTML: https://mlsanity.com/paper/2410.13553/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 15 of 15)

- [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)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Information Retrieval: Recent Advances and Beyond](https://mlsanity.com/paper/2301.08801/) (2023)
- ["My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents](https://mlsanity.com/paper/2404.00573/) (2024)
- [Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment](https://mlsanity.com/paper/2407.03051/) (2024)
- [Memory-augmented Dialogue Management for Task-oriented Dialogue Systems](https://mlsanity.com/paper/1805.00150/) (2018)
- [Multi-turn Dialogue Response Generation in an Adversarial Learning Framework](https://mlsanity.com/paper/1805.11752/) (2018)
- [Learning to Memorize in Neural Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.07687/) (2019)
- [Learning temporal relationships between symbols with Laplace Neural Manifolds](https://mlsanity.com/paper/2302.10163/) (2023)

## Built on by (most cited first, 5 of 5)

- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)
- [Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory](https://mlsanity.com/paper/2607.00017/) (2026)
- [PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs](https://mlsanity.com/paper/2603.09943/) (2026)
- [Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness](https://mlsanity.com/paper/2606.10413/) (2026)
- [EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution](https://mlsanity.com/paper/2608.23265/) (2026)

## Abstract (arXiv)

Existing retrieval methods in Large Language Models show degradation in accuracy when handling temporally distributed conversations, primarily due to their reliance on simple similarity-based retrieval. Unlike existing memory retrieval methods that rely solely on semantic similarity, we propose SynapticRAG, which uniquely combines temporal association triggers with biologically-inspired synaptic propagation mechanisms. Our approach uses temporal association triggers and synaptic-like stimulus propagation to identify relevant dialogue histories. A dynamic leaky integrate-and-fire mechanism then selects the most contextually appropriate memories. Experiments on four datasets of English, Chinese and Japanese show that compared to state-of-the-art memory retrieval methods, SynapticRAG achieves consistent improvements across multiple metrics up to 14.66% points. This work bridges the gap between cognitive science and language model development, providing a new framework for memory management in conversational systems.