# Memory in Deep Time-Series Models

arXiv: https://arxiv.org/abs/2609.06006 · HTML: https://mlsanity.com/paper/2609.06006/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 36 of its 176 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)

## Builds on (most cited first, 30 of 36)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting](https://mlsanity.com/paper/2403.09898/) (2024)
- [Retrieval Augmented Time Series Forecasting](https://mlsanity.com/paper/2411.08249/) (2024)
- [REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models](https://mlsanity.com/paper/2402.07016/) (2024)
- [A Memory-Network Based Solution for Multivariate Time-Series Forecasting](https://mlsanity.com/paper/1809.02105/) (2018)
- [TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis](https://mlsanity.com/paper/2510.01538/) (2025)
- [Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models](https://mlsanity.com/paper/2501.14170/) (2025)
- [Retrieval Based Time Series Forecasting](https://mlsanity.com/paper/2209.13525/) (2022)
- [SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting](https://mlsanity.com/paper/2404.14757/) (2024)
- [Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting](https://mlsanity.com/paper/2404.15772/) (2024)
- [MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting](https://mlsanity.com/paper/2405.16440/) (2024)
- [Agentic Retrieval-Augmented Generation for Time Series Analysis](https://mlsanity.com/paper/2408.14484/) (2024)
- [AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting](https://mlsanity.com/paper/2511.08947/) (2025)
- [Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting](https://mlsanity.com/paper/2602.13802/) (2026)
- [Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting](https://mlsanity.com/paper/2602.01776/) (2026)
- [MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning](https://mlsanity.com/paper/2602.03164/) (2026)
- [Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision](https://mlsanity.com/paper/2506.00807/) (2025)
- [Nexus : An Agentic Framework for Time Series Forecasting](https://mlsanity.com/paper/2605.14389/) (2026)
- [AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning](https://mlsanity.com/paper/2602.13807/) (2026)
- [Patch-based Memory Gate Model in Time Series Foundation Model](https://mlsanity.com/paper/2509.18751/) (2025)
- [MambaSL: Exploring Single-Layer Mamba for Time Series Classification](https://mlsanity.com/paper/2604.15174/) (2026)
- [RATSF: Empowering Customer Service Volume Management through Retrieval-Augmented Time-Series Forecasting](https://mlsanity.com/paper/2403.04180/) (2024)

## Abstract (arXiv)

Deep learning for time series has progressed through successive architectural paradigms, from recurrent networks and transformers to structured state-space models, retrieval-augmented predictors, foundation models, and tool-using agents. These developments are typically studied in isolation, organized by architecture or modeling era. We argue that they can instead be viewed through a common question of how does a time-series model retain and access information beyond its immediate input? This question is motivated by a fundamental limitation of conventional time-series modeling: information relevant to a prediction may lie far beyond a feasible input window, while compressing history into a fixed-size state can discard information that may become useful later. We formulate this challenge as a memory problem and organize existing time-series methods along a spectrum from internal memory, encoded in parameters and fixed-size states, to external memory that is addressable, retrievable, and increasingly maintained by agents. We then develop a unified taxonomy of memory mechanisms and review three classes of external memory, including explicit modules, retrieval augmentation, and agentic stores, under a common framework for what is retained, how it is written and accessed, and how it persists. A cross-cutting analysis maps these mechanisms to time-series tasks and identifies gaps in both methods and evaluation. We conclude by outlining open problems in building memory systems that can selectively retain, retrieve, revise, and forget information as temporal environments evolve. The result is a framework for studying memory as a first-class dimension of time series modeling, independent of the underlying backbone.