# ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents

arXiv: https://arxiv.org/abs/2601.07582 · HTML: https://mlsanity.com/paper/2601.07582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [Human-inspired Episodic Memory for Infinite Context LLMs](https://mlsanity.com/paper/2407.09450/) (2024)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [What Deserves Memory: Adaptive Memory Distillation for LLM Agents](https://mlsanity.com/paper/2508.03341/) (2025)
- [Topic-Aware Multi-turn Dialogue Modeling](https://mlsanity.com/paper/2009.12539/) (2020)
- [SGMem: Sentence Graph Memory for Long-Term Conversational Agents](https://mlsanity.com/paper/2509.21212/) (2025)
- [TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling](https://mlsanity.com/paper/2109.04562/) (2021)
- [Can LLM Agents Maintain a Persona in Discourse?](https://mlsanity.com/paper/2502.11843/) (2025)
- [MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning](https://mlsanity.com/paper/2510.13614/) (2025)
- [SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation](https://mlsanity.com/paper/2305.08371/) (2023)
- [Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation](https://mlsanity.com/paper/2505.21033/) (2025)

## Built on by (most cited first, 4 of 4)

- [Query-focused and Memory-aware Reranker for Long Context Processing](https://mlsanity.com/paper/2602.12192/) (2026)
- [FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue](https://mlsanity.com/paper/2608.16303/) (2026)
- [MEMO: Multimodal Evidence Memory Organization for Long-Horizon LLM Agents](https://mlsanity.com/paper/2609.07471/) (2026)
- [Grounding Memory Summarization in Utility Intent](https://mlsanity.com/paper/2609.33417/) (2026)

## Abstract (arXiv)

Memory is critical for dialogue agents to maintain coherence and enable continuous adaptation in long-term interactions. While existing memory mechanisms offer basic storage and retrieval capabilities, they are hindered by two primary limitations: (1) rigid memory granularity often disrupts semantic integrity, resulting in fragmented and incoherent memory units; (2) prevalent flat retrieval paradigms rely solely on surface-level semantic similarity, neglecting the structural cues of discourse required to navigate and locate specific episodic contexts. To mitigate these limitations, drawing inspiration from Event Segmentation Theory, we propose ES-Mem, a framework incorporating two core components: (1) a dynamic event segmentation module that partitions long-term interactions into semantically coherent events with distinct boundaries; (2) a hierarchical memory architecture that constructs multi-layered memories and leverages boundary semantics to anchor specific episodic memory for precise context localization. Evaluations on two memory benchmarks demonstrate that ES-Mem yields consistent performance gains over baseline methods. Furthermore, the proposed event segmentation module exhibits robust applicability on dialogue segmentation datasets.