# HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues

arXiv: https://arxiv.org/abs/2604.06845 · HTML: https://mlsanity.com/paper/2604.06845/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Long Time No See! Open-Domain Conversation with Long-Term Persona Memory](https://mlsanity.com/paper/2203.05797/) (2022)
- [Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models](https://mlsanity.com/paper/2308.15022/) (2023)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs](https://mlsanity.com/paper/2409.19401/) (2024)
- [Towards Verifiable Text Generation with Evolving Memory and Self-Reflection](https://mlsanity.com/paper/2312.09075/) (2023)
- [Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis](https://mlsanity.com/paper/2506.01262/) (2025)
- [MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation](https://mlsanity.com/paper/2409.15240/) (2024)
- [Memory-augmented Dialogue Management for Task-oriented Dialogue Systems](https://mlsanity.com/paper/1805.00150/) (2018)

## Built on by (most cited first, 2 of 2)

- [LeanMem: Simple and Efficient Long-Term Memory for LLM Agents](https://mlsanity.com/paper/2608.03463/) (2026)
- [Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation](https://mlsanity.com/paper/2609.08599/) (2026)

## Abstract (arXiv)

Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed Top-textitk retrieval, leading to limited adaptability across query categories and high computational overhead. In this paper, we propose HingeMem, a boundary-guided long-term memory that operationalizes event segmentation theory to build an interpretable indexing interface via boundary-triggered hyperedges over four elements: person, time, location, and topic. When any such element changes, HingeMem draws a boundary and writes the current segment, thereby reducing redundant operations and preserving salient context. To enable robust and efficient retrieval under diverse information needs, HingeMem introduces query-adaptive retrieval mechanisms that jointly decide (a) textitwhat to retrieve: determine the query-conditioned routing over the element-indexed memory; (b) textithow much to retrieve: control the retrieval depth based on the estimated query type. Extensive experiments across LLM scales (from 0.6B to production-tier models; textite.g., Qwen3-0.6B to Qwen-Flash) on LOCOMO show that HingeMem achieves approximately 20% relative improvement over strong baselines without query categories specification, while reducing computational cost (68%downarrow question answering token cost compared to HippoRAG2). Beyond advancing memory modeling, HingeMem's adaptive retrieval makes it a strong fit for web applications requiring efficient and trustworthy memory over extended interactions.