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

TL;DR

HingeMem introduces a boundary-guided, interpretable long-term memory system with query-adaptive retrieval, significantly improving dialogue memory efficiency and effectiveness across large language models.

Contribution

The paper proposes HingeMem, a novel boundary-guided memory with adaptive retrieval, enhancing scalability and interpretability in dialogue systems.

Findings

Achieves ~20% improvement over baselines in LOCOMO tasks.

Reduces computational cost by 68% in question answering.

Effective across models from 0.6B to production-scale.

Abstract

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-\textit{k} 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) \textit{what to retrieve}: determine the query-conditioned routing over the element-indexed memory; (b) \textit{how 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; \textit{e.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.