Model Releases
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
arXiv:2604.06845v1 Announce Type: cross Abstract: Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely
arXiv:2604.06845v1 Announce Type: cross 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-extit{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) extit{what to retrieve}: determine the query-conditioned routing over the element-indexed memory; (b) extit{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; extit{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%ownarrow 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.
Related
- Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
- A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
- Dynamic Context Evolution for Scalable Synthetic Data Generation
- TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks
Source: arXiv cs.AI | 2026-04-10