HingeMem: 基于边界的长期记忆与查询自适应检索用于可扩展对话
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
AI总结：
HingeMem通过边界引导的长期记忆和查询自适应检索，提升对话系统在多轮交互中的记忆效率与适应性，实验表明在不同规模的LLM上实现20%的性能提升并降低计算成本。
摘要：
长期记忆对于支持连续、可持续和个性化交互的对话系统至关重要。然而，现有方法依赖于连续摘要或基于OpenIE的图构建，配以固定Top-k检索，导致查询类别适应性有限且计算开销高。本文提出HingeMem，一种基于边界的长期记忆，通过事件分割理论构建可解释的索引接口，利用边界触发的超边在四要素（人、时间、地点、主题）上建立索引。当任一要素变化时，HingeMem绘制边界并写入当前段，从而减少冗余操作并保留显著上下文。为在多样化的信息需求下实现稳健高效的检索，HingeMem引入查询自适应检索机制，联合决定（a）检索什么：确定基于查询条件的要素索引记忆路由；（b）检索多少：根据估计的查询类型控制检索深度。在LLM规模（从0.6B到生产级模型；例如，Qwen3-0.6B到Qwen-Flash）的LOCOMO数据集上进行的广泛实验表明，HingeMem在无查询类别指定的情况下，相对于强基线模型实现了约20%的相对提升，同时将计算成本降低68%（相比HippoRAG2）。除了推进记忆建模，HingeMem的自适应检索使其成为需要高效和可信长期记忆的网络应用中的有力选择。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
