# StructMem: Structured Memory for Long-Horizon Behavior in LLMs Source: [StructMem: Structured Memory for Long-Horizon Behavior in LLMs]() Collection index: [llms.txt]() Data updated: 2026-04-25T05:00:11.494Z Authors: Buqiang Xu, Yijun Chen, Jizhan Fang, Ruobin Zhong, Yunzhi Yao, Yuqi Zhu, Lun Du, Shumin Deng Published: 2026-04-23T14:57:23.000Z ## Abstract Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose \\textbf{StructMem}, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on \\texttt{LoCoMo}, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem . ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Long-term dialogue memory on LoCoMo (test)](): Long-term dialogue memory; LoCoMo (test); Accuracy: 76.82. - [Long-term memory evaluation on LoCoMo](): Long-term memory evaluation; Locomo; Overall F1: not recorded. ## Original sources and implementation [Original paper]() [PDF]()