Paper Detail
Buqiang Xu, Yijun Chen, Jizhan Fang, Ruobin Zhong, Yunzhi Yao, Yuqi Zhu, Lun Du, Shumin Deng
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 .
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{xu2026structmem,
title = {StructMem: Structured Memory for Long-Horizon Behavior in LLMs},
author = {Buqiang Xu and Yijun Chen and Jizhan Fang and Ruobin Zhong and Yunzhi Yao and Yuqi Zhu and Lun Du and Shumin Deng},
year = {2026},
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 \textbackslash{}textbf\{StructMem\}, a structure-enriched hierarchical memo},
url = {https://arxiv.org/abs/2604.21748},
keywords = {cs.CL, cs.AI, cs.IR, cs.LG, cs.MA},
eprint = {2604.21748},
archiveprefix = {arXiv},
}
{}