StructMem: Structured Memory for Long-Horizon Behavior in LLMs

ACL ARR 2026 January Submission3801 Authors

Keywords: large language model, LLM memory

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 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 LoCoMo, while substantially reducing token usage, API calls, and runtime compared to prior memory systems.

Paper Type: Short

Research Area: AI/LLM Agents

Research Area Keywords: LLM/AI agents, retrieval-augmented generation, applications, prompting

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 3801