Research
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
arXiv:2604.21748v1 Announce Type: cross Abstract: Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasonin
arXiv:2604.21748v1 Announce Type: cross 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 extbf{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 exttt{LoCoMo}, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem .
Related
- TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
- Human-like Working Memory Interference in Large Language Models
- From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
- Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
Source: arXiv cs.AI | 2026-04-24