# StructMem: Structured Memory for Long-Horizon Behavior in LLMs

arXiv: https://arxiv.org/abs/2604.21748 · HTML: https://mlsanity.com/paper/2604.21748/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 17 of 17)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Memp: Exploring Agent Procedural Memory](https://mlsanity.com/paper/2508.06433/) (2025)
- [LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning](https://mlsanity.com/paper/2511.01448/) (2025)
- [TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents](https://mlsanity.com/paper/2601.02845/) (2026)
- [A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2511.17208/) (2025)
- [MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents](https://mlsanity.com/paper/2512.20237/) (2025)
- [Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management](https://mlsanity.com/paper/2508.04664/) (2025)
- [Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue](https://mlsanity.com/paper/2509.10852/) (2025)
- [HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents](https://mlsanity.com/paper/2601.06377/) (2026)
- [From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory](https://mlsanity.com/paper/2511.07800/) (2025)
- [MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation](https://mlsanity.com/paper/2510.07713/) (2025)

## Built on by (most cited first, 18 of 18)

- [WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents](https://mlsanity.com/paper/2606.18847/) (2026)
- [LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory](https://mlsanity.com/paper/2607.22690/) (2026)
- [LightMem-Ego: Your AI Memory for Everyday Life](https://mlsanity.com/paper/2607.11487/) (2026)
- [CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents](https://mlsanity.com/paper/2608.01739/) (2026)
- [MemFail: Stress-Testing Failure Modes of LLM Memory Systems](https://mlsanity.com/paper/2605.26667/) (2026)
- [MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models](https://mlsanity.com/paper/2605.28009/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)
- [TokenPilot: Cache-Efficient Context Management for LLM Agents](https://mlsanity.com/paper/2606.17016/) (2026)
- [DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory](https://mlsanity.com/paper/2605.15759/) (2026)
- [Rethinking Memory as Continuously Evolving Connectivity](https://mlsanity.com/paper/2605.28773/) (2026)
- [T-Mem: Memory That Anticipates, Not Archives](https://mlsanity.com/paper/2606.15405/) (2026)
- [EM^2Mem: Event-Centric Multimodal Memory for Large Language Models](https://mlsanity.com/paper/2609.00551/) (2026)
- [MemTools: A Unified Research Framework for Interoperable Agent Memory](https://mlsanity.com/paper/2607.21404/) (2026)
- [MemFuse: Multi-Source Memory Fusion from Fragmented Observations](https://mlsanity.com/paper/2608.18704/) (2026)
- [Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents](https://mlsanity.com/paper/2608.31076/) (2026)
- [SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue](https://mlsanity.com/paper/2609.26780/) (2026)
- [Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation](https://mlsanity.com/paper/2609.32401/) (2026)
- [Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory](https://mlsanity.com/paper/2610.12874/) (2026)

## Abstract (arXiv)

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 textttLoCoMo, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem .