# Hierarchical Memory Orchestration for Personalized Persistent Agents

arXiv: https://arxiv.org/abs/2604.01670 · HTML: https://mlsanity.com/paper/2604.01670/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation](https://mlsanity.com/paper/2409.05591/) (2024)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [MemVerse: Multimodal Memory for Lifelong Learning Agents](https://mlsanity.com/paper/2512.03627/) (2025)
- [Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking](https://mlsanity.com/paper/2506.09944/) (2025)
- [TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents](https://mlsanity.com/paper/2601.02845/) (2026)
- [Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation](https://mlsanity.com/paper/2403.02135/) (2024)
- [Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models](https://mlsanity.com/paper/2508.09874/) (2025)

## Built on by (most cited first, 4 of 4)

- [Mi-Memory: A Lifecycle Memory Framework for Personal AI](https://mlsanity.com/paper/2607.18975/) (2026)
- [The Compaction Cliff in Long-Running AI Agent Memory](https://mlsanity.com/paper/2608.22752/) (2026)
- [MemCodex: Self-Programming Hierarchical Memory for Language Agents](https://mlsanity.com/paper/2609.39765/) (2026)
- [MIRROR: From Imitation to Internalization in LLM Personalization](https://mlsanity.com/paper/2610.09795/) (2026)

## Abstract (arXiv)

While long-term memory is essential for intelligent agents to maintain consistent historical awareness, the accumulation of extensive interaction data often leads to performance bottlenecks. Naive storage expansion increases retrieval noise and computational latency, overwhelming the reasoning capacity of models deployed on constrained personal devices. To address this, we propose Hierarchical Memory Orchestration (HMO), a framework that organizes interaction history into a three-tiered directory driven by user-centric contextual relevance. Our system maintains a compact primary cache, coupling recent and pivotal memories with an evolving user profile to ensure agent reasoning remains aligned with individual behavioral traits. This primary cache is complemented by a high-priority secondary layer, both of which are managed within a global archive of the full interaction history. Crucially, the user persona dictates memory redistribution across this hierarchy, promoting records mapped to long-term patterns toward more active tiers while relegating less relevant information. This targeted orchestration surfaces historical knowledge precisely when needed while maintaining a lean and efficient active search space. Evaluations on multiple benchmarks achieve state-of-the-art performance. Real-world deployments in ecosystems like OpenClaw demonstrate that HMO significantly enhances agent fluidity and personalization.