Hierarchical Memory

Follow this topic Ask about this topic

Hierarchical memory studies how AI systems can organize information across levels, from compact summaries and reusable patterns to detailed episodes and original evidence. Common approaches use trees, graphs, or tiered stores, with temporal or semantic indexing, consolidation, and query-adaptive routing to retrieve only the context a task needs. These methods support long-running conversational and multimodal agents, and are often evaluated on benchmarks such as LoCoMo and LongMemEval. A central challenge is balancing lower storage and context costs against accurate, traceable retrieval: deeper hierarchies do not always improve answers, and summaries can omit details needed for reasoning.

Latest papers

42 papers4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
Oct 27, 2026Xinying Qian, Ying Zhang, Yu Zhao +3Memory Management for LLM Agents Long-Term Conversational Memory
Nankai University, Tianjin, China · Tiangong University, Tianjin, China · The University of Edinburgh, Edinburgh, United Kingdom
Stratum: Repository Memory for Coding Agents Beyond the Context Window
Oct 26, 2026Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-JivanLLM Agent Memory Memory Management for LLM Agents
Department of Computer Science, Brock University, St. Catharines, Ontario, Canada · School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada
EGCForest: Structured Agent Memory Organization for Enterprise Group Chats
Oct 14, 2026Lingxi Cui, Jinhao Ruan, Wenqing Wei +4Conversational Memory Evidence Retrieval
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · Xiaohongshu
Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval
Oct 6, 2026Michael AndreevConversational Memory LLM Evaluation
Independent Researcher
APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory
Oct 1, 2026Chin-Lun Fu, Anagha Kulkarni, Hong Ni +1Long-Term Conversational Memory Agent Memory Management
Machine Learning Center of Excellence, JPMorgan Chase & Co.
MemCodex: Self-Programming Hierarchical Memory for Language Agents
Sep 30, 2026Xiaoqiang Wang, Bang LiuAgent Memory Management Memory-Augmented Language Model Agents
Université de Montréal · Mila – Quebec AI Institute
AtomWorld-Mem: Memory-Restored World States for Long-Horizon Atomistic Evolution
Sep 25, 2026Tian Luo, Ruge Zhang, Haozhi Han +5Hierarchical Memory Latent World Models
Sichuan University, Chengdu, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China +2
Hierarchical Prototype Emergence in Modern Hopfield Models
Sep 10, 2026Aditya Cowsik, Adithya SriramNeural Network Generalization Hopfield Networks
Department of Physics, Stanford University, Stanford, CA 94305, USA
Not All Memories Are Equal: Hierarchical Collaborative Memory for Validity-Aware Retrieval in LLM Agents
Sep 9, 2026Yufei Shi, Rujing Yao, Ang Li +3Memory-Augmented Language Model Agents Hierarchical Memory
Nanyang Technological University, Singapore · University of Macau, China · Worcester Polytechnic Institute, USA +1
Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers
Aug 31, 2026Mohammed Yusuf Mujawar, Noorbakhsh Amiri GolilarzHebbian Learning Vision Transformer
Department of Computer Science The University of Alabama, Tuscaloosa, AL, USA
MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data
Aug 22, 2026Xinyuan Song, Bowen Zhu, Hasibul Haque +1Retrieval-Augmented Generation Hierarchical Memory
Causal Dynamics Lab, USA · Emory University, USA
Consolidator: Learning Persistent Routed Memory Across Context Boundaries
Aug 12, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungMemory-Augmented Neural Networks Persistent Memory for Language Models
College of Pharmacy, Chungnam National University · Department of Computer Science & Engineering, Chungnam National University
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
Aug 5, 2026Xiawei Yue, Boran Wang, Xiaoqing Zhang +2LLM Agent Memory Graph-Based Agent Memory
Nankai University, Tianjin, China · Zhongguancun Academy, Beijing, China · Beihang University, Beijing, China
MCHA: A Memory-Centric Hierarchical Architecture for Parallel-Sequential Computing
Aug 5, 2026Daijing Shi, Hongxiao Zhao, Yihan Fu +7Hierarchical Memory
Peking University, Beijing 100871, China
MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents
Jul 6, 2026Jizhizi Li, Amy Shi-NashGraph-Based Agent Memory Hierarchical Memory
NxtLab Innovations
LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams
Jun 16, 2026Zhenyu Yang, Kairui Zhang, Bing Wang +2Streaming Video Understanding Long-Video Understanding
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision
Jun 15, 2026Ye Jin, Yangyang Xu, Jun Zhu +1LLM Personalization Hierarchical Memory
Beijing University of Posts and Telecommunications · Tsinghua University · Shanghai Jiao Tong University
MADAR: An Address-Free Processor
Jun 14, 2026Mohamed Amine BergachEnergy-Efficient ML Hierarchical Memory
Illumina San Diego, California, USA
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
Jun 10, 2026Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu +2Hierarchical Memory Long-Horizon Agent Tasks
Duke University · Snowflake AI Research
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
Jun 5, 2026Cong Chen, Guo Gan, Kaixiang Ji +7Agentic Retrieval Long-Video Understanding
Ant Group · Zhejiang University · Central South University +2
PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents
Jun 3, 2026Yubo Hou, Jingwei Song, Hongbo Zhang +4LLM Personalization LLM Agent Memory
School of ASEE, Beihang University, Beijing, China · The University of Hong Kong, Hong Kong, China · Peking University, Beijing, China +3
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
Jun 3, 2026Yifan Simon Liu, Liam Gallagher, Faeze Moradi Kalarde +3Temporal IR Hierarchical Memory
University of Toronto · 2Vector Institute for Artificial Intelligence
PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search
Jun 2, 2026Kailin Lyu, Zhiqiang Yuan, Jianwei He +9Multimodal Search Agents Hierarchical Memory
Pattern Recognition Center, WeChat AI, Tencent Inc. · Institute of Automation, Chinese Academy of Sciences · Zhongguancun Academy +2
Evaluation of Baseline Methods for IDD-based SSD External Memory Search
Jun 1, 2026Yuki Suzuki, Alex FukunagaTree Search Hierarchical Memory
The University of Tokyo
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
May 16, 2026Han Chen, Zining Zhang, Wenqi Pei +6LLM Agent Memory Hierarchical Memory
National University of Singapore · Singapore, Singapore · Zero Gravity Labs +1
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
May 15, 2026Jiawei Yu, Yixiang Fang, Xilin Liu +1Agent Memory LLM Agent Memory
The Chinese University of Hong Kong, Shenzhen · Huawei Cloud Computing Technologies CO., LTD.
Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning
May 10, 2026Aojie Yuan, Tianqi Shen, Dajun ZhangKV-Cache Offloading KV Caching
University of Southern California · †University of Wisconsin–Madison
MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
May 5, 2026Bronislav Sidik, Lior RokachLLM Agent Memory Hierarchical Memory
Institute for Applied AI Research · Faculty of Computer and Information Science · Ben-Gurion University of the Negev, Beer Sheva, Israel
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
Apr 23, 2026Buqiang Xu, Yijun Chen, Jizhan Fang +5Multi-Hop QA Temporal Reasoning
Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group
WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
Apr 20, 2026Harish Santhanalakshmi GanesanTemporal KGs Persistent Memory for Language Models
Independent Researcher

Oct 27, 2026J/K move · Enter open · S save

ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents

Xinying Qian, Ying Zhang, Yu Zhao, Xubo Liu+2

Nankai University, Tianjin, China · Tiangong University, Tianjin, China · The University of Edinburgh, Edinburgh, United Kingdom

Memory Management for LLM Agents Long-Term Conversational Memory Memory-Augmented Language Models Hierarchical Memory

Open paper AskPDF arXiv

Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entanglement, where heterogeneous information is mixed within coarse-grained memory units; and (2) Organizational Mismatch, where memory structures based primarily on semantic similarity may overlook other associations. To address these challenges, we propose ETAMem, a multi-view memory framework that decouples heterogeneous conversational information and aligns memory representations and organization with its distinct characteristics. Specifically, heterogeneous information parsing extracts atomic memory units and identifies affective information. View-specific memory structuring then organizes these units into three complementary hierarchical views: Event, Affect, and Time. ETAMem incrementally maintains memory structures with adaptively calibrated thresholds. For retrieval, entropy-based retrieval allocates query-specific budgets across views and performs hierarchical search within each view. Experiments on LoCoMo and LongMemEval-S demonstrate that ETAMem outperforms state-of-the-art baselines, achieving relative accuracy improvements of 12.46% and 7.96%, respectively, while maintaining competitive token efficiency. Further analyses demonstrate the complementary benefits of different memory views.