# MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

arXiv: https://arxiv.org/abs/2609.08273 · HTML: https://mlsanity.com/paper/2609.08273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory](https://mlsanity.com/paper/2508.09736/) (2025)
- [StreamForest: Efficient Online Video Understanding with Persistent Event Memory](https://mlsanity.com/paper/2509.24871/) (2025)
- [EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning](https://mlsanity.com/paper/2601.02163/) (2026)
- [WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning](https://mlsanity.com/paper/2512.02425/) (2025)
- [General Agentic Memory Via Deep Research](https://mlsanity.com/paper/2511.18423/) (2025)
- [StreamingTOM: Streaming Token Compression for Efficient Video Understanding](https://mlsanity.com/paper/2510.18269/) (2025)
- [O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents](https://mlsanity.com/paper/2511.13593/) (2025)
- [Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation](https://mlsanity.com/paper/2602.02007/) (2026)
- [From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents](https://mlsanity.com/paper/2603.01455/) (2026)
- [Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs](https://mlsanity.com/paper/2510.17364/) (2025)
- [StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding](https://mlsanity.com/paper/2604.09000/) (2026)

## Abstract (arXiv)

Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose MemForest, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into event-centric units by leveraging global semantic similarity and local temporal continuity. For each unit, it constructs a maximum spanning tree, termed an EventTree, and progressively merges redundant memory nodes by selecting high-weight edges, reducing storage overhead. Furthermore, we introduce an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy. Extensive experiments demonstrate the effectiveness of MemForest. Under the unimodal Mem0 framework, MemForest retains 97.1% of the original performance while compressing 50% of historical memory across three benchmarks (LoCoMo, LongMemEval, and PersonaMem), achieving a 1.89x retrieval speedup. Under the multimodal M3-Agent framework, it preserves 99.7% of the original performance with a 50% compression ratio across two benchmarks (M3-Bench-robot and M3-Bench-web), achieving a 2.24x retrieval speedup. textcolorRoyalBluetextitOur code is available at [https://github.com/Celina-love-sweet/MemForest.](https://github.com/Celina-love-sweet/MemForest.)