MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914593687732224 |
|---|---|
| author | Chen, Han Zhang, Zining Pei, Wenqi He, Bingsheng Wu, Ming Zeng, Jason Heinrich, Michael Wu, Wei Zhang, Hongbao |
| author_facet | Chen, Han Zhang, Zining Pei, Wenqi He, Bingsheng Wu, Ming Zeng, Jason Heinrich, Michael Wu, Wei Zhang, Hongbao |
| contents | Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-grained state management and inherently sequential update pipelines. In particular, updates are often tightly coupled with LLM inference and require full-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data management problem. MemForest breaks the sequential bottleneck via parallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees rather than flat global summaries. This design replaces full-state rewrites with localized per-node updates, reducing maintenance cost to the affected tree paths while naturally preserving temporally evolving states. We evaluate MemForest on two long-context memory benchmarks, LongMemEval-S and LoCoMo. On LongMemEval-S, MemForest achieves the best overall performance among stateful baselines, reaching 79.8% pass@1 accuracy while sustaining a memory construction throughput approximately 6x higher than state-of-the-art approaches including EverMemOS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23986 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing Chen, Han Zhang, Zining Pei, Wenqi He, Bingsheng Wu, Ming Zeng, Jason Heinrich, Michael Wu, Wei Zhang, Hongbao Databases Artificial Intelligence Multiagent Systems H.2.4; I.2.7; I.2.11 Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from significant maintenance overhead due to two key limitations: coarse-grained state management and inherently sequential update pipelines. In particular, updates are often tightly coupled with LLM inference and require full-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data management problem. MemForest breaks the sequential bottleneck via parallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees rather than flat global summaries. This design replaces full-state rewrites with localized per-node updates, reducing maintenance cost to the affected tree paths while naturally preserving temporally evolving states. We evaluate MemForest on two long-context memory benchmarks, LongMemEval-S and LoCoMo. On LongMemEval-S, MemForest achieves the best overall performance among stateful baselines, reaching 79.8% pass@1 accuracy while sustaining a memory construction throughput approximately 6x higher than state-of-the-art approaches including EverMemOS. |
| title | MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing |
| topic | Databases Artificial Intelligence Multiagent Systems H.2.4; I.2.7; I.2.11 |
| url | https://arxiv.org/abs/2605.23986 |