MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Summary
MemForest proposes a memory framework for long-context LLM agents that improves scalability and reduces latency through parallel chunk extraction and hierarchical temporal indexing, achieving 6x higher throughput on benchmarks.
View Cached Full Text
Cached at: 05/26/26, 06:42 AM
Paper page - MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Source: https://huggingface.co/papers/2605.23986
Abstract
MemForest presents a memory framework for long-context LLM agents that improves scalability and reduces latency through parallel chunk extraction and hierarchical temporal indexing.
Memory is a fundamental component for enablinglong-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 requirefull-state rewrites, leading to poor scalability and growing latency as memory accumulates. To address these challenges, we present MemForest, amemory frameworkthat reformulates agent memory as a write-efficienttemporal data managementproblem. MemForest breaks the sequential bottleneck viaparallel chunk extraction, decoupling memory construction into concurrent, independent operations. To further eliminate coarse-grained maintenance, we introduceMemTree, ahierarchical temporal indexthat organizes memory as time-ordered trees rather than flat global summaries. This design replacesfull-state rewriteswithlocalized 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.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.23986
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.23986 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.23986 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.23986 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
This paper presents the first systematic exploration of filesystem-based memory for LLM agents, formalizing roles of management, search, and execution agents around a shared memory store. It finds that organization primarily reduces retrieval cost but does not yet improve answer quality, and that tooling choices affect store shape as much as model selection.
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
H-Mem is a novel memory mechanism for LLM-based agents that uses a hybrid structure combining a temporal and semantic tree with a knowledge graph to model memory evolution and improve retrieval, achieving state-of-the-art performance on QA benchmarks.
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
DimMem introduces a dimensional memory framework for LLM agents that represents memories as atomic, typed units with explicit fields, achieving state-of-the-art accuracy on LoCoMo-10 and LongMemEval-S while reducing token costs by 24%.
HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents
The paper proposes HasMem, an adaptive memory compression method for long-term LLM agents that adjusts memory widths while maintaining frozen LLM parameters, demonstrating improved performance on reconstruction and QA benchmarks.
AdMem: Advanced Memory for Task-solving Agents
This paper introduces AdMem, a unified memory framework for LLM-based agents that integrates semantic, episodic, and procedural memory with a bi-level short-term and long-term store, using a multi-agent architecture for automatic memory generation and adaptive retrieval. Experiments show improved robustness and success on long multi-turn tasks.