EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning

Papers with Code Trending Papers
memory-systems long-term-reasoning llm-agents self-organizing huggingface

Summary

EverMemOS is a self-organizing memory operating system for large language models that enhances long-horizon reasoning by structuring dialogue into memory cells and scenes.

Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions. Existing memory systems often store isolated records and retrieve fragments, limiting their ability to consolidate evolving user states and resolve conflicts. We introduce EverMemOS, a self-organizing memory operating system that implements an engram-inspired lifecycle for computational memory. Episodic Trace Formation converts dialogue streams into MemCells that capture episodic traces, atomic facts, and time-bounded Foresight signals. Semantic Consolidation organizes MemCells into thematic MemScenes, distilling stable semantic structures and updating user profiles. Reconstructive Recollection performs MemScene-guided agentic retrieval to compose the necessary and sufficient context for downstream reasoning. Experiments on LoCoMo and LongMemEval show that EverMemOS achieves state-of-the-art performance on memory-augmented reasoning tasks. We further report a profile study on PersonaMem v2 and qualitative case studies illustrating chat-oriented capabilities such as user profiling and Foresight. Code is available at https://github.com/EverMind-AI/EverMemOS.
Original Article
View Cached Full Text

Cached at: 05/08/26, 09:03 AM

Paper page - EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning

Source: https://huggingface.co/papers/2601.02163 Authors:

,

,

,

,

,

,

,

,

,

Abstract

EverMemOS presents a self-organizing memory system for large language models that processes dialogue streams into structured memory cells and scenes to enhance long-term interaction capabilities.

Large Language Models(LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions. Existingmemory systemsoften store isolated records and retrieve fragments, limiting their ability to consolidate evolving user states and resolve conflicts. We introduce EverMemOS, a self-organizing memory operating system that implements an engram-inspired lifecycle for computational memory.Episodic Trace Formationconverts dialogue streams intoMemCellsthat capture episodic traces, atomic facts, and time-boundedForesightsignals.Semantic ConsolidationorganizesMemCellsinto thematicMemScenes, distilling stable semantic structures and updating user profiles.Reconstructive Recollectionperforms MemScene-guidedagentic retrievalto compose the necessary and sufficient context for downstream reasoning. Experiments on LoCoMo and LongMemEval show that EverMemOS achieves state-of-the-art performance onmemory-augmented reasoningtasks. We further report a profile study on PersonaMem v2 and qualitative case studies illustrating chat-oriented capabilities such asuser profilingandForesight. Code is available at https://github.com/EverMind-AI/EverMemOS.

View arXiv pageView PDFGitHub4.47kautoAdd to collection

Get this paper in your agent:

hf papers read 2601\.02163

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/2601.02163 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2601.02163 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2601.02163 in a Space README.md to link it from this page.

Collections including this paper2

Similar Articles

MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents

arXiv cs.AI

The article introduces MindMemOS, a portable and self-evolving memory operating layer for AI agents that uses a unified entity-property-time structure, with algorithms for memory refinement and skill evolution. It achieves notable accuracy on LOCOMO and PersonaMem benchmarks and improves SpreadsheetBench performance by 9.2 percentage points.

AdMem: Advanced Memory for Task-solving Agents

arXiv cs.AI

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.

StageMem: Lifecycle-Managed Memory for Language Models

arXiv cs.CL

StageMem proposes a lifecycle-managed memory framework for language models that organizes memory into transient, working, and durable stages with explicit confidence and strength metrics, treating memory as a stateful process rather than a static store to better manage retention and forgetting under bounded capacity.