Skip to content
Preprint

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

Aug 2026 · 0 citations · 37 references
Computer Science Mathematics

TL;DR

MindMemOS is presented, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure that supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution.

Abstract

Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems often remain fixed after development, limiting their ability to adapt their memory models, organization strategies, and procedural knowledge through continued use. We present MindMemOS, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure. MindMemOS supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution. Its MindMemEvolve algorithm employs validation-driven evolutionary search to optimize memory schemas for target scenarios, whiledreaming consolidates accumulated memories by merging redundant records and resolving conflicts. In addition, implicit corrective feedback serves as a human-in-the-loop signal for identifying and revising potentially inaccurate or misaligned memories. Its MindSkillEvolve algorithm further transforms agent execution trajectories into reusable and progressively refined skills. MindMemOS achieves 94.03% accuracy on LOCOMO and 70.63% on PersonaMem. MindSkillEvolve improves SpreadsheetBench success by 9.2 percentage points over the initial-skill baseline.

View source

Similar papers

Just-In-Time Agent Memory with Runtime Agentic Research

Just-In-Time Agent Memory (JAM), a trainable framework for query-conditioned context construction at runtime, is proposed, where it achieves stronger task performance than AOT-style memory systems while remaining substantially more efficient than prior trained agentic memory approaches.

Bing-Yu Yan, Chao-Fan Li, Hong-Jin Qian et al. · 1 citation
#artificial intelligence Preprint Oct 2026

Capability-Driven Self-Evolution of Agent Memory

This work proposes PrisMem, which uses dependency-aware capability selection to prioritize targets with potential cross-capability benefits and history-guided diagnosis to refine capability specialists, and introduces capability-driven evolution, which extends search guidance from overall performance to individual capa...

Yao-Qi Chen, Yu-Ru Feng, Qianxi Zhang et al. · 1 citation

GenMem: Generative Symbolic Memory for Self-Evolving Harness

GenMem is presented, which reformulates memory management as generative symbolic addressing, a multi-level discrete token tuple drawn from a Cartesian-product address space that factorizes a million-scale sparse memory space using fewer than one hundred discrete symbols.

Xin-Ke Jiang, Tao Feng, Wei-Xuan Xu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents

The proposed REALM framework models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback.

Yuan-Yi Song, Yukai Wang, Xin-Bei Ma et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.