{"slug": "mindmemos-a-portable-and-self-evolving-memory-operating-layer-for-ai-agents", "title": "MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents", "summary": "Researchers introduced MindMemOS, a portable and self-evolving memory operating layer for AI agents, which achieved 94.03% accuracy on LOCOMO and 70.63% on PersonaMem, and its MindSkillEvolve algorithm improved SpreadsheetBench success by 9.2 percentage points over the initial-skill baseline. The system organizes information using a unified entity property timestructure and supports adaptive memory modeling, autonomous refinement, and continuous skill evolution.", "body_md": "arXiv:2608.12428v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/mindmemos-a-portable-and-self-evolving-memory-operating-layer-for-ai-agents", "canonical_source": "https://arxiv.org/abs/2608.12428", "published_at": "2026-08-14 04:00:00+00:00", "updated_at": "2026-08-14 04:10:03.977087+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "machine-learning"], "entities": ["MindMemOS", "MindMemEvolve", "MindSkillEvolve", "LOCOMO", "PersonaMem", "SpreadsheetBench"], "alternates": {"html": "https://wpnews.pro/news/mindmemos-a-portable-and-self-evolving-memory-operating-layer-for-ai-agents", "markdown": "https://wpnews.pro/news/mindmemos-a-portable-and-self-evolving-memory-operating-layer-for-ai-agents.md", "text": "https://wpnews.pro/news/mindmemos-a-portable-and-self-evolving-memory-operating-layer-for-ai-agents.txt", "jsonld": "https://wpnews.pro/news/mindmemos-a-portable-and-self-evolving-memory-operating-layer-for-ai-agents.jsonld"}}