← Long-Term Memory Systems for AI Agents
Page History
Every revision of this knowledge page since it was created on October 15, 2026. Each entry shows what kind of change was made, how the page grew or shrank, and the source articles that drove it — so the paper's memory is inspectable, not taken on faith.
Page createdOctober 15, 2026 (+1,925 chars)
- Recall What Is Missing: Composing Evidence from Long-Term Agent Memory
- When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization
- Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate
- History Replays Itself: Unleashing Long-Context Capability in Linear Attention