Memory Models: Towards Agents That Learn | Letta
Agents that truly learn from experience will be powered by memory models: models that create and curate token-space memory across model generations, trained with memory-native RL.
Memory is the key to unlocking AI agents that are not only teachable, but also capable of continually learning and self-improving. Techniques for continual learning in token space have seen widespread real-world adoption, with agentic memory management, agent dreaming, and skill learning becoming central features in agent harnesses such as Letta Code, Claude Code, DeepAgents, and OpenClaw. Token-space learning takes advantage of the in-context learning capabilities of modern LLMs, which continue to improve across model generations, and provides an incredibly data-efficient mechanism for…
saved by
related reading
- Continual Learning in Token Space | Lettaletta.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- The Continual Learning Problemjessylin.com
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- Supermemory — Memory and continual learning for agentssupermemory.ai
- Making Sense of Memory in AI Agents – Leonie Monigattileoniemonigatti.com
- How AI Agents Remember Thingsdamiangalarza.com
- Engramme – Remember Everythingengramme.com
- Agent memory as a file formatcalpaterson.com
- [2603.23516] MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokensarxiv.org
- Introducing Context Repositories: Git-based Memory for Coding Agents | Lettaletta.com
- Memory for agentsblog.langchain.dev