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
- Supermemory — Memory and continual learning for agentssupermemory.ai
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- Machine Studying | Jacob Xiaochen Lijacobxli.com
- The Era of Experience Paper.pdfstorage.googleapis.com
- NL.pdfabehrouz.github.io
- The Continual Learning Problemjessylin.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- Announcing our investment in Engram, the memory dream team — Amplify Partnersamplifypartners.com
- Making Sense of Memory in AI Agents – Leonie Monigattileoniemonigatti.com
- Introducing Context Repositories: Git-based Memory for Coding Agents | Lettaletta.com
- The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com