Lifelong Context Adaptation through Bidirectional Memory-Skill Learning

The paper introduces MemCryst, a framework that enables lifelong learning for large language model agents by jointly adapting memory and skills while keeping the language model frozen. MemCryst stores recurring episodes in memory to support skill creation and revision, and uses the resulting skills to guide future interactions, which in turn generate new memory. Experiments across ten diverse settings—including embodied control, long-document reading, conversation, mathematics, and code—show that MemCryst outperforms memory-only and skill-only baselines, achieving 63.17% success on ALFWorld.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• robotics