AI RESEARCH
Compiled Memory: Not More Information, but More Precise Instructions for Language Agents
arXiv CS.AI
•
ArXi:2603.15666v1 Announce Type: new Existing memory systems for language agents address memory management: how to retrieve and page information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it should change agent behavior. We present Atlas, a memory kernel that compiles accumulated task experience into an agent's instruction structure -- without fine-tuning, RAG, or human intervention. Memory is distillation, not storage; delivery is instruction rewriting, not context injection.