EvoLib: Turning experience into evolving knowledge
Microsoft Research Weijia Xu, Alessandro Sordoni, Zelalem Gero, Michel Galley, Eric Yuan, Jianfeng Gao
Microsoft Research introduced EvoLib, a framework that enables large language models to extract reusable skills and insights from their own experiences during inference without model updates or external labels. The system consolidates and reweights knowledge over time, allowing it to convert test-time compute into performance improvements more effectively than existing memory-based approaches across mathematical reasoning, coding, and decision-making tasks. This enables AI systems to continually learn and improve after deployment by building evolving libraries of transferable knowledge rather than accumulating static memories.
Why it matters
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment. The post EvoLib: Turning experience into evolving knowledge appeared first on Microsoft Research.
