精选理由
微软研究院新出的EvoLib，让LLM在部署后还能变聪明，不是死记硬背，而是积累可复用的技能和经验，挺有想法的。
微软研究院发布EvoLib框架，区别于传统方法仅靠增加记忆，它把模型过往经验提炼为可重用的技能和知识。该框架使LLM在部署后仍能持续学习并适应新任务。EvoLib构建的进化知识库帮助模型调用之前积累的洞见，提升泛化能力。
原文 · Microsoft Research
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, t...
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. msft.it/6019vh35f Your browser does not support the video tag. 🔗 View on Twitter 💬 1 🔄 3 ❤️ 7 👀 1090 📊 3 ⚡