Google这篇论文教你如何让AI智能体通过持久化知识库保持技能，小模型进化技能后能打败大模型。
Google研究人员提出了一种新的智能体技能进化方法，将执行轨迹、持久化知识库和可执行技能分离。该方法通过将经验整合到知识库中，使后续技能更新基于累积知识而非分散优化历史。实验表明，较小规模的模型通过进化技能可以显著超越更大规模但未进化技能的模型。此外，一个模型进化出的技能可以跨模型家族迁移，有时甚至优于模型自我进化的技能。
A great paper from Google on maintaining agent skills through persistent knowledge.
A great paper from Google on maintaining agent skills through persistent knowledge. DAIR.AI @dair_ai Banger paper from Google. If you maintain a skill library for your agents, you might want to check this out. (bookmark it) This work separates three things that skill-evolution systems usually collapse into one. Raw execution traces, a persistent wiki of accumulated knowledge, and the executable skills themselves. Experience gets consolidated into the wiki, and every later skill update builds on that wiki instead of on a scattered optimization history. Ablations confirm the wiki is what carries a lot of the gain. Two results stand out in particular. Smaller models with evolved skills beat substantially larger models without them. And skills evolved by one model transfer across families, where skills evolved elsewhere sometimes beat self-evolved ones. Paper: arxiv.org/abs/2608.27454 Chat with Paper: academy.dair.ai/papers/wikiski… 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 521 ⚡