腾讯混元团队整理了549篇论文，给自进化智能体分了L0-L4五个等级，还提出一套验证更新靠不靠谱的方法，做Agent研究的朋友可以看看。
腾讯混元团队发布《Diving into Reliable Self-Evolving Agents: A Survey》综述，系统梳理智能体自我进化机制。该综述定义了L0到L4的五级自进化分类法，并引入可靠性阶梯用于评估每次更新的可信度。研究团队整理了549篇相关论文，建立开放配套目录。核心原则是任何更新都不能仅用自身产生的证据来验证，确保进化过程可审计。
📄New Research on Self-Evolving Agents: When AI agents modify themselves, how do we know they actual...
📄New Research on Self-Evolving Agents: When AI agents modify themselves, how do we know they actually got better? We present Diving into Reliable Self-Evolving Agents: A Survey—a systematic map of how agents self-evolve and what evidence is needed to trust each update. The survey: 🔹 Defines an L0–L4 taxonomy for self-evolving agents 🔹 Introduces a reliability ladder for trustworthy updates 🔹 Curates 549 works in an open companion catalog One core principle: no update should control the only evidence used to accept itself. Explore the full survey ↓ 📄 Pap openreview.net/forum?id=CGO1h… dF2FP 🌐 Pro wkqdzkd.github.io/Awesome-Reliab… 9EIPf0 💻 G github.com/wkqdzkd/Awesom… now4J9X 💬 0 🔄 4 ❤️ 15 👀 743 📊 5 ⚡