这篇论文让AI智能体自己学会改进工具链，三步流程从找问题到验证，基于DeepAgents框架，适合做Agent开发的人看看。
新论文提出Self-Harness方法，让智能体自动改进其harness。流程分三步：1/弱点挖掘，从执行轨迹中发现失败模式；2/harness提案，基于发现生成修改方案；3/提案验证，通过回归测试筛选有效提案。该方法基于DeepAgents框架，论文见arxiv.org/pdf/2606.09498。实验在多个基准上显示性能持续提升。
🧠Self-Harness: Harnesses that improve themselves New paper on agents shaping their own harnesses t...
🧠Self-Harness: Harnesses that improve themselves New paper on agents shaping their own harnesses to improve over time. Not from LangChain, but builds on top of DeepAgents! Three key steps: 1/ Weakness mining: find failure modes from traces 2/ Harness proposal: suggest changes to the harness 3/ Proposal validation: does regression testing on proposals and then accepts Paper: arxiv.org/pdf/2606.09498 l Builds on top of DeepAgents: github.com/langchain-ai/d… y 💬 4 🔄 4 ❤️ 22 👀 1566 📊 8 ⚡