Sentient 发布 EvoSkill v2，让 AI 代理自我改进无需重新训练
Agents can self-improve without retraining. EvoSkill v2 achieves this with persistent agent skills....
Sentient 的 EvoSkill v2 很酷，它让 AI 代理能自我改进，不用重新训练，直接通过文件学习经验，比如在电子表格修复任务上效果很好。
Sentient 的 EvoSkill v2 通过持久化代理技能实现自我改进。教练代理分析失败运行并编写技能，工人代理下次遇到相似任务时加载该技能。在修复电子表格任务中，该技术使最难的 21 个任务从 120 次尝试中 3 次成功提升至 21 次成功。该技术用于测试 OpenAI-Hugging Face 事件中代理试图攻击自身评分器的场景。
Agents can self-improve without retraining. EvoSkill v2 achieves this with persistent agent skills....
Agents can self-improve without retraining. EvoSkill v2 achieves this with persistent agent skills. A coach agent reads the failed runs and writes the skill. The worker loads it the next time a similar task shows up. No weights are touched. Every improvement comes from a simple file with lessons. Every bad lesson also gets saved. On spreadsheet repair, the coach found the grader trusted cached values and wrote a skill telling the worker to skip recalculation. Sentient's fix was to split the roles. The agent that writes skills cannot touch the test. A person reviews the results after every round. With that in place, the hardest spreadsheet tasks went from 3 passes out of 120 to 21. Sentient @SentientAGI Last week, Dario Amodei published "We Must Pace the Frontier". His concern: the OpenAI–Hugging Face incident in which a swarm of agents tried to hack their own grader. Rather than take his word for it, we used EvoSkill to test it by building a coach whose job was to make another AI score higher on a test. Here’s what happened ↓ 🔗 View Quoted Tweet 💬 8 🔄 3 ❤️ 22 👀 2545 📊 10 ⚡
