跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 11 天前AI 評分23

自主 AI 智能體的自生成更新如何以證據把關

Evidence-Governed Adoption of Self-Generated Updates in Autonomous AI Agents

AI 導讀

Evidence-Governed Evolution(EGE)框架提出,以獨立評估、可衡量的證據及防止能力退化的保障措施,決定 AI 智能體自行提出的改進能否成為永久更新。智能體可以自由提出修改,但只有通過證據檢驗的修改才會保留,適用範圍包括提示詞、記憶、工具及工作流程。

正文

What happens when an AI agent decides to improve itself? More importantly, how do we know whether those improvements are actually making it better?

As agents begin modifying their own prompts, memories, tools, and workflows, one question becomes increasingly important: Should every self-generated improvement be trusted?

This paper introduces Evidence-Governed Evolution (EGE), a framework for ensuring that an agent's proposed improvements earn the right to become permanent through independent evaluation, measurable evidence, and safeguards against capability degradation.

The central idea is simple: An AI agent should be free to propose changes, but evidence should decide which changes survive.

I'd be interested to hear your thoughts on how we should govern the next generation of self-evolving AI agents.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co