AI Agents Keep Going After They Should Stop. Here’s What the Incident Reports and Experiments Show.
中文摘要
研究表明，AI代理在应停止时仍持续执行任务，这种选择机制问题无法仅用能力提升来解释。
English Summary
AI agents continue tasks unnecessarily, highlighting a critical action-selection issue that capability improvements alone cannot resolve.
原文节选
Recent incidents and intervention experiments point to an action-selection problem that capability alone doesn’t explain Continue reading on Towards AI »