arXiv · cs.AI · Weiheng Wu, Junkai Chen, Zhensu Sun, Jieke Shi, Yunbo Lyu, David Lo · 9 小时前模型评分50
Caper:先沙箱试跑再审批的编码智能体命令放行机制
"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents
导读
论文提出 Caper,一种面向编码智能体的后果感知审批机制:先在快照沙箱中预执行每条命令,把观察到的效果整理成有界报告交给独立审批方,放行的命令提交、拦截的命令回滚并附上可供智能体处理的原因。
分类置信度
中 · 待人工复核
- 只有单一媒体来源,需要人工复核。
来源级别:媒体与个人
事件类型:研究发布
证据摘录
- “We present Caper, a consequence-aware approval mechanism that pre-executes each command in a snapshotted sandbox, provides an independent approver with a bounded report of its observed effects, commits allowed commands, and rolls back blocked ones with a reason the agent can act on.”
来源:arXiv · cs.AI · arxiv.org