返回全部动态

Amazon Bedrock 推出自动策略细化功能

原标题:Automated Reasoning policy refinement in Amazon Bedrock

AWS Machine Learning Blog一手来源产品发布质量 82

AI 摘要

AWS 宣布在 Amazon Bedrock 中推出自动策略细化功能,用于自动化 Automated Reasoning 策略的故障诊断与修复流程。该功能提供两种模式:迭代细化(Iterative Refinement)处理规则问题,以及模糊变量细化(Ambiguous Variable Refinement)处理语言歧义问题。用户需审批所有更改,从而减少手动编辑形式逻辑的工作量,提升策略开发效率。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

Automated Reasoning policy refinement in Amazon Bedrock Refining an Automated Reasoning policy in Amazon Bedrock has been a manual cycle of diagnose, hand-edit, retest, and repeat. Today, we are announcing automatic policy refinement, which automates the diagnose-and-fix work in that cycle. The refinement engine diagnoses failing tests and proposes formal-logic fixes. You approve every change before it takes effect. Automated Reasoning checks in Amazon Bedrock Guardrails use formal verification


发布时间:2026-08-04 00:30
抓取时间:2026-08-04 00:35
来源机构:AWS
阅读原文aws.amazon.com