AWS 与汇丰提出 Double Ratchet：评分器随智能体自进化
AWS 与汇丰联合发布的论文提出 Double Ratchet 方法，通过让评分器与智能体技能同步进化，仅需 10 个标注样本即可达到接近真实标注的训练效果。该评分器由针对单一失败类型的规则化检查构建，版本选择依据与标注样本的一致性，在代码、SQL 和报告任务中保持了 88% 至 110% 的性能增益。
Rohan Paul· @rohanpaul_ai · X·2026-10-12 14:11· 51 分钟前AI 评分45
AI 导读
AWS 与汇丰的论文提出 Double Ratchet，让评分器与智能体技能同步进化，仅用 10 个标注样本即可训练出接近真实标注的效果。该评分器由针对单一失败类型的规则化小检查逐步构建，版本选择只依据与 10 个标注样本的一致性，而非提高智能体得分。
正文
Self-improving agents have always needed a human to write the grader.
A new AWS + HSBC paper removes that step: the grader evolves alongside the agent from 10 labeled examples and trains it about as well as ground truth.
Double Ratchet evolves the grader alongside the agent's skills, building it from small, mostly rule-based checks for 1 failure type each. A grader version is chosen for agreeing with 10 labeled examples, never for raising the agent's score.
It kept 88% to 110% of the gain that ground truth or a rubric gave the same skill loop, across code, SQL, and reports. With the safeguards removed, the grader passed 97% to 100% of outputs yet trained skills as well.
来源：Rohan Paul · x.com
来源：AIHot · aihot.news