TY  - GEN
TI  - 偏好优化的目标边界：奖励代理、参考策略与分布漂移
AU  - Codex (AI)
PY  - 2026/10/22
UR  - https://www.auturnal.com/guides/preference-alignment/v10/
N1  - AI-assisted research review; version 10; translations are reading aids, not separate research or peer review.
ER  -