把生产 bad case / 失败轨迹转成训练数据时使用——从失败归因、轨迹前缀截取、DPO 偏好对构造、LoRA 训练到边界集与保留集双集验证的完整链路;也用于判断某类问题该走 SFT、DPO、RL 还是先修 Harness/工具/tokenizer,以及如何从运行轨迹中提取带证据的结构化学习信号。触发词:bad case、失败归因、DPO、偏好对、轨迹前缀、拒绝采样、过度矫正、边界集、保留集、过早结束、reward hacking、LoRA 微调、训练评估隔离。
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Scanned
bojieli/ai-agent-book
dbc046e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.