SkillPublic
post-training-strategy
为 Agent 模型做后训练或选路线时使用——判断该先补 Mid-training、用 SFT 立协议还是直接上 RL；构造 Mid-training 语料与 SFT 数据、搭建 RL 环境、在 GRPO/PPO/DPO 与蒸馏之间取舍；排查 pass@k 近零、格式不稳就训 RL、组内无奖励差异、训练-推理数值失配、过度训练泛化下降。触发词：后训练、Mid-training、继续预训练、SFT、RL、GRPO、PPO、DPO、拒绝采样、RFT、蒸馏、on-policy、RLVR、LoRA。
Quality
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Securityby
Passed
No findings from the security scan
No security issues found
Scanned
- Repository
bojieli/ai-agent-book
- Revision
dbc046e
- Audited
- Security analysis
Is this your skill?
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.