ActionOPD: Distilling Decisions, Not Tokens
🔗 https://huggingface.co/papers/2610.19820 ↗ActionOPD aligns smaller language-model agents with teachers via semantic action-level on-policy distillation, improving out-of-distribution tool-use performance without requiring shared tokenizers or teacher probabilities.
內容為收集當日抓取的摘要原文。