MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation 事件

MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation arXiv:2605.27186v1 Announce Type: new Abstract: Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap. We trace part of this degradation to self-contamination: intermediate assistant replies enter later context and carry early deviations forward. Motivated by this mechanism, we propo