TTPO: Test-Time Policy Optimization

  • 类型:arxiv
  • 标识:2608.27448
  • 链接:https://arxiv.org/abs/2608.27448
  • 主分类:engineering
  • 形态:method
  • TLDR:Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token. We observe that this failure mode is asymmetric: rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is corre
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-08-28-agent-rag-longcontext-candidates.json