copt-contrastive-on-policy-thinking-with-continuous-spaces-for-general-and-agentic-reasoning
wiki · · 1 min read
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
Definition
arXiv ID: 2605.20075
Sources
- raw/AI/hf-paper-260520075-CopT-Contrastive-On-Policy-Thinking-with.md