AI RESEARCH
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
arXiv CS.AI
•
ArXi:2606.03503v1 Announce Type: new Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoTs naturally contain trial and errors and mainstream RLVR approaches choose outcome-correct CoT trajectories for memorization, the redundant explorations in long CoTs are inevitably reinforced, which results in the over-thinking issues of LRMs.