作者位次 #6/11ACL 2026Poster· Natural Language Processing
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
Siyuan Gan · JIAHENG LIU · Boyan Wang · Tianpei Yang · Runqing Miao · Yuyao Zhang · Fanyu Meng · Junlan Feng · Linjian Meng · Jing Huo · Yang Gao
摘要
Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. To address this overthinking problem, existing work focuses...