AI RESEARCH
STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning
arXiv CS.CL
•
ArXi:2506.18831v2 Announce Type: replace Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and redundant reasoning steps that increase computational costs while potentially degrading performance. While recent work has explored static steering approaches to mitigate this issue, they lack the adaptability to dynamically adjust intervention strength based on real-time reasoning quality. We propose STUPID (Steering Token Usage via PID controller), a novel.