InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning 事件

InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning arXiv:2603.17310v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost. While existing reinforcement learning approaches address this by optimizing final response length, they neglect the quality of intermediate reasoning steps, leaving models vulnerable to reward hacking. We a