{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization","html":"","width":"100%","height":180,"duration":1214,"description":"\n 🤗 Upvotes: 25 | cs.AI, cs.CL\n\n Authors:\n Xingyu Wu, Yuchen Yan, Shangke Lyu, Linjuan Wu, Yiwen Qiu, Yongliang Shen, Weiming Lu, Jian Shao, Jun Xiao, Yueting Zhuang\n\n Title:\n LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization\n\n Arxiv:\n http://arxiv.org/abs/2507.15758v1\n\n Abstract:\n Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy Optimization (LAPO), a novel framework that transforms reasoning length control from an external constraint into an intrinsic model capability. Unlike existing approaches that impose rigid limits or rely on post-hoc interventions, LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process. In the first stage, models learn natural reasoning patterns by discovering the statistical distribution of successful solution lengths. The second stage leverages these patterns as meta-cognitive guidance, embedding them directly within the model's reasoning context to ensure inference-time flexibility. Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9\\% while improving accuracy by 2.3\\%. Our analysis reveals that models trained with LAPO develop emergent abilities to allocate computational resources based on problem complexity, achieving efficient reasoning without sacrificing quality.\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}