@inproceedings{yuan-etal-2026-shorten,
    title = "Shorten After You{'}re Right: Lazy Length Penalties for Reasoning {RL}",
    author = "Yuan, Danlong  and
      Xie, Tian  and
      Huang, Shaohan  and
      Zhang, Huishuai  and
      Gong, Zhuocheng  and
      Luo, Chong  and
      Wei, Furu  and
      Zhao, Dongyan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.626/",
    pages = "12864--12877",
    ISBN = "979-8-89176-395-1",
    abstract = "Long-reasoning models achieve strong accuracy on complex reasoning tasks, but their extended reasoning trajectories incur substantial memory and latency costs. Several existing shortening methods rely on additional supervision or multi-stage post-training, which primarily reduces inference length and does not reduce the rollout tokens during on-policy reinforcement learning (RL). We instead target on-policy response shortening, aiming to improve both inference efficiency and RL training throughput. However, because on-policy RL couples optimization with exploration, naively penalizing length can destabilize training and suppress exploration. To impose length pressure safely, we propose a lazy length penalty integrated into the rule-based RL pipeline: it activates only on correct trajectories, only after training accuracy enters a stably improving regime, and only when responses exceed a tolerance band beyond the minimal correct length. Across four settings, our method significantly reduces response length without extra training stages while maintaining or improving performance. In a logic reasoning setting, we achieve a 40{\%} reduction in step-averaged response length alongside a 14-point gain in performance. For math problems, we reduce step-averaged response length by 33{\%} while preserving performance."
}