@inproceedings{bi-etal-2026-cut,
    title = "Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning",
    author = "Bi, Jiaxi  and
      Luo, Tongxu  and
      Du, Wenyu  and
      Tang, Zhengyang  and
      Wang, Benyou",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.876/",
    pages = "19171--19189",
    ISBN = "979-8-89176-390-6",
    abstract = "Parallel reasoning enhances Large Reasoning Models (LRMs) but incurs prohibitive costs due to futile paths caused by early errors. To mitigate this, path pruning at the prefix level is essential, yet existing research remains fragmented without a standardized framework. In this work, we propose the first systematic taxonomy of path pruning, categorizing methods by their signal source (internal vs. external) and learnability (learnable vs. non-learnable). This classification reveals the unexplored potential of learnable internal methods, motivating our proposal of **STOP** (**S**uper **TO**ken for **P**runing). Extensive evaluations across LRMs ranging from 1.5B to 20B parameters demonstrate that STOP achieves superior effectiveness and efficiency compared to existing baselines. Furthermore, we rigorously validate the scalability of STOP under varying compute budgets{---}for instance, boosting GPT-OSS-20B accuracy on AIME25 from 84{\%} to nearly 90{\%} under fixed compute budgets. Finally, we distill our findings into formalized empirical guidelines to facilitate optimal real-world deployment. Code, data and models are available at https://bijiaxihh.github.io/STOP."
}