@inproceedings{nan-etal-2026-rhombus,
    title = "Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning",
    author = "Nan, Ziyuan  and
      Yi, Qi  and
      Huang, Di  and
      Wu, Yutong  and
      Huang, Guanhua  and
      Gong, Xue  and
      Li, Kejiao  and
      Jiang, Yuhao  and
      Zhang, Chenchen  and
      Xu, Zenan  and
      Hu, Xing  and
      Zhou, Bo",
    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.1956/",
    pages = "39258--39270",
    ISBN = "979-8-89176-395-1",
    abstract = "Parallel thinking offers a promising avenue for scaling test-time compute in Large Language Models (LLMs), enabling them to explore diverse solution paths simultaneously before aggregating them into a final answer. However, coordinating the exploration and aggregation stages remains challenging, as simple aggregation techniques often incur information loss, failing to preserve the subtle, decision-relevant signals generated during exploration. To overcome this, we propose Rhombus, a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning. Rhombus employs multiple parallel Proposers to generate compact, decision-focused reasoning cues and a central Synthesizer to integrate them into final predictions, utilizing co-training under a shared task reward to align their interaction. Across challenging mathematical reasoning benchmarks, Rhombus improves accuracy by 6.0{\%} over long chain-of-thought baselines while reducing wall-clock latency by 39.4{\%} under matched token budgets. Our work demonstrates that explicit communication optimization is essential for realizing the accuracy and efficiency gains of parallel reasoning."
}