@inproceedings{ding-etal-2026-empowering,
    title = "Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization",
    author = "Ding, Yifeng  and
      Le, Hung  and
      Han, Songyang  and
      Ruan, Kangrui  and
      Jin, Zhenghui  and
      Kumar, Varun  and
      Wang, Zijian  and
      Deoras, Anoop",
    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.1962/",
    pages = "42409--42423",
    ISBN = "979-8-89176-390-6",
    abstract = "Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) {--} where models iteratively reason, generate code, and verify through execution {--} remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy Optimization (GRPO), suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. To address this issue, we propose Group Turn Policy Optimization (GTPO), a novel RL algorithm specifically designed for training LLMs on multi-turn TIR tasks. GTPO introduces three key innovations: (1) turn-level reward assignment that provides fine-grained feedback for individual turns, (2) return-based advantage estimation where normalized discounted returns are calculated as advantages, and (3) self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. Our comprehensive evaluation demonstrates that GTPO outperforms GRPO by 3.0{\%} across diverse math reasoning benchmarks, establishing its effectiveness. GTPO also improves GRPO by 3.9{\%} on commonsense reasoning and program synthesis tasks, demonstrating its generalizability to non-math domains. Importantly, GTPO incurs negligible overhead, ensuring its practicality for real-world scenarios."
}