@inproceedings{yang-etal-2026-harmonizing,
    title = "Harmonizing Dense and Sparse Signals in Multi-turn {RL}: Dual-Horizon Credit Assignment for Industrial Sales Agents",
    author = "Yang, Haojin  and
      Jian, Ai  and
      Wang, Yiwei  and
      Huang, Xinyue  and
      Zhang, Weipeng  and
      Zeng, Ke  and
      Cai, Xunliang  and
      Ruan, Jingqing",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.74/",
    pages = "1067--1076",
    ISBN = "979-8-89176-394-4",
    abstract = "Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluency and compliance. Conventional reinforcement learning often merges these heterogeneous goals into a single reward, causing high-magnitude session-level rewards to overwhelm subtler turn-level signals, which leads to unstable training or reward hacking.To address this issue, we propose **Dual-Horizon Credit Assignment (DuCA)**, a framework that disentangles optimization across time scales. Its core, **Horizon-Independent Advantage Normalization (HIAN)**, separately normalizes advantages from turn-level and session-level rewards before fusion, ensuring balanced gradient contributions from both immediate and long-term objectives to the policy update.Extensive experiments with a high-fidelity user simulator show DuCA outperforms the state-of-the-art GRPO baseline, achieving a 6.82{\%} relative improvement in conversion rate, reducing inter-sentence repetition by 82.28{\%}, and lowering identity detection rate by 27.35{\%}, indicating a substantial improvement for an industrial sales scenario that effectively balances the dual demands of strategic performance and naturalistic language generation."
}