@inproceedings{leng-etal-2025-decex,
    title = "{D}ec{E}x-{RAG}: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision",
    author = "Leng, Yongqi  and
      Lei, Yikun  and
      Liu, Xikai  and
      Zhong, Meizhi  and
      Xiong, Bojian  and
      Zhang, Yurong  and
      Gao, Yan  and
      Yiwu  and
      Hu, Yao  and
      Xiong, Deyi",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.99/",
    pages = "1412--1425",
    ISBN = "979-8-89176-333-3",
    abstract = "Agentic Retrieval-Augmented Generation (Agentic RAG) enhances the processing capability for complex tasks through dynamic retrieval and adaptive workflows. Recent advances (e.g., Search-R1) have shown that outcome-supervised reinforcement learning demonstrate strong performance. However, this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback.To address these challenges, we propose DecEx-RAG, which models RAG as a Markov Decision Process (MDP) incorporating decision-making and execution, while introducing an efficient pruning strategy to optimize data expansion. Through comprehensive process-level policy optimization, DecEx-RAG significantly enhances the autonomous task decomposition, dynamic retrieval, and high-quality answer generation capabilities of large language models (LLMs). Experiments show that DecEx-RAG achieves an average absolute performance improvement of 6.2{\%} across six datasets, significantly outperforming existing baselines. Moreover, the pruning strategy improves data construction efficiency by nearly $6 \times$, providing an efficient solution for process-supervised RAG training. The code is available at \url{https://github.com/sdsxdxl/DecEx-RAG}."
}