@inproceedings{wu-etal-2025-search,
    title = "Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty",
    author = "Wu, Peilin  and
      Zhang, Mian  and
      Zhang, Xinlu  and
      Du, Xinya  and
      Chen, Zhiyu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.998/",
    pages = "19734--19745",
    ISBN = "979-8-89176-332-6",
    abstract = "Agentic Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by enabling dynamic, multi-step reasoning and information retrieval. However, these systems often exhibit sub-optimal search behaviors like over-search (retrieving redundant information) and under-search (failing to retrieve necessary information), which hinder efficiency and reliability. This work formally defines and quantifies these behaviors, revealing their prevalence across multiple QA datasets and agentic RAG systems (e.g., one model could have avoided searching in 27.7{\%} of its search steps). Furthermore, we demonstrate a crucial link between these inefficiencies and the models' uncertainty regarding their own knowledge boundaries, where response accuracy correlates with model{'}s uncertainty in its search decisions. To address this, we propose {\ensuremath{\beta}}-GRPO, a reinforcement learning-based training method that incorporates confidence threshold to reward high-certainty search decisions. Experiments on seven QA benchmarks show that {\ensuremath{\beta}}-GRPO enable a 3B model with better agentic RAG ability, outperforming other strong baselines with a 4{\%} higher average exact match score."
}