@inproceedings{zhang-etal-2025-evolvesearch,
    title = "{E}volve{S}earch: An Iterative Self-Evolving Search Agent",
    author = "Zhang, Ding-Chu  and
      Zhao, Yida  and
      Wu, Jialong  and
      Zhang, Liwen  and
      Li, Baixuan  and
      Yin, Wenbiao  and
      Jiang, Yong  and
      Li, Yu-Feng  and
      Tu, Kewei  and
      Xie, Pengjun  and
      Huang, Fei",
    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.663/",
    pages = "13134--13147",
    ISBN = "979-8-89176-332-6",
    abstract = "The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches for enabling LLM web search proficiency face significant challenges: supervised fine-tuning struggles with data production in open-search domains, while RL converges quickly, limiting their data utilization efficiency. To address these issues, we propose EvolveSearch, a novel iterative self-evolution framework that combines SFT and RL to enhance agentic web search capabilities without any external human-annotated reasoning data. Extensive experiments on seven multi-hop question-answering (MHQA) benchmarks demonstrate that EvolveSearch consistently improves performance across iterations, ultimately achieving an average improvement of 4.7{\%} over the current state-of-the-art across seven benchmarks, opening the door to self-evolution agentic capabilities in open web search domains."
}