@inproceedings{mo-etal-2026-agentic,
    title = "Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning",
    author = "Mo, Fengran  and
      Gao, Yifan  and
      Li, Sha  and
      Zeng, Hansi  and
      Liu, Xin  and
      Tan, Zhaoxuan  and
      Li, Xian  and
      Chen, Jianshu  and
      Wang, Dakuo  and
      Jiang, Meng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.443/",
    pages = "9125--9138",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) have become a popular interface for human{--}AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Existing studies usually follow static ``rewrite, retrieve, and generate'' pipelines, which optimize different procedures separately and overlook the mixed-initiative action optimization simultaneously. Although the recent developments in deep search agents demonstrate the effectiveness in jointly optimizing retrieval and generation via reasoning, these approaches focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods by surpassing several existing strong baselines."
}