@inproceedings{chao-etal-2025-llmxmapreduce,
    title = "{LLM}$\times${M}ap{R}educe-V3: Enabling Interactive In-Depth Survey Generation through a {MCP}-Driven Hierarchically Modular Agent System",
    author = "Chao, Yu  and
      Lin, Siyu  and
      Wang, Xiaorong  and
      Zhang, Zhu  and
      Zhou, Zihan  and
      Wang, Haoyu  and
      Wang, Shuo  and
      Zhou, Jie  and
      Liu, Zhiyuan  and
      Sun, Maosong",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-demos.51/",
    pages = "688--695",
    ISBN = "979-8-89176-334-0",
    abstract = "We introduce LLM$\times$MapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLM$\times$MapReduce-V2, this version incorporates a multi-agent architecture where individual functional components, such as skeleton initialization, digest construction, and skeleton refinement, are implemented as independent model-context-protocol (MCP) servers. These atomic servers can be aggregated into higher-level servers, creating a hierarchically structured system. A high-level planner agent dynamically orchestrates the workflow by selecting appropriate modules based on their MCP tool descriptions and the execution history. This modular decomposition facilitates human-in-the-loop intervention, affording users greater control and customization over the research process. Through a multi-turn interaction, the system precisely captures the intended research perspectives to generate a comprehensive skeleton, which is then developed into an in-depth survey. Human evaluations demonstrate that our system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning. Demo, video and code are available at \url{https://github.com/thunlp/LLMxMapReduce}."
}