LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chao, Yu, Lin, Siyu, wang, xiaorong, Zhang, Zhu, Zhou, Zihan, Wang, Haoyu, Wang, Shuo, Zhou, Jie, Liu, Zhiyuan, Sun, Maosong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912856820154368
author Chao, Yu
Lin, Siyu
wang, xiaorong
Zhang, Zhu
Zhou, Zihan
Wang, Haoyu
Wang, Shuo
Zhou, Jie
Liu, Zhiyuan
Sun, Maosong
author_facet Chao, Yu
Lin, Siyu
wang, xiaorong
Zhang, Zhu
Zhou, Zihan
Wang, Haoyu
Wang, Shuo
Zhou, Jie
Liu, Zhiyuan
Sun, Maosong
contents We introduce LLM x MapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLM x 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10890
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System
Chao, Yu
Lin, Siyu
wang, xiaorong
Zhang, Zhu
Zhou, Zihan
Wang, Haoyu
Wang, Shuo
Zhou, Jie
Liu, Zhiyuan
Sun, Maosong
Computation and Language
We introduce LLM x MapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLM x 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.
title LLM$\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System
topic Computation and Language
url https://arxiv.org/abs/2510.10890