# LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System

arXiv: https://arxiv.org/abs/2510.10890 · HTML: https://mlsanity.com/paper/2510.10890/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 12 of 12)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [Factuality of Large Language Models: A Survey](https://mlsanity.com/paper/2402.02420/) (2024)
- [AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents](https://mlsanity.com/paper/2502.05957/) (2025)
- [AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes](https://mlsanity.com/paper/2506.14728/) (2025)
- [OpenResearcher: Unleashing AI for Accelerated Scientific Research](https://mlsanity.com/paper/2408.06941/) (2024)
- [InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System](https://mlsanity.com/paper/2504.08762/) (2025)

## Built on by (most cited first, 2 of 2)

- [SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation](https://mlsanity.com/paper/2602.11238/) (2026)
- [MVSS: A Unified Framework for Multi-View Structured Survey Generation](https://mlsanity.com/paper/2601.09504/) (2026)

## Abstract (arXiv)

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.