Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
Abstract
As information grows exponentially, enterprises face increasing pressure to transform unstructured data into coherent, actionable insights. While autonomous agents show promise, they often struggle with domain-specific nuances, intent alignment, and enterprise integration. We present Enterprise Deep Research (EDR), a multi-agent system that integrates (1) a Master Planning Agent for adaptive query decomposition, (2) four specialized search agents (General, Academic, GitHub, LinkedIn), (3) an extensible MCP-based tool ecosystem supporting NL2SQL, file analysis, and enterprise workflows, (4) a Visualization Agent for data-driven insights, and (5) a reflection mechanism that detects knowledge gaps and updates research direction with optional human-in-the-loop steering guidance. These components enable automated report generation, real-time streaming, and seamless enterprise deployment, as validated on internal datasets. On open-ended benchmarks including DeepResearch Bench and DeepConsult, EDR outperforms state-of-the-art agentic systems without any human steering. We release the EDR framework and benchmark trajectories to advance research on multi-agent reasoning applications. Code at https://github.com/SalesforceAIResearch/enterprise-deep-research and Dataset at https://huggingface.co/datasets/Salesforce/EDR-200
Cite
@article{arxiv.2510.17797,
title = {Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics},
author = {Akshara Prabhakar and Roshan Ram and Zixiang Chen and Silvio Savarese and Frank Wang and Caiming Xiong and Huan Wang and Weiran Yao},
journal= {arXiv preprint arXiv:2510.17797},
year = {2025}
}
Comments
Technical report; 13 pages plus references and appendices