Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Prabhakar, Akshara, Ram, Roshan, Chen, Zixiang, Savarese, Silvio, Wang, Frank, Xiong, Caiming, Wang, Huan, Yao, Weiran
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911254118924288
author Prabhakar, Akshara
Ram, Roshan
Chen, Zixiang
Savarese, Silvio
Wang, Frank
Xiong, Caiming
Wang, Huan
Yao, Weiran
author_facet Prabhakar, Akshara
Ram, Roshan
Chen, Zixiang
Savarese, Silvio
Wang, Frank
Xiong, Caiming
Wang, Huan
Yao, Weiran
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2510_17797
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
Prabhakar, Akshara
Ram, Roshan
Chen, Zixiang
Savarese, Silvio
Wang, Frank
Xiong, Caiming
Wang, Huan
Yao, Weiran
Computation and Language
Artificial Intelligence
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
title Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.17797