企业深度研究：面向企业分析的可控多智能体深度研究

摘要

随着信息呈指数级增长，企业面临着将非结构化数据转化为连贯、可操作洞察的日益增长的压力。尽管自主代理展现出潜力，但它们往往难以应对领域特定的细微差别、意图对齐以及企业集成。我们提出了企业深度研究（EDR），这是一个多代理系统，集成了（1）用于自适应查询分解的主规划代理，（2）四个专业搜索代理（通用、学术、GitHub、LinkedIn），（3）一个基于MCP的可扩展工具生态系统，支持NL2SQL、文件分析及企业工作流，（4）一个用于数据驱动洞察的可视化代理，以及（5）一个检测知识缺口并更新研究方向的反思机制，该机制可选地结合人类在环的指导。这些组件实现了自动化报告生成、实时流处理和无缝企业部署，已在内部数据集上得到验证。在包括DeepResearch Bench和DeepConsult在内的开放式基准测试中，EDR在无需任何人工干预的情况下超越了最先进的代理系统。我们发布了EDR框架及基准轨迹，以推动多代理推理应用的研究。代码位于 https://github.com/SalesforceAIResearch/enterprise-deep-research，数据集位于 https://huggingface.co/datasets/Salesforce/EDR-200。

English

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

企业深度研究：面向企业分析的可控多智能体深度研究

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

摘要

Support