企业级智能研究系统，自动拆解问题并多代理协作找答案。
Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics
- 用主控代理分解问题，四个专业搜索代理协同查资料
- 在开放基准上表现超顶尖系统，无需人工干预
- 适合需要自动分析报告的企业用户和研究者
随着信息爆炸式增长，企业面临将非结构化数据转化为可行动洞察的压力。现有自主代理常因领域特性、意图对齐及企业集成问题而受限。我们提出企业深度研究（Enterprise Deep Research, EDR），一个包含五部分的多代理系统：(1) 主控规划代理实现动态查询分解，(2) 四个专用搜索代理（通用、学术、GitHub、LinkedIn），(3) 基于MCP的可扩展工具生态，支持自然语言转SQL、文件分析与企业工作流，(4) 可视化代理生成数据驱动洞察，(5) 反思机制检测知识缺口并可选地通过人机协同引导研究方向调整。该系统支持自动化报告生成、实时流式处理与无缝企业部署，在内部数据集上验证有效。在DeepResearch Bench与DeepConsult等开放式基准测试中，EDR在无任何人工干预下超越现有顶尖代理系统。我们开源EDR框架与基准轨迹，以推动多代理推理应用研究。代码见https://github.com/SalesforceAIResearch/enterprise-deep-research，数据集见https://huggingface.co/datasets/Salesforce/EDR-200。
原文摘要 · Abstract (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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。