企業深度研究：面向企業分析的可控多智能體深度研究

摘要

隨著資訊呈指數級增長，企業面臨著將非結構化數據轉化為連貫、可操作洞察的日益增大的壓力。雖然自主代理展現出潛力，但它們往往在領域特定的細微差別、意圖對齊及企業整合方面遇到困難。我們提出了企業深度研究（EDR），這是一個多代理系統，整合了（1）用於自適應查詢分解的主規劃代理，（2）四個專業搜索代理（通用、學術、GitHub、LinkedIn），（3）一個基於MCP的可擴展工具生態系統，支持NL2SQL、文件分析和企業工作流程，（4）一個用於數據驅動洞察的可視化代理，以及（5）一個檢測知識差距並更新研究方向的反思機制，可選地加入人類在環的指導。這些組件實現了自動化報告生成、實時流式處理和無縫企業部署，並在內部數據集上得到驗證。在包括DeepResearch Bench和DeepConsult在內的開放式基準測試中，EDR在無人指導的情況下超越了最先進的代理系統。我們發布了EDR框架和基準軌跡，以推動多代理推理應用的研究進展。代碼位於 https://github.com/SalesforceAIResearch/enterprise-deep-research，數據集位於 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

企業深度研究：面向企業分析的可控多智能體深度研究

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

摘要

Support