让企业对话式分析更智能，自动拆解复杂查询并解释原因
Polaris : Multi Agentic System for Conversational Enterprise Analytics
- 用动态任务协调机制分配不同专业智能体完成查询、可视化和推理
- 在真实企业数据集上实现高语义准确率和答案相关性
- 适合需要快速理解业务数据背后原因的决策者和分析师
在快节奏环境中，快速获取、理解并行动于数据已成必要。然而多数企业仍面临数据丰富但洞察匮乏的问题，受限于查询、解读和解释大规模企业信息的复杂性。我们提出Polaris，一种由监督者引导的多智能体对话式企业分析框架。Polaris引入动态任务协调（DTC），基于决策理论的编排层，将智能体-任务分配建模为自适应二分匹配，实现实时协调、故障恢复与优化。结合‘先推理’的ReAct风格智能体，Polaris将自然语言查询转化为连贯的分析工作流，不仅检索与可视化数据，还能解释背后原因。在结构化企业数据集上的评估显示其具备高语义保真度与答案相关性，验证了多智能体编排在规模化可信端到端商业智能中的潜力。
原文摘要 · Abstract (English)
In today's fast-paced environment, the ability to swiftly access, understand, and act on data is no longer optional; it is essential. Yet most organizations remain data-rich but insight-poor, constrained by the complexity of querying, interpreting, and explaining enterprise-scale information. We present Polaris, a supervisor-led multi-agent framework for conversational enterprise analytics that bridges this gap. Polaris introduces Dynamic Task Coordination (DTC), a decision-theoretic orchestration layer that models agent-task assignment as adaptive bipartite matching, enabling real-time coordination, recovery, and optimization across specialized agents for querying, visualization, and reasoning. By coupling DTC with reason-first, ReAct-style agents, Polaris transforms natural-language queries into coherent analytical workflows that not only retrieve and visualize data but also explain the underlying "why." Evaluation on structured enterprise datasets demonstrates high semantic fidelity and answer relevancy, underscoring the potential of multi-agent orchestration to deliver trustworthy, end-to-end business intelligence at scale.
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。