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.
Figures & tables
Figure 1: Architecture and Decision Flow for Polaris
Metric
Average Score
Model
Semantic Similarity
0.85
GPT-4o
Context Precision
0.99
GPT-4o
Answer Relevancy
0.90
GPT-4o
Table 1: Average metric scores across 40 evaluation samples.
Metric
Threshold
Above (%)
Semantic Similarity
0.70
100.0
Context Precision
0.90
100.0
Answer Relevancy
0.70
92.5
Table 2: Threshold-based evaluation of metric quality.