A Multi-Agent Intelligence Framework for Enterprise Knowledge Orchestration and Executive Decision Support
Year: 2026
Type: article
Abstract: Enterprise decision-making increasingly requires systems that can retrieve, validate, reason over, and synthesize fragmented organizational knowledge into actionable executive insight. This study proposes a multi-agent intelligence framework for enterprise knowledge orchestration and executive decision support by integrating semantic knowledge acquisition, retrieval-augmented evidence access, specialized agent reasoning, validation control, evidence fusion, and recommendation scoring. The framework was evaluated across six enterprise decision domains: financial planning, operational risk, compliance monitoring, human resource allocation, supply chain disruption, and market expansion. The results show that retrieval precision ranged from 0.86 to 0.91, recall ranged from 0.81 to 0.87, evidence coverage ranged from 0.79 to 0.89, and source traceability ranged from 0.89 to 0.95. Validation improved reasoning consistency from an initial range of 0.69-0.78 to 0.84-0.91 after validation. Recommendation quality also showed strong performance, with evidence support reaching 0.92, strategic alignment 0.91, executive readability 0.89, action relevance 0.88, implementation clarity 0.86, and confidence calibration 0.84. Compared with retrieval-only question answering, single-agent reasoning, and non-validated multi-agent configurations, the proposed framework achieved the strongest results across retrieval, reasoning, recommendation relevance, traceability, and usability. Executive assessment further showed high practical value, with evidence traceability rated 4.58, trust support 4.51, decision usefulness 4.47, output clarity 4.42, review efficiency 4.36, and implementation readiness 4.18 on a five-point scale. These findings indicate that orchestrated multi-agent intelligence can strengthen enterprise decision support when agent specialization, evidence validation, and traceable recommendation generation are integrated into a unified decision-intelligence pipeline.
Author: Hussain Ahmad Awad
Institution: Amman Arab University
Language: English
Subfield: Information Systems and Management
Field: Decision Sciences
Domain: Social Sciences
Keywords: multi-agent systems, business decision support, semantic knowledge acquisition, retrieval-augmented generation, evidence verification, evidence combination, recommendation generation, source traceability, agent specialization, organizational knowledge, financial planning, operational risk, compliance monitoring, human resource allocation, supply chain disruption, market expansion
Open Access status: diamond
OpenAlex ID: W7235499160
