A Multi-Agent Framework for Human–AI Collaboration in Enterprise Knowledge Orchestration and Executive Strategic Decision Support
Main Article Content
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.
Article Details

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with International Journal for Applied Information Management agree to the following terms: Authors retain copyright and grant the International Journal for Applied Information Management right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgement of the work's authorship and initial publication in International Journal for Applied Information Management. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in International Journal for Applied Information Management. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).