HIKMA: Human-Inspired Knowledge by Machine Agents through a Multi-Agent Framework for Semi-Autonomous Scientific Conferences

TL;DR

HIKMA introduces a comprehensive multi-agent framework that integrates AI into every stage of scholarly communication, demonstrating how AI can support traditional academic practices while addressing ethical and operational challenges.

Contribution

This paper presents the first end-to-end AI-integrated conference framework, combining language models with research workflows to enhance scholarly communication.

Findings

AI supports manuscript creation, peer review, and dissemination.

The framework maintains transparency and intellectual property protection.

Insights into AI's role and challenges in academic settings.

Abstract

HIKMA Semi-Autonomous Conference is the first experiment in reimagining scholarly communication through an end-to-end integration of artificial intelligence into the academic publishing and presentation pipeline. This paper presents the design, implementation, and evaluation of the HIKMA framework, which includes AI dataset curation, AI-based manuscript generation, AI-assisted peer review, AI-driven revision, AI conference presentation, and AI archival dissemination. By combining language models, structured research workflows, and domain safeguards, HIKMA shows how AI can support - not replace traditional scholarly practices while maintaining intellectual property protection, transparency, and integrity. The conference functions as a testbed and proof of concept, providing insights into the opportunities and challenges of AI-enabled scholarship. It also examines questions about AI authorship, accountability, and the role of human-AI collaboration in research.