Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zain Ul Abideen Tariq, Mahmood Al-Zubaidi, Uzair Shah, Marco Agus, Mowafa Househ

TL;DR

HIKMA introduces a fully integrated, human-supervised semi-autonomous scholarly conference pipeline that couples dataset intake, AI-generated manuscripts, AI-driven peer review, iterative revisions, camera-ready preparation, slide and avatar-based presentations, and open archival release. A comprehensive audit trail records provenance, model versions, and artifact lineage to ensure transparency and reproducibility, while IP protection and explicit labeling mitigate ethical risks. Evaluation shows 60 AI-generated drafts, 120 AI reviews, 30 camera-ready manuscripts, 30 presentation decks, and 30 avatar videos across tracked domains, demonstrating end-to-end feasibility and the potential for auditable AI-assisted scholarship. The work provides governance guidelines and a roadmap for integrating AI into research workflows responsibly, with attention to governance, reproducibility, inclusivity, and human–AI collaboration.

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.

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

TL;DR

HIKMA introduces a fully integrated, human-supervised semi-autonomous scholarly conference pipeline that couples dataset intake, AI-generated manuscripts, AI-driven peer review, iterative revisions, camera-ready preparation, slide and avatar-based presentations, and open archival release. A comprehensive audit trail records provenance, model versions, and artifact lineage to ensure transparency and reproducibility, while IP protection and explicit labeling mitigate ethical risks. Evaluation shows 60 AI-generated drafts, 120 AI reviews, 30 camera-ready manuscripts, 30 presentation decks, and 30 avatar videos across tracked domains, demonstrating end-to-end feasibility and the potential for auditable AI-assisted scholarship. The work provides governance guidelines and a roadmap for integrating AI into research workflows responsibly, with attention to governance, reproducibility, inclusivity, and human–AI collaboration.

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.
Paper Structure (63 sections, 18 figures, 1 table)

This paper contains 63 sections, 18 figures, 1 table.

Table of Contents

  1. Introduction
  2. Scope and claims
  3. Related Works
  4. Conference and Workflow Automation
  5. Methodology
  6. Data and Asset Intake
  7. Manuscript Generation
  8. AI Peer Review
  9. Revision Loop
  10. Revised Manuscript Generation
  11. Response Letter Generation
  12. Camera-Ready Manuscripts
  13. Slide and Script Synthesis
  14. Avatar Presentation
  15. Archival and Release
  16. ...and 48 more sections

Figures (18)

  • Figure 1: HIKMA process pipeline from data intake to avatar presentations.
  • Figure 2: Manuscript Generation through AI Scholar Frontier.
  • Figure 3: Administrator view of manuscript generation proces through AI Scholar Frontier.
  • Figure 4: HIKMA Conference experimental website.
  • Figure 5: List of submissions with final status and details of authors and institutions
  • ...and 13 more figures