Journal article · 2026 · Open access

Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning

Konstantinos I. Roumeliotis, Ranjan Sapkota, Manoj Karkee, Nikolaos D. Tselikas

IEEE Access, 14, 26965–26982 · Published 1 January 2026 · DOI 10.1109/access.2026.3662282

Open full textCite this paper

In brief

“Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning” is a 2026 journal article by Konstantinos I. Roumeliotis and 3 co-authors, published in IEEE Access. OpenAlex counts 21 citations as of 17 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at IEEE Access.

Citations
21
Most cited in
2026 (20)
Field-weighted impact
26.39
References
52
Authors
4

Abstract

Modern Artificial Intelligence (AI) increasingly relies on multi-agent architectures that blend visual and language understanding. Yet, a pressing challenge remains: How can we trust these agents especially in zero-shot settings with no fine-tuning? We introduce a novel modular Agentic AI visual classification framework that integrates generalist multimodal agents with a non-visual reasoning orchestrator and a Retrieval-Augmented Generation (RAG) module. Applied to apple leaf disease diagnosis, we benchmark three configurations: (I) zero-shot with confidence-based orchestration, (II) fine-tuned agents with improved performance, and (III) trust-calibrated orchestration enhanced by CLIP-based image retrieval and re-evaluation loops. Using confidence calibration metrics (ECE, OCR, CCC), the orchestrator modulates trust across agents. Our results demonstrate a 77.94\% accuracy improvement in the zero-shot setting using trust-aware orchestration and RAG, achieving 85.63\% overall. GPT-4o showed better calibration, while Qwen-2.5-VL displayed overconfidence. Furthermore, image-RAG grounded predictions with visually similar cases, enabling correction of agent overconfidence via iterative re-evaluation. The proposed system separates perception (vision agents) from meta-reasoning (orchestrator), enabling scalable and interpretable multi-agent AI. This blueprint illustrates how Agentic AI can deliver trustworthy, modular, and transparent reasoning, and is extensible to diagnostics, biology, and other trust-critical domains. In doing so, we highlight Agentic AI not just as an architecture but as a paradigm for building reliable multi-agent intelligence. agentic ai, orchestrator agent trust, trust orchestration, visual classification, retrieval augmented reasoning

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Roumeliotis, K. I., Sapkota, R., Karkee, M., & Tselikas, N. D. (2026). Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning. IEEE Access, 14, 26965–26982. https://doi.org/10.1109/access.2026.3662282

MLA 9

Roumeliotis, Konstantinos I., et al. “Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning.” IEEE Access, vol. 14, 2026, pp. 26965–26982. https://doi.org/10.1109/access.2026.3662282.

Chicago

Roumeliotis, Konstantinos I., Ranjan Sapkota, Manoj Karkee, and Nikolaos D. Tselikas. 2026. “Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning.” IEEE Access 14: 26965–26982. https://doi.org/10.1109/access.2026.3662282.

Harvard

Roumeliotis, K. I. et al. (2026) ‘Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning’, IEEE Access, 14, pp. 26965–26982. doi:10.1109/access.2026.3662282.

IEEE

K. I. Roumeliotis, R. Sapkota, M. Karkee, and N. D. Tselikas, “Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning,” IEEE Access, vol. 14, pp. 26965–26982, 2026, doi: 10.1109/access.2026.3662282.

BibTeX

@article{roumeliotis2026agentic,
  title     = {{Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning}},
  author    = {Roumeliotis, Konstantinos I. and Sapkota, Ranjan and Karkee, Manoj and Tselikas, Nikolaos D.},
  journal   = {IEEE Access},
  year      = {2026},
  volume    = {14},
  pages     = {26965--26982},
  doi       = {10.1109/access.2026.3662282},
  url       = {https://doi.org/10.1109/access.2026.3662282}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications

  • agentic AI
  • multi-agent systems
  • retrieval-augmented generation
  • confidence calibration
  • overconfidence
  • meta-reasoning
  • GPT-4o

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Roumeliotis, K. I., Sapkota, R., Karkee, M., & Tselikas, N. D. (2026). Agentic AI With Orchestrator-Agent Trust: A Modular Visual Classification Framework With Trust-Aware Orchestration and RAG-Based Reasoning. IEEE Access, 14, 26965–26982. https://doi.org/10.1109/access.2026.3662282

How many times has this paper been cited?

21 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Access: sign in and open the full text from this page.

Who wrote this paper?

Konstantinos I. Roumeliotis, Ranjan Sapkota, Manoj Karkee, Nikolaos D. Tselikas.

What is the DOI of this paper?

10.1109/access.2026.3662282, permanently at https://doi.org/10.1109/access.2026.3662282. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.