Research Article

Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust

Number: 10 July 14, 2026

Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust

Abstract

This study addresses the growing challenge of explainability in Agentic Artificial Intelligence (Agentic AI), where autonomous systems operate through sequential, goal-driven decision processes rather than isolated predictions. The primary objective of this study is to develop and experimentally evaluate a behavior-centric explainability framework, termed Explainable Action Chains (XAC), for improving transparency and trust in Agentic AI systems. Existing Explainable AI (XAI) approaches are predominantly model-centric and fail to adequately capture the temporal and behavioral complexity of agentic systems. To bridge this gap, we propose Explainable Action Chains (XAC), a behavior-centric framework that represents agent decisions as temporally ordered units linking goals, states, actions, rationales, and outcomes. The framework is integrated into a modular Agentic AI architecture following the Goal–Plan–Act–Reflect cycle, enabling explanation generation as an inherent part of the decision process rather than a post-hoc addition. A prototype implementation is developed and evaluated through a comparative study between a baseline agent and an XAC-enabled agent under identical conditions. Experimental results demonstrate that XAC significantly increases perceived transparency and user trust without significantly affecting task success, while introducing only a modest increase in decision time. These findings validate the feasibility of behavior-level explainability for autonomous AI systems. The proposed framework contributes to the design of more transparent, accountable, and trustworthy Agentic AI systems, and provides a foundation for future research in explainable autonomous decision-making.

Keywords

Ethical Statement

This study adhered to rigorous academic research ethics and international standards for human-computer interaction experiments. Throughout the controlled comparative evaluation involving 50 human participants, strict protocols were maintained regarding informed consent, voluntary participation, and the complete anonymization of user data. The privacy, digital footprints, and psychological well-being of all participants were fully protected during the evaluation of transparency, trust, and cognitive load metrics, ensuring full compliance with institutional and general ethical principles in technological research.

Thanks

The authors sincerely express their gratitude to the Editor-in-Chief and the anonymous reviewers of the Journal of AI for their valuable comments and professional suggestions. Their insightful feedback greatly contributed to improving the research framework, data analysis, and overall academic quality of this manuscript.

References

  1. Abou Ali, M., Dornaika, F., & Charafeddine, J. (2026). Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions. Artificial Intelligence Review, 59(11). Retrieved from https://doi.org/10.1007/s10462-025-11422-4
  2. Ali, İ., Selim, A., & Skender, F. (2026). Leveraging OCR and AI Tools: A Comparative Guide to Enhancing Data Processing and Decision-Making Efficiency in the Digital Age. Turkish Journal of Engineering, 10(1), 129-142.
  3. Chan, A., Ezell, C., Kaufmann, M., Wei, K., Hammond, L., Bradley, H., . . . Anderljung, M. (2024). Visibility into AI Agents. Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT '24), (pp. 958-973). Rio de Janeiro, Brazil. Retrieved from https://doi.org/10.1145/3630106.3658948
  4. Chen, X., Wang, S., Qian, C., Wang, H., Han, P., & Ji, H. (2025). DecisionFlow: Advancing Large Language Model as Principled Decision Maker. arXiv. Retrieved from https://doi.org/10.48550/arXiv.2505.21397
  5. Dazeley, R., Vamplew, P., & Cruz, F. (2023). Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey. Neural Computing and Applications, 35, 16893-16916. Retrieved from https://doi.org/10.1007/s00521-023-08423-1
  6. Deshpande, R. S., & Ambatkar, P. V. (2023). Interpretable Deep Learning Models: Enhancing Transparency and Trustworthiness in Explainable AI. Ciência & Engenharia – Science & Engineering Journal, 11(1), 1352-1363. Retrieved from https://scispace.com/pdf/interpretable-deep-learning-models-enhancing-transparency-3dqmawdb.pdf
  7. NIST (2017). Framework for Cyber-Physical Systems: Volume 1, Overview, Version 1.0. Gaithersburg, MD, USA: National Institute of Standards and Technology (NIST). Retrieved from https://doi.org/10.6028/NIST.SP.1500-201
  8. Galeas, J., Bensch, S., Hellström, T., & Bandera, A. (2025). Personalized Causal Explanations of a Robot's Behavior. Frontiers in Robotics and AI, Art. no. 1637574. Retrieved from https://doi.org/10.3389/frobt.2025.1637574

Details

Primary Language

English

Subjects

Autonomous Agents and Multiagent Systems, Artificial Reality

Journal Section

Research Article

Publication Date

July 14, 2026

Submission Date

May 20, 2026

Acceptance Date

July 12, 2026

Published in Issue

Year 2026 Number: 10

APA
Selim, A., Ali, İ., & Cafer, C. (2026). Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust. Journal of AI, 10, 187-201. https://doi.org/10.61969/jai.1955038
AMA
1.Selim A, Ali İ, Cafer C. Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust. Journal of AI. 2026;(10):187-201. doi:10.61969/jai.1955038
Chicago
Selim, Aybeyan, İlker Ali, and Cansur Cafer. 2026. “Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust”. Journal of AI, nos. 10: 187-201. https://doi.org/10.61969/jai.1955038.
EndNote
Selim A, Ali İ, Cafer C (July 1, 2026) Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust. Journal of AI 10 187–201.
IEEE
[1]A. Selim, İ. Ali, and C. Cafer, “Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust”, Journal of AI, no. 10, pp. 187–201, July 2026, doi: 10.61969/jai.1955038.
ISNAD
Selim, Aybeyan - Ali, İlker - Cafer, Cansur. “Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust”. Journal of AI. 10 (July 1, 2026): 187-201. https://doi.org/10.61969/jai.1955038.
JAMA
1.Selim A, Ali İ, Cafer C. Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust. Journal of AI. 2026;:187–201.
MLA
Selim, Aybeyan, et al. “Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust”. Journal of AI, no. 10, July 2026, pp. 187-01, doi:10.61969/jai.1955038.
Vancouver
1.Aybeyan Selim, İlker Ali, Cansur Cafer. Explainable Action Chains in Agentic AI: Enhancing Transparency and Trust. Journal of AI. 2026 Jul. 1;(10):187-201. doi:10.61969/jai.1955038

Journal of AI
is indexed and abstracted by
WoS Research Commons, DOAJ, OpenAIRE, ERIHPLUS, Google Scholar, Harvard Hollis, Scilit, ROAD

Publisher
Izmir Academy Publishing
www.izmirakademi.org

Although the scope of our journal is related to artificial intelligence studies, the abbreviation "AI" in the name of the journal is derived from "Academy Izmir".