Abstract: Agentic artificial intelligence systems combine autonomous planning, memory, tool use, and multi-agent coordination, creating risks that extend beyond the behavior of an individual model to include interactions with external environments and operational workflows. Trustworthy deployment therefore requires assurance that integrates explainability, security, reliability, and governance across system layers and throughout the lifecycle. This paper proposes a unified framework that connects decision- and action-level explanations with threat modeling, bounded permissions, runtime verification, traceability, and reliability monitoring. It treats explanations as one component of assurance rather than a sufficient basis for trust, and situates them alongside calibrated human oversight and enforceable operational controls. The framework provides a structured basis for designing and evaluating agentic systems whose actions are interpretable, constrained, and auditable.

REFERENCES

[1]. U. Nisa, M. R. Shirazi, M. A. Saip, and M. S. M. Pozi, “Agentic AI: The age of reasoning—A review,” Journal of Automation and Intelligence, vol. 5, no. 1, pp. 69–89, Aug. 2025, doi: 10.1016/j.jai.2025.08.003.

[2]. I. Evtimov, A. Zharmagambetov, A. Grattafiori, C. Guo, and K. Chaudhuri, “WASP: Benchmarking web agent security against prompt injection attacks,” arXiv (Cornell University). Apr. 22, 2025. doi: 10.48550/arxiv.2504.18575.

[3]. B. Ramakrishnan and A. Balaji, “Securing AI agents against prompt injection attacks,” arXiv (Cornell University). Nov. 19, 2025. doi: 10.48550/arxiv.2511.15759.

[4]. Q. Zhan, R. Fang, H. S. Panchal, and D. Kang, “Adaptive attacks break defenses against indirect prompt injection attacks on LLM agents,” in Findings of the Association for Computational Linguistics: NAACL 2025, Stroudsburg, PA, USA: Association for Computational Linguistics, 2025, pp. 7101–7117. doi: 10.18653/v1/2025.findings-naacl.395.

[5]. [C. Huang, X. Huang, N. P. Tran, and A. M. Fard, “Model context protocol threat modeling and analysis of vulnerabilities to prompt injection with tool poisoning,” Journal of Cybersecurity and Privacy, vol. 6, no. 3, p. 84, May 2026, doi: 10.3390/jcp6030084.

[6]. A. Edoardo, S. Ananth, and C. Berkay Z., “Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems,” ArXiv.org, 2025, [Online]. Available: https://arxiv.org/pdf/2510.14133

[7]. R. Koohestani, “AgentGuard: Runtime verification of AI agents,” arXiv (Cornell University). Sep. 28, 2025. doi: 10.48550/arxiv.2509.23864.

[8]. C. Păduraru, P.-L. Bouruc, and A. Ştefănescu, “A trace-based assurance framework for agentic AI orchestration: Contracts, testing, and governance,” arXiv (Cornell University). Mar. 18, 2026. doi: 10.48550/arxiv.2603.18096.

[9]. J. C. J. K. Cliff, “Assured intelligence systems: A governed architecture for reliable, auditable, and controllable agentic AI,” Zenodo (CERN European Organization for Nuclear Research). 2026. doi: 10.5281/zenodo.20122776.

[10]. I. A. Rafe, M. R. Dewan, and M. K. Islam, “Orchestration and verification of agentic AI systems: A survey of multi-agent collaboration and safety,” European Journal of Applied Science Engineering and Technology, vol. 4, no. 2, pp. 238–256, Apr. 2026, doi: 10.59324/ejaset.2026.4(2).16.

[11]. R. Haider, “The algorithmic memory of brands: Developing a longitudinal theory of how large language models learn, retain, distort and correct brand knowledge proposal field details,” Jul. 2026, doi: 10.13140/rg.2.2.26017.36966.

[12]. I. ADABARA, B. O. Sadiq, A. N. Shuaibu, Y. I. Danjuma, and M. Venkateswarlu, “Trustworthy agentic AI systems: a cross-layer review of architectures, threat models, and governance strategies for real-world deployment,” F1000Research, vol. 14, p. 905, Sep. 2025, doi: 10.12688/f1000research.169927.1.

[13]. P. Radanliev, O. Santos, and C. Maple, “Threats and vulnerabilities in artificial intelligence and agentic AI models,” Frontiers in Artificial Intelligence, vol. 9, p. 1731566, Feb. 2026, doi: 10.3389/frai.2026.1731566.

[14]. R. Haider, “From search visibility to answer share: Developing and testing a causal theory of brand discoverability and consumer conversion in generative engine optimization,” Jul. 2026, doi: 10.13140/rg.2.2.24339.64807.

[15]. A. Zamecnik, W. Febriantoro, M. Cukurova, S. Joksimovíc, G. Grossmann, and G. Siemens, “Linking AI agent architectures to trust antecedents in human-autonomous teams: a scoping review,” Artificial Intelligence Review, Apr. 2026, doi: 10.1007/s10462-026-11572-z.

[16]. R. Haider, “Attention sovereignty in digital markets: Designing and testing consumer-owned preference agents as an alternative to surveillance-based advertising,” Jul. 2026, doi: 10.13140/rg.2.2.27695.09125.

[17]. Y. Xie, R. Zhou, A. H. S. Chan, and D. Xiong, “Do you trust me? measuring people’s perception of being trusted by AI in a human–agent team,” International Journal of Human-Computer Interaction, vol. 41, no. 20, pp. 13041–13058, Mar. 2025, doi: 10.1080/10447318.2025.2468783.

[18]. “European journal of prosthodontics and restorative dentistry,” May 2026, doi: 10.1922/ejprd.v34i.

[19]. S. Chaduvula et al., “From features to actions: Explainability in traditional and agentic AI systems,” Open MIND. Feb. 06, 2026. doi: 10.48550/arxiv.2602.06841.

[20]. R. Haider et al., “Forensic consumer psychology: An evidence-based framework for detecting deception and digital market manipulation,” Natural Resources for Human Health, vol. 6, no. 16s, pp. 58–73, 2026.

[21]. Z. Atf and P. R. Lewis, “Is trust correlated with explainability in AI? a meta-analysis,” IEEE Transactions on Technology and Society, vol. 7, no. 1, pp. 70–77, Apr. 2025, doi: 10.1109/tts.2025.3558448.

[22]. R. Tomsett et al., “Rapid trust calibration through interpretable and uncertainty-aware AI,” Patterns, vol. 1, no. 4, p. 100049, Jul. 2020, doi: 10.1016/j.patter.2020.100049. [

23].S. Raza, R. Sapkota, M. Karkee, and C. Emmanouilidis, “TRiSM for agentic AI: A review of trust, risk, and security management in LLM-based agentic multi-agent systems,” AI Open, vol. 7, pp. 71–95, 2026, doi: 10.1016/j.aiopen.2026.02.006.

[24]. R. Haider, Md. R. Amin, Md. S. Arafat, I. Hossain, and R. Ahmad, “Smart Automation: Revolutionizing Business Operations, Advertising Costs and Customer Satisfaction Through Technology,” European Economic Letters, vol. 16, no. 1, p. null, 2026.

[25]. M. C. Calzarossa, P. Giudici, and R. Zieni, “An assessment framework for explainable AI with applications to cybersecurity,” Artificial Intelligence Review, vol. 58, no. 5, Feb. 2025, doi: 10.1007/s10462-025-11141-w.

[26]. RaiyanHaider, “Generative AI and quantum-inspired optimization: Redefining portfolio risk management and real-time capital allocation in volatile markets,” Journal of Informatics Education and Research, Mar. 2026, doi: 10.52783/jier.v6i1.4540.

[27]. F. Alpay and T. Alpay, “AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents,” ArXiv.org, 2026, [Online]. Available: https://arxiv.org/pdf/2605.26269

[28]. [34] R. Haider, T. Dwivedi, A. G. G. Girish, N. Verma, B. Kashyap, and V. S. Dubey, “Neuromarketing approaches to shaping healthy consumer choices: An integrative analysis of methods, efficacy, and ethical considerations,” CLOK (University of Central Lancashire), Mar. 2026, doi: 10.25258/ijddt.16.4s.62.

[29]. Y. Liu et al., “Prompt injection attack against LLM-integrated applications,” arXiv (Cornell University). Jun. 08, 2023. doi: 10.48550/arxiv.2306.05499.

[30]. R. Haider, Md. F. I. Shaif, R. Ahmed, N. H. Nafi, M. R. Sumon, and M. Rahman, “Assessing the impact of influencer marketing on brand value and business revenue: An empirical and thematic analysis,” International Journal of Science and Research Archive, vol. 16, no. 2, pp. 471–482, Aug. 2025, doi: 10.30574/ijsra.2025.16.2.2355.

[31]. D. Daniel and J. Sunny, “A Hybrid Defense Against Prompt Injection in LLM Agents : Evaluating Security Efficacy and Computational Performance Trade-offs,” Diva portal (Dalarna University Library), 2026, [Online]. Available: http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-59221

[32]. K. A. Tannenbaum, “AEGIS: A constitutional governance architecture for autonomous AI agents,” Zenodo (CERN European Organization for Nuclear Research). Mar. 25, 2026. doi: 10.5281/zenodo.19223924.

[33].T. Miller, “Controlled agentic AI systems: A governance-driven architecture for auditable and reproducible decision pipelines,” Machine Learning and Knowledge Extraction, vol. 8, no. 5, p. 125, May 2026, doi: 10.3390/make8050125.

[34]. D. Kaur, S. Uslu, K. J. Rittichier, and A. Durresi, “Trustworthy artificial intelligence: A review,” ACM Computing Surveys, vol. 55, no. 2, pp. 1–38, Jan. 2022, doi: 10.1145/3491209.

[35]. R. Haider, Md. F. I. Shaif, R. Ahmed, N. H. Nafi, M. R. Sumon, and M. Rahman, “The influence of social media branding on consumer purchase behavior: A comprehensive empirical and thematic analysis,” International Journal of Science and Research Archive, vol. 16, no. 2, pp. 460–470, Aug. 2025, doi: 10.30574/ijsra.2025.16.2.2354.

[36]. M. Saleme, “Beyond identity governance: A protocol-level security testing framework for multi-agent AI systems,” Zenodo (CERN European Organization for Nuclear Research). Mar. 23, 2026. doi: 10.5281/zenodo.19343034.

[37]. M. Baduwal and P. Paudel, “Evaluating agentic artificial intelligence: A comprehensive survey of metrics, benchmarks, and methodologies.” Institute of Electrical and Electronics Engineers (IEEE), Feb. 27, 2026. doi: 10.36227/techrxiv.177162480.04513202/v2.

[38]. R. Haider, J. T. Juba, and S. Chowdhury, “Exploring the link between suicidal ideation and digital environments: The hidden impact of marketing content,” International Journal of Science and Research Archive, vol. 16, no. 2, pp. 607–614, Aug. 2025, doi: 10.30574/ijsra.2025.16.2.2353.

[39]. N. Flehmig, M. A. Lundteigen, and S. Yin, “Perspectives on a reliability monitoring framework for agentic AI systems,” arXiv (Cornell University). Nov. 12, 2025. doi: 10.48550/arxiv.2511.09178.

[40]. D. Miruke, “AEGIS algebra: A unified mathematical framework for executable assurance of agentic AI artifacts,” Zenodo (CERN European Organization for Nuclear Research), Jun. 2026, doi: 10.5281/zenodo.20813698.

[41]. H. Gough, “Bounded autonomy: Behavioral specification languages and runtime enforcement architectures for trustworthy agentic AI systems.” Wiley, Feb. 11, 2026. doi: 10.22541/au.177083908.89981049/v1.

[42]. R. Haider, W. A. Megha, J. T. Juba, A. Alamgir, and L. Ahmad, “The conversational revolution in health promotion: Investigating chatbot impact on healthcare marketing, patient engagement, and service reach,” International Journal of Science and Research Archive, vol. 15, no. 3, pp. 1585–1592, Jun. 2025, doi: 10.30574/ijsra.2025.15.3.1937.

[43]. R. N. Khan, D. Joyce, and M. Habiba, “AGENTSAFE: A unified framework for ethical assurance and governance in agentic AI,” arXiv (Cornell University). Dec. 02, 2025. doi: 10.48550/arxiv.2512.03180.

[44]. N. Díaz-Rodríguez, J. Del Ser, M. Coeckelbergh, M. L. de Prado, E. Herrera‐Viedma, and F. Herrera, “Connecting the dots in trustworthy artificial intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation,” Information Fusion, vol. 99, p. 101896, Jun. 2023, doi: 10.1016/j.inffus.2023.101896.

[45]. B. Li et al., “Trustworthy AI: From principles to practices,” ACM Computing Surveys, vol. 55, no. 9, pp. 1–46, Aug. 2022, doi: 10.1145/3555803.

[46]. R. Haider, F. A. I. Bari, Osru, N. Afia, and M. A. khan Mugdho, “Leveraging internet of things data for real-time marketing: Opportunities, challenges, and strategic implications,” International Journal of Science and Research Archive, vol. 15, no. 3, pp. 1657–1663, Jun. 2025, doi: 10.30574/ijsra.2025.15.3.1936.

[47]. S. A. Adedokun, D. A. Adedokun, B. O. Ishola, R. I. Adeniran, and C. O. Olaleye, “Agentic AI and autonomous decisionmaking: A review of human-in-the-loop frameworks, oversight mechanisms, and trust calibration,” International Journal of Research and Innovation in Applied Science, vol. 11, no. 3, pp. 1350–1374, 2026, doi: 10.51584/ijrias.2026.11030104.

[48]. P. Papanokechi, “Agent epistemic accountability layer: A framework for runtime verification and trust calibration of

[49]. R. Haider, M. Bari, Md. F. I. Shaif, M. Rahman, Md. N. H. Ohi, and K. M. M. Rahman, “Quantifying the impact: Leveraging AI-Powered sentiment analysis for strategic digital marketing and enhanced brand reputation management,” International Journal of Science and Research Archive, vol. 15, no. 2, pp. 1103–1121, May 2025, doi: 10.30574/ijsra.2025.15.2.1524. [

50]. X. Li, P. Ye, J. Li, Z. Liu, L. Cao, and F. Wang, “From features engineering to scenarios engineering for trustworthy AI: I&I, c&c, and v&v,” IEEE Intelligent Systems, vol. 37, no. 4, pp. 18–26, Jul. 2022, doi: 10.1109/mis.2022.3197950.

[51]. R. Haider and J. Sabatina, “Harnessing the power of micro-influencers: A comprehensive analysis of their effectiveness in promoting climate adaptation solutions,” International Journal of Science and Research Archive, vol. 15, no. 2, pp. 595–610, May 2025, doi: 10.30574/ijsra.2025.15.2.1448.

[52]. R. Haider, M. Bari, Osru, N. Afia, and T. Al Karim, “Illuminating the black box: Explainable AI for enhanced customer behavior prediction and trust,” International Journal of Science and Research Archive, vol. 15, no. 3, pp. 247–268, Jun. 2025, doi: 10.30574/ijsra.2025.15.3.1674.

[53]. R. Haider, M. Bari, Md. F. I. Shaif, and M. Rahman, “Engineering hyper-personalization: Software challenges and brand performance in AI-driven digital marketing management: An empirical study,” International Journal of Science and Research Archive, vol. 15, no. 2, pp. 1122–1141, May 2025, doi: 10.30574/ijsra.2025.15.2.1525.

[54]. A. D. Kaplan, T. T. Kessler, J. C. Brill, and P. A. Hancock, “Trust in artificial intelligence: Meta-Analytic findings,” Human Factors The Journal of the Human Factors and Ergonomics Society, vol. 65, no. 2, pp. 337–359, May 2021, doi: 10.1177/00187208211013988.

[55]. E. Glikson and A. W. Woolley, “Human trust in artificial intelligence: Review of empirical research,” Academy of Management Annals, vol. 14, no. 2, pp. 627–660, Mar. 2020, doi: 10.5465/annals.2018.0057.

[56]. Y. Zhang, Q. V. Liao, and R. K. E. Bellamy, “Effect of confidence and explanation on accuracy and trust calibration in AIassisted decision making,” in Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, New York, NY, USA: ACM, Jan. 2020, pp. 295–305. doi: 10.1145/3351095.3372852.

[57]. N. Wang, D. V. Pynadath, and S. G. Hill, “Trust calibration within a human-robot team: Comparing automatically generated explanations,” 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 109– 116, Mar. 2016, doi: 10.1109/hri.2016.7451741.