Xueping Liang

Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these systems enable powerful new capabilities, increasing autonomy introduces critical challenges related to explainability, accountability, robustness, and governance, especially when agent outputs influence downstream actions or decisions. Existing agentic AI implementations often emphasize functionality and scalability, yet provide limited mechanisms for understanding decision rationale or enforcing responsibility across agent interactions. This paper presents a Responsible(RAI) and Explainable(XAI) AI Agent Architecture for production-grade agentic workflows based on multi-model consensus and reasoning-layer governance. In the proposed design, a consortium of heterogeneous LLM and VLM agents independently generates candidate outputs from a shared input context, explicitly exposing uncertainty, disagreement, and alternative interpretations. A dedicated reasoning agent then performs structured consolidation across these outputs, enforcing safety and policy constraints, mitigating hallucinations and bias, and producing auditable, evidence-backed decisions. Explainability is achieved through explicit cross-model comparison and preserved intermediate outputs, while responsibility is enforced through centralized reasoning-layer control and agent-level constraints. We evaluate the architecture across multiple real-world agentic AI workflows, demonstrating that consensus-driven reasoning improves robustness, transparency, and operational trust across diverse application domains. This work provides practical guidance for designing agentic AI systems that are autonomous and scalable, yet responsible and explainable by construction.

Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks. Unlike traditional single model prompting, agentic workflows integrate multiple specialized agents with different Large Language Models(LLMs), tool-augmented capabilities, orchestration logic, and external system interactions to form dynamic pipelines capable of autonomous decision-making and action. As adoption accelerates across industry and research, organizations face a central challenge: how to design, engineer, and operate production-grade agentic AI workflows that are reliable, observable, maintainable, and aligned with safety and governance requirements. This paper provides a practical, end-to-end guide for designing, developing, and deploying production-quality agentic AI systems. We introduce a structured engineering lifecycle encompassing workflow decomposition, multi-agent design patterns, Model Context Protocol(MCP), and tool integration, deterministic orchestration, Responsible-AI considerations, and environment-aware deployment strategies. We then present nine core best practices for engineering production-grade agentic AI workflows, including tool-first design over MCP, pure-function invocation, single-tool and single-responsibility agents, externalized prompt management, Responsible-AI-aligned model-consortium design, clean separation between workflow logic and MCP servers, containerized deployment for scalable operations, and adherence to the Keep it Simple, Stupid (KISS) principle to maintain simplicity and robustness. To demonstrate these principles in practice, we present a comprehensive case study: a multimodal news-analysis and media-generation workflow. By combining architectural guidance, operational patterns, and practical implementation insights, this paper offers a foundational reference to build robust, extensible, and production-ready agentic AI workflows.

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these systems introduce novel and evolving security challenges, including prompt injection attacks, context poisoning, model manipulation, and opaque agent-to-agent communication, that are not effectively captured by traditional threat modeling frameworks. In this paper, we introduce ASTRIDE, an automated threat modeling platform purpose-built for AI agent-based systems. ASTRIDE extends the classical STRIDE framework by introducing a new threat category, A for AI Agent-Specific Attacks, which encompasses emerging vulnerabilities such as prompt injection, unsafe tool invocation, and reasoning subversion, unique to agent-based applications. To automate threat modeling, ASTRIDE combines a consortium of fine-tuned vision-language models (VLMs) with the OpenAI-gpt-oss reasoning LLM to perform end-to-end analysis directly from visual agent architecture diagrams, such as data flow diagrams(DFDs). LLM agents orchestrate the end-to-end threat modeling automation process by coordinating interactions between the VLM consortium and the reasoning LLM. Our evaluations demonstrate that ASTRIDE provides accurate, scalable, and explainable threat modeling for next-generation intelligent systems. To the best of our knowledge, ASTRIDE is the first framework to both extend STRIDE with AI-specific threats and integrate fine-tuned VLMs with a reasoning LLM to fully automate diagram-driven threat modeling in AI agent-based applications.

Software services are crucial for reliable communication and networking; therefore, Site Reliability Engineering (SRE) is important to ensure these systems stay reliable and perform well in cloud-native environments. SRE leverages tools like Prometheus and Grafana to monitor system metrics, defining critical Service Level Indicators (SLIs) and Service Level Objectives (SLOs) for maintaining high service standards. However, a significant challenge arises as many developers often lack in-depth understanding of these tools and the intricacies involved in defining appropriate SLIs and SLOs. To bridge this gap, we propose a novel SRE platform, called SRE-Llama, enhanced by Generative-AI, Federated Learning, Blockchain, and Non-Fungible Tokens (NFTs). This platform aims to automate and simplify the process of monitoring, SLI/SLO generation, and alert management, offering ease in accessibility and efficy for developers. The system operates by capturing metrics from cloud-native services and storing them in a time-series database, like Prometheus and Mimir. Utilizing this stored data, our platform employs Federated Learning models to identify the most relevant and impactful SLI metrics for different services and SLOs, addressing concerns around data privacy. Subsequently, fine-tuned Meta's Llama-3 LLM is adopted to intelligently generate SLIs, SLOs, error budgets, and associated alerting mechanisms based on these identified SLI metrics. A unique aspect of our platform is the encoding of generated SLIs and SLOs as NFT objects, which are then stored on a Blockchain. This feature provides immutable record-keeping and facilitates easy verification and auditing of the SRE metrics and objectives. The automation of the proposed platform is governed by the blockchain smart contracts. The proposed SRE-Llama platform prototype has been implemented with a use case featuring a customized Open5GS 5G Core.

In recent years, blockchain has experienced widespread adoption across various industries, becoming integral to numerous enterprise applications. Concurrently, the rise of generative AI and LLMs has transformed human-computer interactions, offering advanced capabilities in understanding and generating human-like text. The introduction of the MCP has further enhanced AI integration by standardizing communication between AI systems and external data sources. Despite these advancements, there is still no standardized method for seamlessly integrating LLM applications and blockchain. To address this concern, we propose "MCC: Model Context Contracts" a novel framework that enables LLMs to interact directly with blockchain smart contracts through MCP-like protocol. This integration allows AI agents to invoke blockchain smart contracts, facilitating more dynamic and context-aware interactions between users and blockchain networks. Essentially, it empowers users to interact with blockchain systems and perform transactions using queries in natural language. Within this proposed architecture, blockchain smart contracts can function as intelligent agents capable of recognizing user input in natural language and executing the corresponding transactions. To ensure that the LLM accurately interprets natural language inputs and maps them to the appropriate MCP functions, the LLM was fine-tuned using a custom dataset comprising user inputs paired with their corresponding MCP server functions. This fine-tuning process significantly improved the platform's performance and accuracy. To validate the effectiveness of MCC, we have developed an end-to-end prototype implemented on the Rahasak blockchain with the fine-tuned Llama-4 LLM. To the best of our knowledge, this research represents the first approach to using the concept of Model Context Protocol to integrate LLMs with blockchain.

While Ethereum's discovery protocols (Discv4/ Discv5) incorporate robust cryptographic designs to protect user privacy, real-world deployment reveals critical vulnerabilities when users deviate from security guidelines. In this paper, we design a system called EGNInfoLeaker. Our study is the first work that uncovers widespread public key reuse across Ethereum's peer-to-peer networks - a practice that fundamentally undermines the protocol's privacy guarantees. Through systematic analysis of 300 real-world network snapshots, we identify 83 users controlling 483 service nodes via public key reuse, enabling precise de-anonymization through IP correlation. Using evidence collected by EGNInfoLeaker, our Graph-Based Identity Association Algorithm links users to network entities and generates comprehensive user profiles. For User27, it exposes the public key, IP, network ID, location (country/region/city), and ISP/ORG details. The EGNInfoLeaker system demonstrates how such cryptographic misuse transforms theoretical anonymity into practical identity leakage, exposing users to surveillance and targeted attacks. These findings establish that protocol security depends not only on sound design but also on strict user compliance. Going forward, our detection framework provides a foundation for enhancing real-world privacy preservation in decentralized networks.

Background: Telehealth played a critical role during the COVID-19 pandemic and continues to function as an essential component of health care. Existing platforms cannot ensure privacy and prevent cyberattacks. Objective: The main objectives of this study are to understand existing cybersecurity issues in identity management and trustworthy communication processes in telehealth platforms and to design a software architecture integrated with blockchain to improve security and trustworthiness with acceptable performance. Methods: We improved personal information security in existing telehealth platforms by adopting an innovative interdisciplinary approach combining design science, social science, and computer science in the health care domain, with prototype implementation. We used the design science research methodology to implement our overall design. We innovated over existing telehealth platforms with blockchain integration that improves health care delivery services in terms of security, privacy, and efficiency. We adopted a user-centric design approach and started with user requirement collection, followed by system functionality development. Overall system implementation facilitates user requirements, thus promoting user behavior for the adoption of the telehealth platform with decentralized identity management and an access control mechanism. Results: Our investigation identified key challenges to identity management and trustworthy communication processes in telehealth platforms used in the current health care domain. By adopting distributed ledger technology, we proposed a decentralized telehealth platform to support identity management and a trustworthy communication process. Our design and prototype implementation using a smart contract–driven telehealth platform to provide decentralized identity management and trustworthy communication with token-based access control addressed several security challenges. This was substantiated by testing with 10,000 simulated transactions across 5 peers in the Rahasak blockchain network. The proposed design provides resistance to common attacks while maintaining a linear time overhead, demonstrating improved security and efficiency in telehealth services. We evaluated the performance in terms of transaction throughput, smart contract execution time, and block generation time. To create a block with 10,000 transactions, it takes 8 seconds on average, which is an acceptable overhead for blockchain-based applications. Conclusions: We identified technical limitations in current telehealth platforms. We presented several design innovations using blockchain to prototype a system. We also presented the implementation details of a unique distributed architecture for a trustworthy communication system. We illustrated how this design can overcome privacy, security, and scalability limitations. Moreover, we illustrated how improving these factors sets the stage for improving and standardizing the application and for the wide adoption of blockchain-enabled telehealth platforms.