Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 13299-13303· 0 citations· 18 references
Abstract
Large language model (LLM) based agents are evolving from conversational chatbots into autonomous decision-makers that plan, reason, wield tools, and collaborate across high-stakes domains such as healthcare, finance, and scientific discovery. Yet this power brings a fundamental challenge: trustworthiness. How can we guarantee that an agent remains robust when real-world data shifts, degrades, or is deliberately poisoned? What defenses exist against memory injection, tool-based exploits, or cascade failures in multi-agent systems? Can we embed domain-specific causal validity, clinical safety, or fairness directly into agent reasoning? And how do we measure trust when it spans robustness, security, reliability, and alignment — each with its own irreconcilable trade-offs? This tutorial delivers a systematic, data-centric roadmap to build LLM agents that are not merely capable but provably trustworthy. We organize the landscape into four interconnected pillars: (i) generalizability under distribution shift, noise, and adversarial inputs; (ii) security architectures that defend against emerging threats — from indirect prompt injection to supply-chain vulnerabilities; (iii) domain-grounded trust in science, engineering, medicine, and commerce, where agents must respect theories, systems, clinical causality, and fairness constraints; and (iv) multi-dimensional evaluation benchmarks that expose trade-offs rather than collapsing them into a single score. By unifying advances in LLM agents, robust machine learning, and data-centric AI, we equip the audience with both foundational principles and actionable recipes to design, deploy, and ultimately trust the next generation of autonomous agent systems.
Agentic AI based on large language models (LLMs) is rapidly evolving from static chatbots to autonomous systems that plan, act, and interact with tools in open-ended environments. However, current LLM agents lack calibrated uncertainty, robust safety mechanisms, and faithful explanations, making them ill-suited for safety-critical settings such as healthcare, finance, cybersecurity, and industrial operations. Extended Belief Rule Bases (EBRB) are representative examples of interpretable, rule-based probabilistic reasoning frameworks with explicit representation of belief and ignorance, and have been successfully applied in complex decision problems without suffering from the rule explosion that affects traditional rule-based approaches. This position paper argues that EBRB could serve as a core safety and reasoning governor within LLM-based agentic pipelines, yielding hybrid systems to better align agentic AI systems with emerging regulatory and ethical requirements for Trustworthy AI (TAI) in high-risk settings. We outline: (i) a conceptual architecture integrating LLMs with EBRB in agentic workflows; (ii) the mapping from this architecture to TAI dimensions including transparency, uncertainty, safety, fairness, and auditability; (iii) concrete opportunities across healthcare, finance, cybersecurity, and industrial safety; and (iv) a research agenda highlighting open challenges in scalable rule induction, co-adaptation between LLMs and EBRB, and evaluation of hybrid agents. Our goal is not to present empirical benchmarks, but to articulate a vision and roadmap for EBRB-enhanced agentic AI that is both powerful and trustworthy.
Jun Liu, Chris D. Nugent, De-Hu Yu et al.· International Journal of Com...· 0 citations
Large language models (LLMs) are increasingly embedded as core components of data-centric systems, supporting analytical decision making, and automated reasoning over large-scale, heterogeneous datasets. Yet their deployment in open-world environments raises fundamental challenges to security and trustworthiness: LLMs can leak sensitive data, fall prey to prompt injection and jailbreaks, generate misinformation, and behave unpredictably under adversarial inputs, failures that propagate through data pipelines and affect downstream decisions. The rise of LLM-based agents further amplifies these risks through unsafe tool use and autonomous decision-making. The 2nd SeT-LLM Workshop on Secure and Trustworthy Large Language Models brings together researchers and practitioners from data mining, machine learning, security, and responsible AI to address these issues from a data-centric, system-level perspective, spanning robust defenses, trustworthy evaluation, privacy and copyright protection, robustness, alignment and safety, agent security, and high-stakes applications. Through invited talks, contributed papers, a poster session, and a panel discussion, the workshop prioritizes early-stage ideas, system experiences, and open problems across the lifecycle of LLM-based systems.
Lu Lin, Jinghui Chen, Ting Wang et al.· Proceedings of the 32nd ACM...· 0 citations
It is argued that adversarial vulnerability stems from the absence of boundary verification, a security primitive that enforces explicit validation of data as it crosses inter-agent boundaries, including content, identity, execution intent, and state integrity.
Faisal Haque Bappy, Tahrim Hossain, T. S. Zaman et al.· 0 citations
Mobile network operators are increasingly exploring the use of artificial intelligence (AI) to automate complex network tasks, such as cell selection and mobility management. A fundamental problem arises: there is currently no way to verify that an AI function is making the right decisions or for the right reasons, rather than arriving at correct-looking answers through unreliable shortcuts. In safety-critical and resilience-focused infrastructure, this lack of transparency poses a significant challenge to the widespread adoption of AI technologies in wireless networks. In this paper, we propose a mechanical auditing approach: inspecting a function's internal representations and checking them against machine-verifiable 3GPP specifications. Specifically, we set out a general three-step auditing principle that locates protocol-relevant features, verifies their causal role, and diagnoses how adaptation reshapes their use, grounding it throughout publicly available interpretability and telecommunications research. We present an audit-native network architecture in which a dedicated verification agent continuously checks the reasoning of AI functions in networks, supporting both predeployment certification and runtime auditing. We also discuss how it could be realised, the data and benchmarks, as well as the open challenges that remain before mechanistic auditing can enter telecommunications practice and standardisation.
Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale: a finite context window cannot hold a multi-thousand-host authentication graph, and free-form generation offers no guarantee that a recommended containment action is consistent with the topology it operates on. We present Sentinel-RL, an agentic-SOC architecture that decouples topological reasoning from semantic reasoning: a heterogeneous graph attention encoder summarizes the live authentication subgraph into a fixed-dimensional state, a Proximal Policy Optimization (PPO) policy maps this state to a constrained set of investigative actions, and an LLM agent loop is restricted to consuming the policy's recommendations and producing analyst-readable narratives gated by a critic. We instantiate the system on the LANL Comprehensive, Multi-Source Cyber-Security Events dataset and the Indiana University Quartz HPC cluster, reporting four results: (i) a two-phase CREATE ingestion pattern loads a 24M-edge authentication subgraph into Neo4j in 14.2 minutes on a single 32-core node, roughly 24x faster than the canonical MERGE-based pipeline; (ii) a sliding-window alert engine reliably trips a 25-event/10-second threshold in<=2.5 s across 50 trials; (iii) PPO training over 200 iterations converges to a mean episodic return of 8.74+/-0.31, with held-out precision of 0.91 and recall of 0.87 on labeled red-team events; and (iv) the integrated containment loop completes a full detect-investigate-recommend-human-approve cycle in a median of 6.3 s. We contribute a reusable engineering pattern (the hot-node deadlock workaround), a portable HPC deployment pattern (anchor-node co-location), and an enterprise-readiness analysis covering false-positive economics, reversibility guarantees, audit compliance, and the human-approval boundary.
Uday Vallabhaneni, Cassie L. Cagwin, David J. Wild· 1 citation
BekchiAI is a complementary web-based observability and control layer for deployed agents, providing full token and latency telemetry as well as remote run termination and the benchmark, evaluation tools, and platform are publicly released.
Mesut Toruk· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
