~ similar to 2607.29405· 20 results
This paper identifies and discusses various challenges in securing autonomous agents, focusing on behavioral containment, single-agent attack surfaces, and multi-agent trust and communication.
This paper surveys the trustworthiness of agentic AI systems in engineering domains, organizing it around five dimensions: safety, robustness, transparency, accountability, and privacy.
Jinhu Qi, Muzhi Li, Jiahong Liu, Yuqin Shu +8 more
This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.
Proposes AI-GRACE, a framework for organizations to deploy agentic artificial intelligence while meeting obligations and delivering intended outcomes.
Agentproof is a system that provides static, pre-deployment verification of safety properties in agent workflow graphs by automatically extracting a unified graph model and applying structural and tem…
The paper introduces POIROT, a novel protocol that uses the agents within a multi-agent system itself to diagnose and detect failures, demonstrating superior performance over traditional evaluation me…
This tutorial explores advances and challenges in deploying large language model-based agentic systems across industries, with a focus on reasoning and planning, multi-agent coordination, and evaluati…
The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.
Shengcheng Yu, Yuchen Ling, Junyang Xing, Quan Zhou +2 more
This paper reviews 336 GUI-agent papers from 2018 to 2026, examining the research landscape, architectures, evaluation, software lifecycle concerns, and future opportunities.
The paper proposes a Semantic Gateway and a Zero-Trust security model to formally validate and secure autonomous AI agents operating in enterprise systems, achieving a 100% discovery rate of unauthori…
The paper proposes a methodology for auditable trustworthiness levels in AI governance with a formal framework and a lightweight procedure.
The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…
This paper proposes a framework for proactive agent security assurance through a five-layer Boundary Assurance Stack and a Proactive Agent Security Assurance Cycle.
The paper introduces the Function--Evidence--Validation (FEV) framework to assess the accountability of agent-generated workflows in bioinformatics, focusing on workflow correctness.
The paper defines AI Identity as the correspondence between an agent's declared state and its observed behavior, concluding that current infrastructure and standards are fundamentally inadequate for g…
Muhammad Bilal, Jon Crowcroft, Ruizhi Wang, Xiaolong Xu +1 more
The paper surveys the use of LLMs for agentic NetOps and AIOps, arguing that operational reliability depends not on the model itself, but on robust surrounding machinery and workflow-centered evaluati…
A longitudinal study of silent failures in a personal-assistant agent runtime, identifying a new type of failure called 'fail-plausible' and proposing a defense framework.