paper-with-me

Papers

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security

2026-05-17 · Jinhu Qi, Muzhi Li, Jiahong Liu, Yuqin Shu, Dianzhi Yu, Shicheng Ma, Wenqian Cui, Yiyang Zhao, Yiyi Chen, Ruoxi Jiang, Irwin King, Zenglin Xu arxiv

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness. This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments: Safety and Robustness, and Privacy and System Security. For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies. Other trustworthiness aspects (value alignment, transparency, fairness, and accountability) are discussed as relevant context rather than parallel chapters. To support consistent comparison and deployment decisions, we consolidate evaluation into a unified metrics-and-benchmarks hub, emphasizing both outcome and process signals (e.g., constraint violations, trace completeness, and adversarial success rates) and offering scenario-to-metric guidance for release gating. We conclude by outlining open challenges such as self-evolving agents, runtime monitoring and verification, privacy-preserving personalization, and the trust-utility trade-off, and present a case study of real-world security failures in open-source agentic systems. Our goal is to serve as a practical reference for researchers and practitioners building trustworthy agentic systems in high-stakes environments.

📄 PDF Abstract BibTeX arXiv:2605.23989

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks

2023-10-01 · YanJie Li, Bin Xie, Songtao Guo, Yuanyuan Yang 외

Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are …

Deep Learning

Trustworthy AI: A Computational Perspective

2021-07-12 · Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu 외

In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone's daily life and profoundly altering the course of human society. The intention of developing AI is t…

Fairness

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

2025-09-04 · Yanbo Wang, Yongcan Yu, Jian Liang, Ran He arxiv

The development of Long-CoT reasoning has advanced LLM performance across various tasks, including language understanding, complex problem solving, and code generation. This paradigm enables models to generate intermedia…

Code Generation

Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability

2022-09-16 · Mengdi Xu, Zuxin Liu, Peide Huang, Wenhao Ding 외

A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions

2025-10-29 · Mohamad Abou Ali, Fadi Dornaika arxiv

Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice…