English
Related papers

Related papers: Mind the Gap: Comparing Model- vs Agentic-Level Re…

200 papers

As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating deployment-specific risks. We present a comprehensive, observability-driven workflow: we…

Computation and Language · Computer Science 2026-04-28 Ilham Wicaksono , Zekun Wu , Rahul Patel , Theo King , Adriano Koshiyama , Philip Treleaven

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in…

Cryptography and Security · Computer Science 2026-03-25 Hyomin Lee , Sangwoo Park , Yumin Choi , Sohyun An , Seanie Lee , Sung Ju Hwang

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the…

While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on human-specified workflows. This dependence on manually designed workflows suffers from human biases…

Artificial Intelligence · Computer Science 2026-04-06 Jiayi Yuan , Jonathan Nöther , Natasha Jaques , Goran Radanović

Agentic systems have transformed how Large Language Models (LLMs) can be leveraged to create autonomous systems with goal-directed behaviors, consisting of multi-step planning and the ability to interact with different environments. These…

Artificial Intelligence · Computer Science 2026-01-27 Judy Zhu , Dhari Gandhi , Himanshu Joshi , Ahmad Rezaie Mianroodi , Sedef Akinli Kocak , Dhanesh Ramachandran

This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure stack, a structured…

Systems and Control · Electrical Eng. & Systems 2025-11-11 Janet , Lin , Liangwei Zhang

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Cryptography and Security · Computer Science 2026-04-08 Zenghao Duan , Yuxin Tian , Zhiyi Yin , Liang Pang , Jingcheng Deng , Zihao Wei , Shicheng Xu , Yuyao Ge , Xueqi Cheng

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current…

Cryptography and Security · Computer Science 2026-05-12 Monika Jotautaitė , Maria Angelica Martinez , Ollie Matthews , Tyler Tracy

Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation,…

Artificial Intelligence · Computer Science 2025-12-22 Ali Eslami , Jiangbo Yu

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

Cryptography and Security · Computer Science 2026-05-13 Hongwei Yao , Yiming Liu , Yiling He , Bingrun Yang

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Computation and Language · Computer Science 2026-05-22 Asaf Yehudai , Lilach Eden , Michal Shmueli-Scheuer

Foundation model-based agents are increasingly used to automate complex tasks, enhancing efficiency and productivity. However, their access to sensitive resources and autonomous decision-making also introduce significant security risks,…

Cryptography and Security · Computer Science 2025-06-03 Chejian Xu , Mintong Kang , Jiawei Zhang , Zeyi Liao , Lingbo Mo , Mengqi Yuan , Huan Sun , Bo Li

AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control. Agents may skip required tool calls, invoke tools unnecessarily, or…

Artificial Intelligence · Computer Science 2026-05-22 Hariom Tatsat , Ariye Shater

Warning: This paper contains content that may be inappropriate or offensive. AI agents have gained significant recent attention due to their autonomous tool usage capabilities and their integration in various real-world applications. This…

Artificial Intelligence · Computer Science 2025-06-24 Ninareh Mehrabi , Tharindu Kumarage , Kai-Wei Chang , Aram Galstyan , Rahul Gupta

The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…

Artificial Intelligence · Computer Science 2025-11-13 Niclas Flehmig , Mary Ann Lundteigen , Shen Yin

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Artificial Intelligence · Computer Science 2025-10-30 Juan Ren , Mark Dras , Usman Naseem

Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a…

Operating Systems · Computer Science 2025-10-21 Yusheng Zheng , Yanpeng Hu , Tong Yu , Andi Quinn
‹ Prev 1 2 3 10 Next ›