English
Related papers

Related papers: AgentDoG 1.5: A Lightweight and Scalable Alignment…

200 papers

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…

Artificial Intelligence · Computer Science 2026-05-26 Jinhu Qi , Muzhi Li , Jiahong Liu , Yuqin Shu , Dianzhi Yu , Shicheng Ma , Wenqian Cui , Yiyang Zhao , Yiyi Chen , Ruoxi Jiang , Irwin King , Zenglin Xu

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or…

Artificial Intelligence · Computer Science 2025-08-06 Xufang Luo , Yuge Zhang , Zhiyuan He , Zilong Wang , Siyun Zhao , Dongsheng Li , Luna K. Qiu , Yuqing Yang

AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential…

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 AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…

Computers and Society · Computer Science 2024-10-04 Hayley Clatterbuck , Clinton Castro , Arvo Muñoz Morán

The rapid deployment of large language model (LLM)-based agents introduces a new class of risks, driven by their capacity for autonomous planning, multi-step tool integration, and emergent interactions. It raises some risk factors for…

Multiagent Systems · Computer Science 2025-12-04 Rafflesia Khan , Declan Joyce , Mansura Habiba

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…

As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…

The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. However, existing agent frameworks often suffer from…

Artificial Intelligence · Computer Science 2026-01-21 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain…

Cryptography and Security · Computer Science 2026-04-28 Yixiang Zhang , Xinhao Deng , Jiaqing Wu , Yue Xiao , Ke Xu , Qi Li

Agentic AI systems, possessing capabilities for autonomous planning and action, show great potential across diverse domains. However, their practical deployment is hindered by challenges in aligning their behavior with varied human values,…

Artificial Intelligence · Computer Science 2025-08-12 Nell Watson , Ahmed Amer , Evan Harris , Preeti Ravindra , Shujun Zhang

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Artificial Intelligence · Computer Science 2026-05-07 Chenglin Yang

Large Action models are essential for enabling autonomous agents to perform complex tasks. However, training such models remains challenging due to the diversity of agent environments and the complexity of noisy agentic data. Existing…

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of…

Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…

Artificial Intelligence · Computer Science 2026-04-16 Qibin Liu , Julia Gonski

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…

Cryptography and Security · Computer Science 2026-05-15 Surada Suwansathit , Yuxuan Zhang , Guofei Gu

Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical routing question that existing evaluations do not directly answer: which parts of an…

Artificial Intelligence · Computer Science 2026-05-04 Ranit Karmakar , Jayita Chatterjee

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

Cryptography and Security · Computer Science 2026-03-16 Zonghao Ying , Xiao Yang , Siyang Wu , Yumeng Song , Yang Qu , Hainan Li , Tianlin Li , Jiakai Wang , Aishan Liu , Xianglong Liu

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…

Cryptography and Security · Computer Science 2025-03-04 Ishaan Domkundwar , Mukunda N S , Ishaan Bhola , Riddhik Kochhar