English
Related papers

Related papers: The Authorization-Execution Gap Is a Major Safety …

200 papers

Across healthcare, agentic artificial intelligence (AI) systems are increasingly promoted as capable of autonomous action, yet in practice they currently operate under near-total human oversight due to safety, regulatory, and liability…

We are interested in interactive agents that learn to coordinate, namely, a $builder$ -- which performs actions but ignores the goal of the task, i.e. has no access to rewards -- and an $architect$ which guides the builder towards the goal…

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 evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of…

Cryptography and Security · Computer Science 2026-03-03 Chuanming Tang , Ling Qing , Shifeng Chen

Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security…

Artificial Intelligence · Computer Science 2026-01-14 Xinyi Wu , Jiagui Chen , Geng Hong , Jiayi Dong , Xudong Pan , Jiarun Dai , Min Yang

Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce…

Artificial Intelligence · Computer Science 2026-02-05 Zhaotian Weng , Antonis Antoniades , Deepak Nathani , Zhen Zhang , Xiao Pu , Xin Eric Wang

Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilistic inference,…

Cryptography and Security · Computer Science 2026-02-10 Guanquan Shi , Haohua Du , Zhiqiang Wang , Xiaoyu Liang , Weiwenpei Liu , Song Bian , Zhenyu Guan

Enterprise teams building internal coding agents face a gap between prototype performance and production readiness. The root cause is that technical model quality alone is insufficient -- tool design, safety enforcement, state management,…

Software Engineering · Computer Science 2026-04-14 Gustavo Pinto , Pedro Eduardo de Paula Naves , Ana Paula Camargo , Marselle Silva

As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper…

Artificial Intelligence · Computer Science 2026-05-05 Tanav Singh Bajaj , Nikhil Singh , Karan Anand , Eishkaran Singh

With increasing numbers of vulnerabilities exposed on the internet, autonomous penetration testing (pentesting) has emerged as a promising research area. Reinforcement learning (RL) is a natural fit for studying this topic. However, two key…

Machine Learning · Computer Science 2025-02-12 Shicheng Zhou , Jingju Liu , Yuliang Lu , Jiahai Yang , Yue Zhang , Jie Chen

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Machine Learning · Computer Science 2025-07-11 Ram Potham

When should an autonomous agent commit resources to a task? We introduce the Agent Capability Problem (ACP), a framework for predicting whether an agent can solve a problem under resource constraints. Rather than relying on empirical…

Artificial Intelligence · Computer Science 2025-12-09 Shahar Lutati

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Cryptography and Security · Computer Science 2026-04-28 Richard Joseph Mitchell

Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems…

The emergence of autonomous, high-velocity Agentic AI systems is creating an internal assurance scalability crisis. Point-in-time, document-based audits cannot keep pace with non deterministic behaviour and distributed deployments of agents…

Computers and Society · Computer Science 2026-03-05 Guy Lupo , Bao Quoc Vo , Natania Locke

Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…

Cryptography and Security · Computer Science 2025-09-16 Harold Triedman , Rishi Jha , Vitaly Shmatikov

Autonomous agents can produce harmful behavioral patterns from individually valid requests -- a threat class per-request policy evaluation cannot address, because stateless engines evaluate each request in isolation. We present ACP, a…

Cryptography and Security · Computer Science 2026-05-04 Marcelo Fernandez

GUI agents are designed to automate repetitive tasks and enhance productivity. However, existing GUI agents struggle to recover once they follow an incorrect exploration path, often leading to task failure. In this work, we model GUI task…

Artificial Intelligence · Computer Science 2026-01-30 Ziyu Lu , Tengjin Weng , Yiying Yang , Yuhang Zhao , Xinxin Huang , Wenhao Jiang

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful…

Cryptography and Security · Computer Science 2026-05-12 Hardik Goel

We propose an extension to the OWASP Multi-Agentic System (MAS) Threat Modeling Guide, translating recent anticipatory research in multi-agent security (MASEC) into practical guidance for addressing challenges unique to large language model…

Multiagent Systems · Computer Science 2025-08-14 Klaudia Krawiecka , Christian Schroeder de Witt
‹ Prev 1 4 5 6 7 8 10 Next ›