English
Related papers

Related papers: ShieldAgent: Shielding Agents via Verifiable Safet…

200 papers

Multi-agent systems under partial observation often struggle to maintain safety because each agent's locally chosen action does not, in general, determine the resulting joint action. Shielding addresses this by filtering actions based on…

Multiagent Systems · Computer Science 2026-04-09 Haoran Yang , Nobuko Yoshida

Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle…

Systems and Control · Electrical Eng. & Systems 2020-01-01 Wenbo Zhang , Osbert Bastani , Vijay Kumar

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…

Cryptography and Security · Computer Science 2026-05-08 Hao Li , Ruoyao Wen , Shanghao Shi , Ning Zhang , Yevgeniy Vorobeychik , Chaowei Xiao

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Cryptography and Security · Computer Science 2026-01-26 Xianya Fang , Xianying Luo , Yadong Wang , Xiang Chen , Yu Tian , Zequn Sun , Rui Liu , Jun Fang , Naiqiang Tan , Yuanning Cui , Sheng-Jun Huang

The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions…

Computation and Language · Computer Science 2025-10-16 Karthik Avinash , Nikhil Pareek , Rishav Hada

Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and unstructured inter-agent communication introduces severe risks, such as indirect prompt…

Cryptography and Security · Computer Science 2026-03-06 Yangyang Wei , Yijie Xu , Zhenyuan Li , Xiangmin Shen , Shouling Ji

Unseen shifts in environment dynamics, driven by hidden parameters such as friction or gravity, create a challenge for maintaining safety. We address this challenge by proposing Adaptive Shielding, a framework for safe reinforcement…

Machine Learning · Computer Science 2026-02-03 Minjae Kwon , Tyler Ingebrand , Ufuk Topcu , Lu Feng

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

Cryptography and Security · Computer Science 2025-09-10 Haitao Hu , Peng Chen , Yanpeng Zhao , Yuqi Chen

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…

Cryptography and Security · Computer Science 2025-11-19 Peiran Wang , Yang Liu , Yunfei Lu , Yifeng Cai , Hongbo Chen , Qingyou Yang , Jie Zhang , Jue Hong , Ye Wu

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…

Software Engineering · Computer Science 2026-01-14 Aarya Doshi , Yining Hong , Congying Xu , Eunsuk Kang , Alexandros Kapravelos , Christian Kästner

Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rules. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Rahul Ghosh , Baishali Chaudhury , Hari Prasanna Das , Meghana Ashok , Ryan Razkenari , Long Chen , Sungmin Hong , Chun-Hao Liu

This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer…

Artificial Intelligence · Computer Science 2025-09-19 Diego Gosmar , Deborah A. Dahl

We present Multi-Agent gatekeeper, a framework that provides provable safety guarantees for leader-follower formation control in cluttered 3D environments. Existing methods face a trad-off: online planners and controllers lack formal safety…

Robotics · Computer Science 2025-11-26 Thomas Marshall Vielmetti , Devansh R Agrawal , Dimitra Panagou

Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the…

Robotics · Computer Science 2022-11-22 Mahmoud Selim , Amr Alanwar , M. Watheq El-Kharashi , Hazem M. Abbas , Karl H. Johansson

Many sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that…

Machine Learning · Computer Science 2021-07-20 Nolan Wagener , Byron Boots , Ching-An Cheng

Malicious agents pose significant threats to the reliability and decision-making capabilities of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs). Existing defenses often fall short due to reactive designs or centralized…

Cryptography and Security · Computer Science 2026-04-03 Yang Feng , Xudong Pan

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Cryptography and Security · Computer Science 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

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

Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…

Software Engineering · Computer Science 2025-11-26 Aram Vardanyan

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…

Artificial Intelligence · Computer Science 2026-02-03 Hanjun Luo , Shenyu Dai , Chiming Ni , Xinfeng Li , Guibin Zhang , Kun Wang , Tongliang Liu , Hanan Salam