English
Related papers

Related papers: PAuth - Precise Task-Scoped Authorization For Agen…

200 papers

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…

The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often…

Artificial Intelligence · Computer Science 2026-05-20 Haoran Zhang , Luxin Xu , Zhilin Wang , Runquan Gui , Shunkai Zhang , Haodi Lei , Zihao He , Bingsu He , Chicheng Qin , Tong Zhu , Xiaoye Qu , Yang Yang , Yu Cheng , Yafu Li

Previous benchmarks on prompt injection in large language models (LLMs) have primarily focused on generic tasks and attacks, offering limited insights into more complex threats like data exfiltration. This paper examines how prompt…

Cryptography and Security · Computer Science 2025-06-03 Meysam Alizadeh , Zeynab Samei , Daria Stetsenko , Fabrizio Gilardi

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security…

Cryptography and Security · Computer Science 2026-02-25 Che Wang , Jiaming Zhang , Ziqi Zhang , Zijie Wang , Yinghui Wang , Jianbo Gao , Tao Wei , Zhong Chen , Wei Yang Bryan Lim

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

We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on…

People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their…

Computers and Society · Computer Science 2019-02-06 Brett W Israelsen , Nisar R Ahmed

Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…

Artificial Intelligence · Computer Science 2026-03-03 Tri Cao , Bennett Lim , Yue Liu , Yuan Sui , Yuexin Li , Shumin Deng , Lin Lu , Nay Oo , Shuicheng Yan , Bryan Hooi

Remote attestation protocols are widely used to detect device configuration (e.g., software and/or data) compromise in Internet of Things (IoT) scenarios. Unfortunately, the performances of such protocols are unsatisfactory when dealing…

Cryptography and Security · Computer Science 2018-06-18 Moreno Ambrosin , Mauro Conti , Riccardo Lazzeretti , Md Masoom Rabbani , Silvio Ranise

Existing tool-augmented agentic systems are limited in the real world by (i) black-box reasoning steps that undermine trust of decision-making and pose safety risks, (ii) poor multimodal integration, which is inherently critical for…

Artificial Intelligence · Computer Science 2025-12-22 Yushi Feng , Junye Du , Yingying Hong , Qifan Wang , Lequan Yu

AI systems make decisions in physical environments through primitive actions or affordances that are accessed via API calls. While deploying AI agents in the real world involves numerous high-level actions, existing embodied simulators…

Computation and Language · Computer Science 2025-06-17 Jiefu Ou , Arda Uzunoglu , Benjamin Van Durme , Daniel Khashabi

LLM-based agents are increasingly deployed in high-stakes scenarios such as email management, financial transactions, and code execution, where they interact with the external world through tool calling. During execution, these agents must…

Cryptography and Security · Computer Science 2026-05-27 Peiran Wang , Ying Li , Yuan Tian

Learning and remembering to use APIs are difficult. Several techniques have been proposed to assist developers in using APIs. Most existing techniques focus on recommending the right API methods to call, but very few techniques focus on…

Software Engineering · Computer Science 2023-06-13 Son Nguyen , Cuong Tran Manh , Kien T. Tran , Tan M. Nguyen , Thu-Trang Nguyen , Kien-Tuan Ngo , Hieu Dinh Vo

People always desire an embodied agent that can perform a task by understanding language instruction. Moreover, they also want to monitor and expect agents to understand commands the way they expected. But, how to build such an embodied…

Artificial Intelligence · Computer Science 2022-03-10 Haoyu Liu , Yang Liu , Hongkai He , Hangfang Yang

Stories about everyday situations are an essential part of human communication, motivating the need to develop AI agents that can reliably understand these stories. Despite the long list of supervised methods for story completion and…

Computation and Language · Computer Science 2023-11-21 Yifan Jiang , Filip Ilievski , Kaixin Ma

AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…

Software Engineering · Computer Science 2026-05-12 Reshabh K Sharma , Shraddha Barke , Benjamin Zorn

Recent advances in large language models (LLMs) have enabled a new generation of autonomous agents that operate over sustained periods and manage sensitive resources on behalf of users. Trusted for their ability to act without direct…

Cryptography and Security · Computer Science 2025-12-19 Artem Grigor , Christian Schroeder de Witt , Simon Birnbach , Ivan Martinovic

Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…

Cryptography and Security · Computer Science 2025-09-01 Georgios Syros , Anshuman Suri , Jacob Ginesin , Cristina Nita-Rotaru , Alina Oprea

AI agents allow developers to express computational intent abstractly, reducing cognitive effort and helping achieve flow during programming. Increased abstraction, however, comes at a cost: developers cede decision-making authority to…

Human-Computer Interaction · Computer Science 2026-04-08 Saketh Ram Kasibatla , Raven Rothkopf , Hila Peleg , Benjamin C. Pierce , Sorin Lerner , Harrison Goldstein , Nadia Polikarpova

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