English
Related papers

Related papers: AGI Agent Safety by Iteratively Improving the Util…

200 papers

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents…

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…

Cryptography and Security · Computer Science 2026-03-16 Aojie Yuan , Zhiyuan Su , Yue Zhao

How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI assistance and the AI shutdown games. The AI assistance problem concerns designing an AI agent that…

Artificial Intelligence · Computer Science 2025-12-30 Alessio Benavoli , Alessandro Facchini , Marco Zaffalon

A multi-agent AI system (MAS) is composed of multiple autonomous agents that interact, exchange information, and make decisions based on internal generative models. Recent advances in large language models and tool-using agents have made…

How to evaluate Artificial General Intelligence (AGI) is a critical problem that is discussed and unsolved for a long period. In the research of narrow AI, this seems not a severe problem, since researchers in that field focus on some…

Artificial Intelligence · Computer Science 2023-08-25 Bowen Xu , Quansheng Ren

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Haolong Yan , Yeqing Shen , Xin Huang , Jia Wang , Kaijun Tan , Zhixuan Liang , Hongxin Li , Zheng Ge , Osamu Yoshie , Si Li , Xiangyu Zhang , Daxin Jiang

AI agents plan and execute interactions in open-ended environments. For example, OpenAI's Operator can use a web browser to do product comparisons and buy online goods. Much research on making agents useful and safe focuses on directly…

Artificial Intelligence · Computer Science 2025-06-23 Alan Chan , Kevin Wei , Sihao Huang , Nitarshan Rajkumar , Elija Perrier , Seth Lazar , Gillian K. Hadfield , Markus Anderljung

This paper proposes an intent-aware multi-agent planning framework as well as a learning algorithm. Under this framework, an agent plans in the goal space to maximize the expected utility. The planning process takes the belief of other…

Artificial Intelligence · Computer Science 2018-03-07 Siyuan Qi , Song-Chun Zhu

Nowadays, agentic AI is emerging as a transformative paradigm for next-generation communication networks, promising to evolve large language models (LLMs) from passive chatbots into autonomous operators. However, unleashing this potential…

Networking and Internet Architecture · Computer Science 2026-01-14 Yinqiu Liu , Ruichen Zhang , Dusit Niyato , Abbas Jamalipour , Trung Q. Duong , Dong In Kim

AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agents is challenging: they behave autonomously and…

Cryptography and Security · Computer Science 2026-05-15 Tianneng Shi , Jingxuan He , Zhun Wang , Hongwei Li , Linyu Wu , Wenbo Guo , Dawn Song

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…

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

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

Artificial Intelligence · Computer Science 2026-05-26 Andy Xu , Yu-Wing Tai

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

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Artificial Intelligence · Computer Science 2026-02-18 Sanidhya Vijayvargiya , Aditya Bharat Soni , Xuhui Zhou , Zora Zhiruo Wang , Nouha Dziri , Graham Neubig , Maarten Sap

Addressing complex cooperative tasks in safety-critical environments poses significant challenges for multi-agent systems, especially under conditions of partial observability. We focus on a dynamic network bridging task, where agents must…

Multiagent Systems · Computer Science 2025-04-04 Raffaele Galliera , Konstantinos Mitsopoulos , Niranjan Suri , Raffaele Romagnoli

Intelligent agents stand out as a potential path toward artificial general intelligence (AGI). Thus, researchers have dedicated significant effort to diverse implementations for them. Benefiting from recent progress in large language models…

Artificial Intelligence · Computer Science 2024-01-09 Yuheng Cheng , Ceyao Zhang , Zhengwen Zhang , Xiangrui Meng , Sirui Hong , Wenhao Li , Zihao Wang , Zekai Wang , Feng Yin , Junhua Zhao , Xiuqiang He

Reinforcement learning is increasingly used to transform large language models into agentic systems that act over long horizons, invoke tools, and manage memory under partial observability. While recent work has demonstrated performance…

Cryptography and Security · Computer Science 2026-01-01 Ken Huang , Jerry Huang

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

Power is a key concept in AI safety: power-seeking as an instrumental goal, sudden or gradual disempowerment of humans, power balance in human-AI interaction and international AI governance. At the same time, power as the ability to pursue…

Artificial Intelligence · Computer Science 2025-08-06 Jobst Heitzig , Ram Potham