English
Related papers

Related papers: Why Does Agentic Safety Fail to Generalize Across …

200 papers

Large Language Model (LLM)-based agents have emerged as a new paradigm that extends LLMs' capabilities beyond text generation to dynamic interaction with external environments. By integrating reasoning with perception, memory, and tool use,…

Artificial Intelligence · Computer Science 2025-09-23 Minxing Zhang , Yi Yang , Roy Xie , Bhuwan Dhingra , Shuyan Zhou , Jian Pei

Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) have significantly automated data science workflows, but a fundamental…

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

There is a growing focus on how to design safe artificial intelligent (AI) agents. As systems become more complex, poorly specified goals or control mechanisms may cause AI agents to engage in unwanted and harmful outcomes. Thus it is…

Artificial Intelligence · Computer Science 2017-01-09 Mark Muraven

We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration,…

Machine Learning · Computer Science 2017-11-29 Jan Leike , Miljan Martic , Victoria Krakovna , Pedro A. Ortega , Tom Everitt , Andrew Lefrancq , Laurent Orseau , Shane Legg

Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. In particular, policies learned using reinforcement learning often fail to generalize to novel…

Robotics · Computer Science 2023-04-04 Kai-Chieh Hsu , Allen Z. Ren , Duy Phuong Nguyen , Anirudha Majumdar , Jaime F. Fisac

Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments…

Artificial Intelligence · Computer Science 2019-02-20 Christopher Frye , Ilya Feige

While it is still unclear if agents with Artificial General Intelligence (AGI) could ever be built, we can already use mathematical models to investigate potential safety systems for these agents. We present an AGI safety layer that creates…

Artificial Intelligence · Computer Science 2020-07-13 Koen Holtman

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

Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large…

Machine Learning · Computer Science 2025-09-23 Jeffrey Yang Fan Chiang , Seungjae Lee , Jia-Bin Huang , Furong Huang , Yizheng Chen

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

AI safety and alignment research has predominantly been focused on methods for safeguarding individual AI systems, resting on the assumption of an eventual emergence of a monolithic Artificial General Intelligence (AGI). The alternative AGI…

Artificial Intelligence · Computer Science 2026-05-20 Nenad Tomašev , Matija Franklin , Julian Jacobs , Sébastien Krier , Simon Osindero

Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main…

Artificial Intelligence · Computer Science 2025-11-19 Sushant Mehta

The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse)…

Artificial Intelligence · Computer Science 2023-05-31 Catalin Mitelut , Ben Smith , Peter Vamplew

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex…

Cryptography and Security · Computer Science 2026-03-13 Juhee Kim , Xiaoyuan Liu , Zhun Wang , Shi Qiu , Bo Li , Wenbo Guo , Dawn Song

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Artificial Intelligence · Computer Science 2026-05-20 Qiqi Liu , Thorsten Holz , Shilin Ye , Runhan Song

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Cryptography and Security · Computer Science 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

AI-based systems have been used widely across various industries for different decisions ranging from operational decisions to tactical and strategic ones in low- and high-stakes contexts. Gradually the weaknesses and issues of these…

Human-Computer Interaction · Computer Science 2022-01-13 Morteza Saberi

AI agents are increasingly used in consumer-facing applications to assist with tasks such as product search, negotiation, and transaction execution. In this paper, we explore a future scenario where both consumers and merchants authorize AI…

Artificial Intelligence · Computer Science 2025-09-23 Shenzhe Zhu , Jiao Sun , Yi Nian , Tobin South , Alex Pentland , Jiaxin Pei

The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM…

Artificial Intelligence · Computer Science 2025-06-24 Yingxuan Yang , Huacan Chai , Yuanyi Song , Siyuan Qi , Muning Wen , Ning Li , Junwei Liao , Haoyi Hu , Jianghao Lin , Gaowei Chang , Weiwen Liu , Ying Wen , Yong Yu , Weinan Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›