English
Related papers

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

200 papers

Corrigibility is a safety property for artificially intelligent agents. A corrigible agent will not resist attempts by authorized parties to alter the goals and constraints that were encoded in the agent when it was first started. This…

Artificial Intelligence · Computer Science 2020-04-06 Koen Holtman

The AI community has been exploring a pathway to artificial general intelligence (AGI) by developing "language agents", which are complex large language models (LLMs) pipelines involving both prompting techniques and tool usage methods.…

An artificial general intelligence (AGI) might have an instrumental drive to modify its utility function to improve its ability to cooperate, bargain, promise, threaten, and resist and engage in blackmail. Such an AGI would necessarily have…

General Finance · Quantitative Finance 2020-03-03 James D. Miller , Roman Yampolskiy , Olle Häggström

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…

Artificial Intelligence · Computer Science 2025-08-11 Bo Wen

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

Cryptography and Security · Computer Science 2024-12-19 Yifeng He , Ethan Wang , Yuyang Rong , Zifei Cheng , Hao Chen

Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains. We say that an AI is made Artificially Stupid on a task when some limitations are deliberately introduced to match a human's ability to do the…

Artificial Intelligence · Computer Science 2018-08-14 Michaël Trazzi , Roman V. Yampolskiy

Rational agents are usually built to maximize rewards. However, AGI agents can find undesirable ways of maximizing any prior reward function. Therefore value learning is crucial for safe AGI. We assume that generalized states of the world…

Artificial Intelligence · Computer Science 2013-08-06 Alexey Potapov , Sergey Rodionov

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…

Cryptography and Security · Computer Science 2025-03-04 Ishaan Domkundwar , Mukunda N S , Ishaan Bhola , Riddhik Kochhar

Graphical user interface (GUI) agents have advanced rapidly but still struggle with complex tasks involving novel UI elements, long-horizon actions, and personalized trajectories. In this work, we introduce Instruction Agent, a GUI agent…

Artificial Intelligence · Computer Science 2025-09-10 Yinheng Li , Hailey Hultquist , Justin Wagle , Kazuhito Koishida

The complexity of dynamics in AI techniques is already approaching that of complex adaptive systems, thus curtailing the feasibility of formal controllability and reachability analysis in the context of AI safety. It follows that the…

Artificial Intelligence · Computer Science 2018-05-24 Vahid Behzadan , Arslan Munir , Roman V. Yampolskiy

Artificial General Intelligence (AGI), widely regarded as the fundamental goal of artificial intelligence, represents the realization of cognitive capabilities that enable the handling of general tasks with human-like proficiency.…

Neural and Evolutionary Computing · Computer Science 2024-12-13 Bo Yu , Jiangning Wei , Minzhen Hu , Zejie Han , Tianjian Zou , Ye He , Jun Liu

The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be,…

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…

Hardware Architecture · Computer Science 2025-11-13 Eren Kurshan , Yuan Xie , Paul Franzon

Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough to significantly harm humanity. We identify four areas of…

Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…

Cryptography and Security · Computer Science 2025-06-24 Sunil Kumar Jang Bahadur , Gopala Dhar

Progress toward Artificial General Intelligence (AGI) faces significant bottlenecks, particularly in rigorously evaluating complex interactive systems and acquiring the vast interaction data needed for training adaptive agents. This paper…

Artificial Intelligence · Computer Science 2025-09-25 Krisztian Balog , ChengXiang Zhai

The development of Artificial General Intelligence (AGI) promises to be a major event. Along with its many potential benefits, it also raises serious safety concerns (Bostrom, 2014). The intention of this paper is to provide an easily…

Artificial Intelligence · Computer Science 2018-05-22 Tom Everitt , Gary Lea , Marcus Hutter

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Cryptography and Security · Computer Science 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…

Artificial Intelligence · Computer Science 2026-05-19 Ashwin Aravind

The AI safety literature is full of examples of powerful AI agents that, in blindly pursuing a specific and usually narrow objective, ends up with unacceptable and even catastrophic collateral damage to others. In this paper, we consider…

Artificial Intelligence · Computer Science 2025-04-15 Kee Siong Ng , Samuel Yang-Zhao , Timothy Cadogan-Cowper
‹ Prev 1 2 3 10 Next ›