English
Related papers

Related papers: Self-Attribution Bias: When AI Monitors Go Easy on…

200 papers

Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them - attack selection - is particularly concerning. To study this, we let a red team…

Cryptography and Security · Computer Science 2026-04-17 Joachim Schaeffer , Arjun Khandelwal , Tyler Tracy

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection (IPI) attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought (CoT) and tool-use actions to…

Cryptography and Security · Computer Science 2026-02-26 Jafar Isbarov , Murat Kantarcioglu

In distributed processing, agents generally collect data generated by the same underlying unknown model (represented by a vector of parameters) and then solve an estimation or inference task cooperatively. In this paper, we consider the…

Information Theory · Computer Science 2015-06-16 Sheng-Yuan Tu , Ali H. Sayed

Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…

Artificial Intelligence · Computer Science 2025-11-04 Yuhang Huang , Zekai Lin , Fan Zhong , Lei Liu

Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions and handle inputs…

Cryptography and Security · Computer Science 2026-01-16 Nadya Abaev , Denis Klimov , Gerard Levinov , David Mimran , Yuval Elovici , Asaf Shabtai

The usage of automated learning agents is becoming increasingly prevalent in many online economic applications such as online auctions and automated trading. Motivated by such applications, this paper is dedicated to fundamental modeling…

Computer Science and Game Theory · Computer Science 2023-01-04 Yoav Kolumbus , Noam Nisan

The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. In many real-world applications, the agents can only acquire a…

Artificial Intelligence · Computer Science 2019-10-10 Mingyang Geng , Kele Xu , Yiying Li , Shuqi Liu , Bo Ding , Huaimin Wang

While automated driving is often advertised with better-than-human driving performance, this work reviews that it is nearly impossible to provide direct statistical evidence on the system level that this is actually the case. The amount of…

Machine Learning · Computer Science 2021-12-10 Hanno Gottschalk , Matthias Rottmann , Maida Saltagic

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…

When users perceive AI systems as mindful, independent agents, they hold them responsible instead of the AI experts who created and designed these systems. So far, it has not been studied whether explanations support this shift in…

Artificial Intelligence · Computer Science 2023-12-20 Susanne Hindennach , Lei Shi , Filip Miletić , Andreas Bulling

Artificial intelligence (AI) assistants are increasingly embedded in workplace tools, raising the question of how initiative-taking shapes adoption. Prior work highlights trust and expectation mismatches as barriers, but the underlying…

Human-Computer Interaction · Computer Science 2026-04-28 Dana Harari , Ofra Amir

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…

Cryptography and Security · Computer Science 2026-05-19 Sahar Abdelnabi , Eugene Bagdasarian

Self-modification of agents embedded in complex environments is hard to avoid, whether it happens via direct means (e.g. own code modification) or indirectly (e.g. influencing the operator, exploiting bugs or the environment). It has been…

Artificial Intelligence · Computer Science 2021-01-19 Jakub Tětek , Marek Sklenka , Tomáš Gavenčiak

The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human oversight is expensive, one approach is trusted monitoring,…

Cryptography and Security · Computer Science 2026-02-12 Ashwin Sreevatsa , Sebastian Prasanna , Cody Rushing

Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended…

Neurons and Cognition · Quantitative Biology 2025-06-13 Lin Chen , Yunke Zhang , Jie Feng , Haoye Chai , Honglin Zhang , Bingbing Fan , Yibo Ma , Shiyuan Zhang , Nian Li , Tianhui Liu , Nicholas Sukiennik , Keyu Zhao , Yu Li , Ziyi Liu , Fengli Xu , Yong Li

Active learning is a powerful tool when labelling data is expensive, but it introduces a bias because the training data no longer follows the population distribution. We formalize this bias and investigate the situations in which it can be…

Machine Learning · Statistics 2021-06-01 Sebastian Farquhar , Yarin Gal , Tom Rainforth

Agentic AI shifts the investor's role from analytical execution to oversight. We present an agentic strategic asset allocation pipeline in which approximately 50 specialized agents produce capital market assumptions, construct portfolios…

Artificial Intelligence · Computer Science 2026-04-03 Andrew Ang , Nazym Azimbayev , Andrey Kim

Proactive AI writing assistants need to predict when users want drafting help, yet we lack empirical understanding of what drives preferences. Through a factorial vignette study with 50 participants making 750 pairwise comparisons, we find…

Computation and Language · Computer Science 2026-01-09 Vivian Lai , Zana Buçinca , Nil-Jana Akpinar , Mo Houtti , Hyeonsu B. Kang , Kevin Chian , Namjoon Suh , Alex C. Williams

AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks…

Artificial Intelligence · Computer Science 2025-02-24 Peter Cihon , Merlin Stein , Gagan Bansal , Sam Manning , Kevin Xu

Due to the widespread use of data-powered systems in our everyday lives, the notions of bias and fairness gained significant attention among researchers and practitioners, in both industry and academia. Such issues typically emerge from the…

Information Retrieval · Computer Science 2021-10-27 Gianluca Demartini , Kevin Roitero , Stefano Mizzaro