English
Related papers

Related papers: When Actions Go Off-Task: Detecting and Correcting…

200 papers

This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social environment where agents are deployed, either collaborative,…

Artificial Intelligence · Computer Science 2025-06-09 Florian Carichon , Aditi Khandelwal , Marylou Fauchard , Golnoosh Farnadi

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…

Artificial Intelligence · Computer Science 2026-05-29 Yibing Liu , Yangze Liu , Xiaolong Yin , Bin Wang , Chong Zhang , Hao Yin , Zhongyi Han

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…

Machine Learning · Computer Science 2025-04-15 Aryan Bhatt , Cody Rushing , Adam Kaufman , Tyler Tracy , Vasil Georgiev , David Matolcsi , Akbir Khan , Buck Shlegeris

For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics. However, the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Guoqiang Wei , Cuiling Lan , Wenjun Zeng , Zhibo Chen

Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and…

Artificial Intelligence · Computer Science 2026-02-18 Zhouzhou Shen , Xueyu Hu , Xiyun Li , Tianqing Fang , Juncheng Li , Shengyu Zhang

Emergent effects can arise in multi-agent systems (MAS) where execution is decentralized and reliant on local information. These effects may range from minor deviations in behavior to catastrophic system failures. To formally define these…

Multiagent Systems · Computer Science 2024-08-09 Philipp Altmann , Julian Schönberger , Steffen Illium , Maximilian Zorn , Fabian Ritz , Tom Haider , Simon Burton , Thomas Gabor

Graphical User Interface (GUI) agents extend large language models from text generation to action execution in real-world digital environments. Unlike conversational systems, GUI agents perform irreversible operations such as submitting…

Machine Learning · Computer Science 2026-02-25 Yucheng Shi , Wenhao Yu , Jingyuan Huang , Wenlin Yao , Wenhu Chen , Ninghao Liu

Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that their predictions are reliable under the actions they condition on. Existing benchmarks…

Artificial Intelligence · Computer Science 2026-05-29 Tianzhuo Yang , Zihan Shen , Zirui Mi , Zhaoyi Zhang , Jiayi Zhou , Jiaming Ji , Juntao Dai , Jiawei Chen , Boyuan Chen , Yaodong Yang

A computational workflow, also known as workflow, consists of tasks that are executed in a certain order to attain a specific computational campaign. Computational workflows are commonly employed in science domains, such as physics,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-13 Krishnan Raghavan , George Papadimitriou , Hongwei Jin , Anirban Mandal , Mariam Kiran , Prasanna Balaprakash , Ewa Deelman

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating…

Artificial Intelligence · Computer Science 2026-05-01 Jinchao Li , Yunxin Li , Chenrui Zhao , Zhenran Xu , Baotian Hu , Min Zhang

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

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of…

Computation and Language · Computer Science 2026-04-30 Ada Chen , Yongjiang Wu , Junyuan Zhang , Jingyu Xiao , Shu Yang , Jen-tse Huang , Kun Wang , Wenxuan Wang , Shuai Wang

Computer Using Agents (CUAs) are increasingly equipped with external tools, enabling them to perform complex and realistic tasks. For CUAs to operate effectively, application selection, which refers to deciding which application to use…

Adversarial machine learning attacks on video action recognition models is a growing research area and many effective attacks were introduced in recent years. These attacks show that action recognition models can be breached in many ways.…

Cryptography and Security · Computer Science 2024-04-18 Furkan Mumcu , Yasin Yilmaz

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites…

Software Engineering · Computer Science 2026-05-19 Yubin Qu , Ying Zhang , Yanjun Zhang , Gelei Deng , Yuekang Li , Leo Yu Zhang , Yi Liu

Advancements in multimodal foundation models have enabled the development of Computer Use Agents (CUAs) capable of autonomously interacting with GUI environments. As CUAs are not restricted to certain tools, they allow to automate more…

Machine Learning · Computer Science 2026-04-10 Dominik Seip , Matthias Hein

As LLM agents grow more capable of causing harm autonomously, AI developers will rely on increasingly sophisticated control measures to prevent possibly misaligned agents from causing harm. AI developers could demonstrate that their control…

Artificial Intelligence · Computer Science 2025-04-08 Tomek Korbak , Mikita Balesni , Buck Shlegeris , Geoffrey Irving

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

‹ Prev 1 3 4 5 6 7 10 Next ›