English
Related papers

Related papers: SafePred: A Predictive Guardrail for Computer-Usin…

200 papers

Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…

Artificial Intelligence · Computer Science 2025-06-06 Artem Latyshev , Gregory Gorbov , Aleksandr I. Panov

Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrails mostly perform post-hoc detection that may expose unsafe…

Machine Learning · Computer Science 2025-10-14 Xiaodan Li , Mengjie Wu , Yao Zhu , Yunna Lv , YueFeng Chen , Cen Chen , Jianmei Guo , Hui Xue

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

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…

Machine Learning · Computer Science 2022-06-15 Alexandra Kearney , Anna Koop , Johannes Günther , Patrick M. Pilarski

We study a repeated Principal Agent problem between a long lived Principal and Agent pair in a prior free setting. In our setting, the sequence of realized states of nature may be adversarially chosen, the Agent is non-myopic, and the…

Computer Science and Game Theory · Computer Science 2023-11-15 Natalie Collina , Aaron Roth , Han Shao

Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain…

Cryptography and Security · Computer Science 2026-04-28 Yixiang Zhang , Xinhao Deng , Jiaqing Wu , Yue Xiao , Ke Xu , Qi Li

Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag…

Cryptography and Security · Computer Science 2026-04-29 Lijia Lv , Xuehai Tang , Jie Wen , Jizhong Han , Songlin Hu

Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and…

Artificial Intelligence · Computer Science 2026-02-05 Gonzalo Gonzalez-Pumariega , Vincent Tu , Chih-Lun Lee , Jiachen Yang , Ang Li , Xin Eric Wang

We discuss the feasibility of predicting, managing and subsequently manipulating, the future evolution of a Complex Adaptive System. Our archetypal system mimics a population of adaptive, interacting objects, such as those arising in the…

Physics and Society · Physics 2007-05-23 David M. D. Smith , Neil F. Johnson

Securing Agentic Artificial Intelligence (AI) systems requires addressing the complex cyber risks introduced by autonomous, decision-making, and adaptive behaviors. Agentic AI systems are increasingly deployed across industries,…

Cryptography and Security · Computer Science 2025-12-23 Sunil Arora , John Hastings

Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Blind Goal-Directedness (BGD): a bias to pursue goals…

Proactive agents must decide not only what to say but also whether and when to intervene. Many current systems rely on brittle heuristics or indiscriminate long reasoning, which offers little control over the benefit-burden tradeoff. We…

Artificial Intelligence · Computer Science 2026-02-03 Yuxuan Fu , Xiaoyu Tan , Teqi Hao , Chen Zhan , Xihe Qiu

In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over…

Computation and Language · Computer Science 2026-04-07 Pride Kavumba , Koki Wataoka , Huy H. Nguyen , Jiaxuan Li , Masaya Ohagi

In this paper, we present an end-to-end future-prediction model that focuses on pedestrian safety. Specifically, our model uses previous video frames, recorded from the perspective of the vehicle, to predict if a pedestrian will cross in…

Computer Vision and Pattern Recognition · Computer Science 2020-03-18 Mohamed Chaabane , Ameni Trabelsi , Nathaniel Blanchard , Ross Beveridge

Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data or with low-rank adaptation, pre-trained safety behaviors are…

Artificial Intelligence · Computer Science 2025-10-28 Bingjie Zhang , Yibo Yang , Zhe Ren , Dandan Guo , Jindong Gu , Philip Torr , Bernard Ghanem

Safety is one of the biggest concerns to applying reinforcement learning (RL) to the physical world. In its core part, it is challenging to ensure RL agents persistently satisfy a hard state constraint without white-box or black-box…

Robotics · Computer Science 2023-10-19 Weiye Zhao , Tairan He , Changliu Liu

Metaverse is trending to create a digital circumstance that can transfer the real world to an online platform supported by large quantities of real-time interactions. Pre-trained Artificial Intelligence (AI) models are demonstrating their…

Cryptography and Security · Computer Science 2024-01-05 Pengfei Li , Zhibo Zhang , Ameena S. Al-Sumaiti , Naoufel Werghi , Chan Yeob Yeun

While learning-based control techniques often outperform classical controller designs, safety requirements limit the acceptance of such methods in many applications. Recent developments address this issue through so-called predictive safety…

Systems and Control · Electrical Eng. & Systems 2022-05-16 Kim P. Wabersich , Melanie N. Zeilinger

Reactive collision avoidance is essential for agile robots navigating complex and dynamic environments, enabling real-time obstacle response. However, this task is inherently challenging because it requires a tight integration of…

Robotics · Computer Science 2025-06-06 Alessandro Saviolo , Niko Picello , Jeffrey Mao , Rishabh Verma , Giuseppe Loianno

We present an interpretable framework for path prediction that leverages dependencies between agents' behaviors and their spatial navigation environment. We exploit two sources of information: the past motion trajectory of the agent of…

Computer Vision and Pattern Recognition · Computer Science 2018-08-01 Amir Sadeghian , Ferdinand Legros , Maxime Voisin , Ricky Vesel , Alexandre Alahi , Silvio Savarese
‹ Prev 1 8 9 10 Next ›