Related papers: WebTrap: Stealthy Mid-Task Hijacking of Browser Ag…

Robotic systems are nowadays capable of solving complex navigation tasks. However, their capabilities are limited to the knowledge of the designer and consequently lack generalizability to initially unconsidered situations. This makes deep…

With the continuous improvement of attack methods, there are more and more distributed, complex, targeted attacks in which the attackers use combined attack methods to achieve the purpose. Advanced cyber attacks include multiple stages to…

AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…

To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare, complex, and sometimes even adversarially hidden and only detectable when multiple traces are…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

With web applications becoming a preferred method of presenting graphical user interfaces to users, software vulnerabilities affecting web applications are becoming more and more prevalent and devastating. Some of these vulnerabilities,…

Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detailed reports. However, the misuse of LLMs with such powerful…

Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic autonomy, it…

Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The harmful…

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

While much work on web agents emphasizes the promise of autonomously performing tasks on behalf of users, in reality, agents often fall short on complex tasks in real-world contexts and modeling user preference. This presents an opportunity…

Similar to what happens between humans in the real world, in open multi-agent systems distributed over the Internet, such as online social networks or wiki technologies, agents often form coalitions by agreeing to act as a whole in order to…

Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents…

Joint caching and transmission optimization problem is challenging due to the deep coupling between decisions. This paper proposes an iterative distributed multi-agent learning approach to jointly optimize caching and transmission. The goal…

Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like $\pi_0$ showing great promise in generating smooth, continuous actions. As these models advance, their unique action generation…

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making…

This research builds on work in anticipatory human-machine interaction, a subfield of human-machine interaction where machines can facilitate advantageous interactions by anticipating a user's future state. The aim of this research is to…

The goal of Multi-Agent Path Finding (MAPF) is to find a set of paths for a fleet of agents moving in a shared environment such that the agents reach their goals without colliding with each other. In practice, some of the robots executing…

Embodied agents in vision navigation coupled with deep neural networks have attracted increasing attention. However, deep neural networks have been shown vulnerable to malicious adversarial noises, which may potentially cause catastrophic…

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…