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

Existing web agents typically initiate exploration from the root URL, which is inefficient for complex websites with deep hierarchical structures. Without a global view of the website's structure, agents frequently fall into navigation…

In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where…

Browser agents built on LLMs can act in web interfaces, yet most remain confined to a single chat surface (e.g., a sidebar). This mismatch with real browsing can increase context-switching and reduce user control. We introduce…

Since the advent of large language models, prompt engineering now enables the rapid, low-effort creation of diverse autonomous agents that are already in widespread use. Yet this convenience raises urgent concerns about the safety,…

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform malicious actions leading to failures or malicious…

Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior…

In this paper, we study the use of deception for strategic planning in adversarial environments. We model the interaction between the agent (player 1) and the adversary (player 2) as a two-player concurrent game in which the adversary has…

Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks…

Model merging for Large Language Models (LLMs) directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. However, due to potential vulnerabilities in models available on…

Safe navigation is essential for autonomous systems operating in hazardous environments. Traditional planning methods excel at long-horizon tasks but rely on a predefined graph with fixed distance metrics. In contrast, safe Reinforcement…

Website Fingerprinting (WFP) uses deep learning models to classify encrypted network traffic to infer visited websites. While historically effective, prior methods fail to generalize to modern web environments. Single-page applications…

With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The…

Deceptive UI designs, widely instantiated across the web and commonly known as dark patterns, manipulate users into performing actions misaligned with their goals. In this paper, we show that dark patterns are highly effective in steering…

Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an underexplored attack surface: an adversary who injects…

Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because raw data remain local. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for…

Assistive embodied agents that can be instructed in natural language to perform tasks in open-world environments have the potential to significantly impact labor tasks like manufacturing or in-home care -- benefiting the lives of those who…

Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates…

Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon…

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…

Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost…