Related papers: Atomicity for Agents: Exposing, Exploiting, and Mi…
Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…
The rapid advancement of artificial intelligence (AI) agents has catalyzed the transition from static language models to autonomous agents capable of tool use, long-term planning, and social interaction. $\textbf{Moltbook}$, the first…
Tool-Based Agent Systems (TBAS) allow Language Models (LMs) to use external tools for tasks beyond their standalone capabilities, such as searching websites, booking flights, or making financial transactions. However, these tools greatly…
The rapid adoption of AI coding agents and AI assistant web services is fundamentally changing how developers discover, consume, and interact with technical documentation. This paper studies that transformation across three interconnected…
ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a…
Unlike traditional automation tools or static LLM-based systems, agents combine decision-making and tool utilization to accomplish complex tasks, showing great potential in software engineering. However, existing studies largely focus on…
The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes? We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that…
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…
World wide technological advancement has brought in a widespread change in adoption and utilization of open source tools. Since, most of the organizations across the globe deal with a large amount of data to be updated online and…
While Graphical User Interface (GUI) agents have shown promising performance in automated device interaction, they primarily depend on static parametric knowledge from pre-training or instruction tuning. This reliance fundamentally limits…
Timing attacks have been a continuous threat to users' privacy in modern browsers. To mitigate such attacks, existing approaches, such as Tor Browser and Fermata, add jitters to the browser clock so that an attacker cannot accurately…
With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent-based project-level code synthesis. Existing benchmarks rely on idealized assumptions,…
Graphical User Interface (GUI) agents are increasingly deployed to interact with online web services, yet their exposure to open-world content renders them vulnerable to Environmental Injection Attacks (EIAs). In these attacks, an attacker…
Browser-using agents (BUAs) are an emerging class of AI agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online…
Temporal progression is an integral part of knowledge accumulation and update. Web search is frequently adopted as grounding for agent knowledge, yet an improper configuration affects the quality of the agent's responses. Here, we assess…
Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…
Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines…
Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enhance computer workflows. While existing research focuses on online settings, desktop environments,…
Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain…
Website hacking is a frequent attack type used by malicious actors to obtain confidential information, modify the integrity of web pages or make websites unavailable. The tools used by attackers are becoming more and more automated and…