Related papers: "What Did It Actually Do?": Understanding Risk Awa…
Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…
AI agents plan and execute interactions in open-ended environments. For example, OpenAI's Operator can use a web browser to do product comparisons and buy online goods. Much research on making agents useful and safe focuses on directly…
The rapid deployment of autonomous AI agents creates urgent challenges around authorization, accountability, and access control in digital spaces. New standards are needed to know whom AI agents act on behalf of and guide their use…
Software systems are ubiquitous, and their use is ingrained in our everyday lives. They enable us to get in touch with people quickly and easily, support us in gathering information, and help us perform our daily tasks. In return, we…
Chatbots shifted from rule-based to artificial intelligence techniques and gained traction in medicine, shopping, customer services, food delivery, education, and research. OpenAI developed ChatGPT blizzard on the Internet as it crossed one…
Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents. A representative scenario is in software development, where LLM agents demonstrate…
Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously from start to finish, yet this process remains effectively…
Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…
The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…
Natural Language Generation tools, such as chatbots that can generate human-like conversational text, are becoming more common both for personal and professional use. However, there are concerns about their trustworthiness and ethical…
Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats,…
Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from…
As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…
Thanks to advances in large language models, a new type of software agent, the artificial intelligence (AI) agent, has entered the marketplace. Companies such as OpenAI, Google, Microsoft, and Salesforce promise their AI Agents will go from…
AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety…
Each year, thousands of software vulnerabilities are discovered and reported to the public. Unpatched known vulnerabilities are a significant security risk. It is imperative that software vendors quickly provide patches once vulnerabilities…
Artificial intelligence systems increasingly involve continual learning to enable flexibility in general situations that are not encountered during system training. Human interaction with autonomous systems is broadly studied, but research…
Chatbots are increasingly integrated into people's lives and are widely used to help people. Recently, there has also been growing interest in the reverse direction-humans help chatbots-due to a wide range of benefits including better…
As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…