Related papers: SusBench: An Online Benchmark for Evaluating Dark …
Modern web agents possess computer use abilities that allow them to interact with webpages by sending commands to a virtual keyboard and mouse. While such agents have considerable potential to assist human users with complex tasks,…
While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce…
Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why…
Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…
Technologies increasingly mimic human-like social behaviours. Beyond prototypical conversational agents like chatbots, this also applies to basic automated systems like app notifications or self-checkout machines that address or 'talk to'…
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces…
As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic…
Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused…
Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in…
The quality of datasets plays an increasingly crucial role in the research and development of modern artificial intelligence (AI). Despite the proliferation of open dataset platforms nowadays, data quality issues, such as incomplete…
As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise for detecting…
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,…
Deceptive patterns (DPs) are user interface designs deliberately crafted to manipulate users into unintended decisions, often by exploiting cognitive biases for the benefit of companies or services. While numerous studies have explored ways…
We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with…
Millions of users now design personalized LLM-based chatbots that shape their daily interactions, yet they can only roughly anticipate how their design choices will manifest as behaviors in deployment. This opacity is consequential:…
This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants. As what we believe to be the most extensive unified cybersecurity safety…
As Large Language Models (LLMs) and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are…