Related papers: Overeager Coding Agents: Measuring Out-of-Scope Ac…
A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We call this overeager behavior: the prompt is not adversarial and…
Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…
As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…
AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decisions that are invisible in the source code alone. We introduce a controlled benchmark…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…
As Model Context Protocol adoption grows, securing tool invocations via meaningful user consent has become a critical challenge, as existing methods, broad always allow toggles or opaque LLM-based decisions, fail to account for dangerous…
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks,…
As language agents increasingly automate critical tasks, their ability to follow domain-specific standard operating procedures (SOPs), policies, and constraints when taking actions and making tool calls becomes essential yet remains…
Despite coding agents' advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to…
Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on…
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…
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation,…
As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…
As data-science agents shift from co-pilots to auto-pilots, silent misframing becomes a critical failure mode. Agents quietly commit to plausible but unintended task framings, producing clean, executable artifacts that hide their incorrect…
Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…
Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts. However,…
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this…
Graphical User Interface (GUI) agents have the potential to assist users in interacting with complex software (e.g., PowerPoint, Photoshop). While prior research has primarily focused on automating user actions through clicks and…
Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…