Related papers: HINTBench: Horizon-agent Intrinsic Non-attack Traj…
The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers introduces substantial unintentional behavioral safety risks.…
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…
Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks…
Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an important problem, since it helps us determine whether the agent successfully completed the tasks.…
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…
We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation,…
Data analytics is essential for extracting valuable insights from data that can assist organizations in making effective decisions. We introduce InsightBench, a benchmark dataset with three key features. First, it consists of 100 datasets…
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…
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…
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when…
As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time action verification. Current frameworks like AgentBench…
LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…
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…
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…
LLM agents are emerging as a key enabler for autonomous wireless network management. Reliably deploying them, however, demands benchmarks that reflect real engineering risk. Existing wireless benchmarks evaluate single isolated capabilities…
Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…
Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…