相关论文: Auditing Agent Harness Safety
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…
Healthcare administration accounts for over $1 trillion in annual spending, making it a promising target for LLM-based computer-use agents (CUAs). While clinical applications of LLMs have received significant attention, no benchmark exists…
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…
The rise of LLM-based agents has opened new frontiers in AI applications, yet evaluating these agents remains a complex and underdeveloped area. This survey provides an in-depth overview of the emerging field of LLM agent evaluation,…
The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of…
Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…
The rise of large language model (LLM)-based multi-agent systems (MAS) introduces new security and reliability challenges. While these systems show great promise in decomposing and coordinating complex tasks, they also face multi-faceted…
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…
As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations in a lack of external feedback, these agents struggle with…
LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain largely centered on static, isolated, and short-horizon benchmarks that fail to capture…
The rise of LLM-based agents shows great potential to revolutionize task planning, capturing significant attention. Given that these agents will be integrated into high-stake domains, ensuring their reliability and safety is crucial. This…
With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…
LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation protocols primarily focus on task success, overlooking a critical aspect of agent…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…
We address the problem of runtime trajectory anomaly detection, a critical capability for enabling trustworthy LLM agents. Current safety measures predominantly focus on static input/output filtering. However, we argue that ensuring LLM…
As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trustworthy deployment in…
Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across…
LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal…
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…
The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…