Related papers: Auditing Agent Harness Safety

We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record (EHR) environments. Existing medical agent benchmarks primarily focus on static…

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…

Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their…

LLM-based agents have emerged as promising tools, which are crafted to fulfill complex tasks by iterative planning and action. However, these agents are susceptible to undesired planning hallucinations when lacking specific knowledge for…

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

The rapid deployment of Large language model (LLM) agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standardized evaluation benchmarks for these agents in dynamic…

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…

Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through specialist roles, peer review and consensus formation. In clinical decision support, however,…

Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents, leaving multi-agent risks such as coordination failure and conflict…

We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…

Coding agents, which are LLM-driven agents specialized in software development, have become increasingly prevalent in modern programming environments. Unlike traditional AI coding assistants, which offer simple code completion and…

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…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…

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…

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly…

Large language model (LLM) agents are increasingly expected to operate in enterprise environments, where work is distributed across specialized roles, permission-controlled systems, and cross-departmental procedures. However, existing…

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…