相关论文: Auditing Agent Harness Safety

This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer that governs context construction, tool interaction,…

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…

We read twelve well-known LLM agent benchmark papers and recorded, dimension by dimension, what each paper actually says about how its evaluation was run. The motivation came from a familiar frustration: two papers will report results on…

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic…

Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy. We argue that accuracy metrics and return-based scores provide an illusion of reliability,…

Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order…

Autonomous agents powered by large language models (LLMs) are increasingly deployed in real-world applications requiring complex, long-horizon workflows. However, existing benchmarks predominantly focus on atomic tasks that are…

LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is whether those actions…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework…

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.…

Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing…

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…

Large language model (LLM)-based techniques have achieved notable progress in generating harnesses for program fuzzing. However, applying them to arbitrary functions (especially internal functions) \textit{at scale} remains challenging due…

The advances made by Large Language Models (LLMs) have led to the pursuit of LLM agents that can solve intricate, multi-step reasoning tasks. As with any research pursuit, benchmarking and evaluation are key corner stones to efficient and…

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…

We introduce WorkBench: a benchmark dataset for evaluating agents' ability to execute tasks in a workplace setting. WorkBench contains a sandbox environment with five databases, 26 tools, and 690 tasks. These tasks represent common business…