English
Related papers

Related papers: Auditing Agent Harness Safety

200 papers

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Cryptography and Security · Computer Science 2025-02-17 Jizhou Chen , Samuel Lee Cong

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Artificial Intelligence · Computer Science 2026-01-15 Logan Ritchie , Sushant Mehta , Nick Heiner , Mason Yu , Edwin Chen

Modern work relies on an assortment of digital collaboration tools, yet routine processes continue to suffer from human error and delay. To address this gap, this dissertation extends TheAgentCompany with a finance-focused environment and…

Artificial Intelligence · Computer Science 2025-12-03 Rory Milsom

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,…

Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. Despite this, these LLM agents introduce unexpected safety risks when operating in interactive environments.…

Computation and Language · Computer Science 2024-10-08 Tongxin Yuan , Zhiwei He , Lingzhong Dong , Yiming Wang , Ruijie Zhao , Tian Xia , Lizhen Xu , Binglin Zhou , Fangqi Li , Zhuosheng Zhang , Rui Wang , Gongshen Liu

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Cryptography and Security · Computer Science 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…

Information Retrieval · Computer Science 2026-04-10 Maria Movin , Claudia Hauff , Aron Henriksson , Panagiotis Papapetrou

LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long before they surface in the final outcome. Reactive auditing is therefore insufficient:…

Computation and Language · Computer Science 2026-05-28 Jiaqian Li , Yanshu Li , Boxuan Zhang , Ruixiang Tang , Kuan-Hao Huang

Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise…

Cryptography and Security · Computer Science 2025-07-16 Ronny Ko , Jiseong Jeong , Shuyuan Zheng , Chuan Xiao , Tae-Wan Kim , Makoto Onizuka , Won-Yong Shin

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

Computers and Society · Computer Science 2026-02-24 Nelu D. Radpour

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinement framework designed…

Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy is designed to improve their health outcomes and reduce safety risks. Some large language models (LLMs) have…

Computation and Language · Computer Science 2025-07-30 Kaixuan Wang , Chenxin Diao , Jason T. Jacques , Zhongliang Guo , Shuai Zhao

Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to…

Computation and Language · Computer Science 2026-05-19 Linyue Pan , Lexiao Zou , Shuo Guo , Jingchen Ni , Hai-Tao Zheng

Existing benchmarks for tool-using LLM agents primarily report single-run success rates and miss reliability properties required in production. We introduce \textbf{ReliabilityBench}, a benchmark for evaluating agent reliability across…

Artificial Intelligence · Computer Science 2026-01-13 Aayush Gupta

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…

Artificial Intelligence · Computer Science 2025-08-05 Chaojia Yu , Zihan Cheng , Hanwen Cui , Yishuo Gao , Zexu Luo , Yijin Wang , Hangbin Zheng , Yong Zhao

Artificial intelligence is increasingly catalyzing scientific automation, with multimodal large language model (MLLM) agents evolving from lab assistants into self-driving lab operators. This transition imposes stringent safety requirements…

Artificial Intelligence · Computer Science 2026-03-13 Qianpu Sun , Xiaowei Chi , Yuhan Rui , Ying Li , Kuangzhi Ge , Jiajun Li , Sirui Han , Shanghang Zhang

With the increasing intelligence and autonomy of LLM agents, their potential applications in the legal domain are becoming increasingly apparent. However, existing general-domain benchmarks cannot fully capture the complexity and subtle…

Computation and Language · Computer Science 2024-12-24 Haitao Li , Junjie Chen , Jingli Yang , Qingyao Ai , Wei Jia , Youfeng Liu , Kai Lin , Yueyue Wu , Guozhi Yuan , Yiran Hu , Wuyue Wang , Yiqun Liu , Minlie Huang

As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse and realistic agent trajectory benchmark for safety…

Artificial Intelligence · Computer Science 2026-04-30 Zhonghao Yang , Yu Li , Yanxu Zhu , Tianyi Zhou , Yuejin Xie , Haoyu Luo , Jing Shao , Xia Hu , Dongrui Liu

Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing…