English
Related papers

Related papers: Auditing Agent Harness Safety

200 papers

LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that…

Artificial Intelligence · Computer Science 2026-05-28 Yilun Yao , Xinyu Tan , Chao-Hsuan Liu , Yaoming Li , Zhengyang Wang , Wenhan Yu , Zhewen Tan , Yuxuan Tian , Guangxiang Zhao , Lin Sun , Xiangzheng Zhang , Tong Yang

Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent…

Artificial Intelligence · Computer Science 2026-05-12 Haonan Dong , Qiguan Feng , Kehan Jiang , Haoran Ye , Xin Zhang , Guojie Song

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

Machine Learning · Computer Science 2026-04-16 Jiacheng Wang , Jinchang Hou , Fabian Wang , Ping Jian , Chenfu Bao , Zhonghou Lv

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

Cryptography and Security · Computer Science 2026-05-12 Xixun Lin , Yang Liu , Yancheng Chen , Yongxuan Wu , Yucheng Ning , Yilong Liu , Nan Sun , Shun Zhang , Bin Chong , Chuan Zhou , Yanan Cao

Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call workflows rather than text generation alone. While recent benchmarks evaluate agents across diverse environments and risk…

Software Engineering · Computer Science 2026-03-20 Xuan Chen , Lu Yan , Ruqi Zhang , Xiangyu Zhang

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Cryptography and Security · Computer Science 2025-11-03 Sheng Yin , Xianghe Pang , Yuanzhuo Ding , Menglan Chen , Yutong Bi , Yichen Xiong , Wenhao Huang , Zhen Xiang , Jing Shao , Siheng Chen

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…

Artificial Intelligence · Computer Science 2026-05-14 Yu Li , Haoyu Luo , Yuejin Xie , Yuqian Fu , Zhonghao Yang , Shuai Shao , Qihan Ren , Wanying Qu , Yanwei Fu , Yujiu Yang , Jing Shao , Xia Hu , Dongrui Liu

The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…

Computers and Society · Computer Science 2026-05-19 Miles Q. Li , Benjamin C. M. Fung , Boyang Li , Heba Ismail , Farkhund Iqbal

AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…

Multiagent Systems · Computer Science 2026-05-26 Fouad Bousetouane

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…

Artificial Intelligence · Computer Science 2026-02-18 Sanidhya Vijayvargiya , Aditya Bharat Soni , Xuhui Zhou , Zora Zhiruo Wang , Nouha Dziri , Graham Neubig , Maarten Sap

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…

Computation and Language · Computer Science 2025-05-21 Zhexin Zhang , Shiyao Cui , Yida Lu , Jingzhuo Zhou , Junxiao Yang , Hongning Wang , Minlie Huang

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…

Machine Learning · Computer Science 2026-05-22 Boyuan Wang , Bochao Li , Minghan Wang , Yuxin Tao , Fang Kong

Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges…

Computation and Language · Computer Science 2026-05-27 Haoxuan Jia , Yang Liu , Bin Chong , Yingguang Yang , Yancheng Chen , Jiayu Liang , Qian Li , Hanning Lu , Kefu Xu , Hao Zheng , Chongyang Zhang , Hao Peng , Philip S. Yu

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 large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a…

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Machine Learning · Computer Science 2025-07-11 Ram Potham

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…

Artificial Intelligence · Computer Science 2026-02-03 Hanjun Luo , Shenyu Dai , Chiming Ni , Xinfeng Li , Guibin Zhang , Kun Wang , Tongliang Liu , Hanan Salam

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…

Cryptography and Security · Computer Science 2026-04-23 Hanzhi Liu , Chaofan Shou , Xiaonan Liu , Hongbo Wen , Yanju Chen , Ryan Jingyang Fang , Yu Feng

AI agents are increasingly deployed on complex, domain-specific workflows -- navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and…

Artificial Intelligence · Computer Science 2026-05-05 Haebin Seong , Li Yin , Haoran Zhang , Zhan Shi
‹ Prev 1 2 3 10 Next ›