English
Related papers

Related papers: Proteus: A Self-Evolving Red Team for Agent Skill …

200 papers

Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-agent system (MAS) restructuring. This separation can create…

Multiagent Systems · Computer Science 2026-05-19 Shuai Pan , Yixiang Liu , Jiaye Gao , Te Gao , Weiwen Liu , Jianghao Lin , Zhihui Fu , Jun Wang , Weinan Zhang , Yong Yu

Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. However, malicious agents in MAS may inject misinformation…

Artificial Intelligence · Computer Science 2026-05-28 Yaoyang Luo , Zhi Zheng , Ziwei Zhao , Tong Xu , Zhao Jielun , Wenjun Xue , Yong Chen , Enhong Chen

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Multiagent Systems · Computer Science 2025-11-10 Ishan Kavathekar , Hemang Jain , Ameya Rathod , Ponnurangam Kumaraguru , Tanuja Ganu

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…

Machine Learning · Computer Science 2026-04-27 Meghana Karnam , Ananya Joshi

Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the…

Multiagent Systems · Computer Science 2025-06-10 Xinran Li , Chenjia Bai , Zijian Li , Jiakun Zheng , Ting Xiao , Jun Zhang

Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly…

Artificial Intelligence · Computer Science 2026-05-13 Bo Yin , Qi Li , Xinchao Wang

Recently, red teaming, with roots in security, has become a key evaluative approach to ensure the safety and reliability of Generative Artificial Intelligence. However, most existing work emphasizes technical benchmarks and attack success…

Computers and Society · Computer Science 2026-02-24 Adriana Alvarado Garcia , Ruyuan Wan , Ozioma C. Oguine , Karla Badillo-Urquiola

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Cryptography and Security · Computer Science 2025-07-22 Pengfei Du

We present an approach and system for real-time reconstruction of attack scenarios on an enterprise host. To meet the scalability and real-time needs of the problem, we develop a platform-neutral, main-memory based, dependency graph…

Cryptography and Security · Computer Science 2018-01-09 Md Nahid Hossain , Sadegh M Milajerdi , Junao Wang , Birhanu Eshete , Rigel Gjomemo , R Sekar , Scott Stoller , VN Venkatakrishnan

Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under realistic conditions: binary-only feedback, no gradient…

Artificial Intelligence · Computer Science 2026-04-28 Mazal Bethany , Kim-Kwang Raymond Choo , Nishant Vishwamitra , Peyman Najafirad

Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficult to debug and refine. Failures can originate from subtle errors in intermediate outputs…

Computation and Language · Computer Science 2026-05-19 Kazuki Kawamura , Satoshi Waki , Kei Tateno

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current…

Cryptography and Security · Computer Science 2026-05-12 Monika Jotautaitė , Maria Angelica Martinez , Ollie Matthews , Tyler Tracy

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

Multiagent Systems · Computer Science 2025-08-11 Alistair Reid , Simon O'Callaghan , Liam Carroll , Tiberio Caetano

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…

Artificial Intelligence · Computer Science 2026-03-10 Weize Liu , Minghui Liu , Sy-Tuyen Ho , Souradip Chakraborty , Xiyao Wang , Furong Huang

Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Yufan Liu , Wanqian Zhang , Huashan Chen , Lin Wang , Xiaojun Jia , Zheng Lin , Weiping Wang

Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this…

Cryptography and Security · Computer Science 2026-03-10 Naufal Suryanto , Muzammal Naseer , Pengfei Li , Syed Talal Wasim , Jinhui Yi , Juergen Gall , Paolo Ceravolo , Ernesto Damiani

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…

Artificial Intelligence · Computer Science 2026-05-29 Jianshuo Dong , Sheng Guo , Hao Wang , Xun Chen , Zhuotao Liu , Tianwei Zhang , Ke Xu , Minlie Huang , Han Qiu

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…

Cryptography and Security · Computer Science 2025-12-16 Mohamed Amine Ferrag , Norbert Tihanyi , Djallel Hamouda , Leandros Maglaras , Abderrahmane Lakas , Merouane Debbah

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security…

Computation and Language · Computer Science 2024-07-24 Tianjie Ju , Yiting Wang , Xinbei Ma , Pengzhou Cheng , Haodong Zhao , Yulong Wang , Lifeng Liu , Jian Xie , Zhuosheng Zhang , Gongshen Liu

The prevalent deployment of Large Language Model agents such as OpenClaw unlocks potential in real-world applications, while amplifying safety concerns. Among these concerns, the self-replication risk of LLM agents driven by objective…

Artificial Intelligence · Computer Science 2026-04-02 Boxuan Zhang , Yi Yu , Jiaxuan Guo , Jing Shao