English
Related papers

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

200 papers

AI-based defensive solutions are necessary to defend networks and information assets against intelligent automated attacks. Gathering enough realistic data for training machine learning-based defenses is a significant practical challenge.…

Cryptography and Security · Computer Science 2021-10-05 Kalle Kujanpää , Willie Victor , Alexander Ilin

Red teaming is critical for identifying vulnerabilities and building trust in current LLMs. However, current automated methods for Large Language Models (LLMs) rely on brittle prompt templates or single-turn attacks, failing to capture the…

Machine Learning · Computer Science 2025-08-07 Roman Belaire , Arunesh Sinha , Pradeep Varakantham

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

Machine Learning · Computer Science 2025-10-31 David Schmotz , Sahar Abdelnabi , Maksym Andriushchenko

Recent developments in AI governance and safety research have called for red-teaming methods that can effectively surface potential risks posed by AI models. Many of these calls have emphasized how the identities and backgrounds of…

Artificial Intelligence · Computer Science 2025-10-28 Wesley Hanwen Deng , Sunnie S. Y. Kim , Akshita Jha , Ken Holstein , Motahhare Eslami , Lauren Wilcox , Leon A Gatys

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

Machine Learning · Computer Science 2026-05-06 Kunvar Thaman

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, limiting their ability to adapt to dynamic defenses and…

Cryptography and Security · Computer Science 2025-01-06 Yanjiang Liu , Shuhen Zhou , Yaojie Lu , Huijia Zhu , Weiqiang Wang , Hongyu Lin , Ben He , Xianpei Han , Le Sun

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an…

Cryptography and Security · Computer Science 2026-04-22 Isaac David , Arthur Gervais

The rapid adoption of large language models (LLMs) in financial services introduces new operational, regulatory, and security risks. Yet most red-teaming benchmarks remain domain-agnostic and fail to capture failure modes specific to…

Computational Finance · Quantitative Finance 2026-03-12 Fabrizio Dimino , Bhaskarjit Sarmah , Stefano Pasquali

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces…

Cryptography and Security · Computer Science 2026-05-28 Chang Jin , An Wang , Zeming Wei , Kai Wang , Biaojie Zeng , Qiaosheng Zhang , Chao Yang , Jingjing Qu , Xia Hu , Xingcheng Xu

Multi-agent deployments of large language models (LLMs) are increasingly embedded in market, allocation, and governance workflows, yet covert coordination among agents can silently erode trust and social welfare. Existing audits are…

Multiagent Systems · Computer Science 2025-10-21 Om Tailor

Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…

Software Engineering · Computer Science 2026-01-07 Saba Naqvi , Mohammad Baqar , Nawaz Ali Mohammad

Large Language Models (LLMs) exhibit remarkable capabilities but are susceptible to adversarial prompts that exploit vulnerabilities to produce unsafe or biased outputs. Existing red-teaming methods often face scalability challenges,…

Computation and Language · Computer Science 2026-01-21 Quy-Anh Dang , Chris Ngo , Truong-Son Hy

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of…

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Computation and Language · Computer Science 2025-11-18 Xikang Yang , Biyu Zhou , Xuehai Tang , Jizhong Han , Songlin Hu

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

Human-Computer Interaction · Computer Science 2025-04-04 Abed Kareem Musaffar , Anand Gokhale , Sirui Zeng , Rasta Tadayon , Xifeng Yan , Ambuj Singh , Francesco Bullo

Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance,…

Computation and Language · Computer Science 2025-03-03 Xiao Yu , Baolin Peng , Vineeth Vajipey , Hao Cheng , Michel Galley , Jianfeng Gao , Zhou Yu

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels…

Artificial Intelligence · Computer Science 2025-08-28 Neil Kale , Chen Bo Calvin Zhang , Kevin Zhu , Ankit Aich , Paula Rodriguez , Scale Red Team , Christina Q. Knight , Zifan Wang

Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning.…

Artificial Intelligence · Computer Science 2025-10-14 William Nguyen , Vinh Luong , Christopher Nguyen
‹ Prev 1 8 9 10 Next ›