Related papers: MURMUR: Using cross-user chatter to break collabor…

The proliferation of fake news in the digital age has raised critical concerns, particularly regarding its impact on societal trust and democratic processes. Diverging from conventional agent-based simulation approaches, this work…

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural…

Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly…

Large language models (LLMs) have revolutionized how we interact with machines. However, this technological advancement has been paralleled by the emergence of "Mallas," malicious services operating underground that exploit LLMs for…

Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…

Large language models (LLMs) have demonstrated impressive natural language processing abilities but face challenges such as hallucination and outdated knowledge. Retrieval-Augmented Generation (RAG) has emerged as a state-of-the-art…

Large Language Model (LLM) agents equipped with external tools have become increasingly powerful for complex tasks such as web shopping, automated email replies, and financial trading. However, these advancements amplify the risks of…

Simulations, although powerful in accurately replicating real-world systems, often remain inaccessible to non-technical users due to their complexity. Conversely, large language models (LLMs) provide intuitive, language-based interactions…

Language agents powered by large language models (LLMs) have seen exploding development. Their capability of using language as a vehicle for thought and communication lends an incredible level of flexibility and versatility. People have…

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction.…

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and…

This article explores the dynamic influence of computational entities based on multi-agent systems theory (SMA) combined with large language models (LLM), which are characterized by their ability to simulate complex human interactions, as a…

Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains due to their specialized agentic roles and collaborative interactions. However, this also…

Large Language Models (LLMs) have revolutionized Natural Language Processing but exhibit limitations, particularly in autonomously addressing novel challenges such as reasoning and problem-solving. Traditional techniques like…

User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communication, forms the foundation of social interaction and behavior.…

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive…

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of…