Related papers: AgentMark: Utility-Preserving Behavioral Watermark…

The rapid development of LLMs has raised concerns about their potential misuse, leading to various watermarking schemes that typically offer high detectability. However, existing watermarking techniques often face trade-off between…

As LLM-based agents are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic user interactions. To…

Watermarking is a technique that involves embedding nearly unnoticeable statistical signals within generated content to help trace its source. This work focuses on a scenario where an untrusted third-party user sends prompts to a trusted…

The booming success of LLMs initiates rapid development in LLM agents. Though the foundation of an LLM agent is the generative model, it is critical to devise the optimal reasoning strategies and agent architectures. Accordingly, LLM agent…

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…

Large-language models (LLMs) have demonstrated powerful problem-solving capabilities, in particular when organized in multi-agent systems. However, the advent of such systems also raises several questions on the ability of a complex network…

The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However,…

Watermarking for large language models (LLMs) has emerged as an effective tool for distinguishing AI-generated text from human-written content. Statistically, watermark schemes induce dependence between generated tokens and a pseudo-random…

Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $\emph{monitoring}$ to detect and flag unsafe behavior during inference. An open…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external…

We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for identifying watermarks…

In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-intensive, and privacy-sensitive tasks. However, attackers may…

Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change independently of the agent: new emails arrive, calendar…

Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among LLM providers, platforms, and end users, which manifest as…

Existing LLM-enabled multi-agent frameworks are predominantly limited to digital or simulated environments and confined to narrowly focused knowledge domain, constraining their applicability to complex engineering tasks that require the…

A major challenge in developing robust and generalizable Human Activity Recognition (HAR) systems for smart homes is the lack of large and diverse labeled datasets. Variations in home layouts, sensor configurations, and individual behaviors…

The potential of automatic task-solving through Large Language Model (LLM)-based multi-agent collaboration has recently garnered widespread attention from both the research community and industry. While utilizing natural language to…

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code…

Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at…