Related papers: BlindGuard: Safeguarding LLM-based Multi-Agent Sys…

With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent…

Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems,…

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

LLM-based multi-agent systems (MAS) have shown significant potential in tackling diverse tasks. However, to design effective MAS, existing approaches heavily rely on manual configurations or multiple calls of advanced LLMs, resulting in…

LLM-based Multi-Agent Systems ( LLM-MAS ) have become a research hotspot since the rise of large language models (LLMs). However, with the continuous influx of new related works, the existing reviews struggle to capture them…

Accurate detection of errors in large language models (LLM) responses is central to the success of scalable oversight, or providing effective supervision to superhuman intelligence. Yet, self-diagnosis is often unreliable on complex tasks…

Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. However, existing designs almost exclusively adopt a centralized…

In recent years, Large Language Models (LLMs) have shown great abilities in various tasks, including question answering, arithmetic problem solving, and poem writing, among others. Although research on LLM-as-an-agent has shown that LLM can…

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge…

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…

Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false…

Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware…

This study proposes the design and implementation of a multimodal LLM-based Multi-Agent System (MAS) leveraging a No-Code platform to address the practical constraints and significant entry barriers associated with AI adoption in…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal…

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…