Related papers: Exposing Weak Links in Multi-Agent Systems under A…

Service system performance depends on how participants respond to design choices, but modeling these responses is hard due to the complexity of human behavior. We introduce an LLM-powered multi-agent simulation (LLM-MAS) framework for…

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the…

Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation, demonstrating impressive performance on established benchmarks. Despite their prosperous development, the fundamental mechanisms underlying their…

Multi-agent systems (MAS) increasingly solve complex tasks by orchestrating agents and tools selected from rapidly growing marketplaces. As these marketplaces expand, many candidates become functionally overlapping, making selection not…

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of…

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-privileged tool use. This paper aims to understand and mitigate…

Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based…

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

While multi-agent LLM systems show strong capabilities in various domains, they are highly vulnerable to adversarial and low-performing agents. To resolve this issue, in this paper, we introduce a general and adversary-resistant multi-agent…

The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhanced problem-solving. These multi-agent debate (MAD)…

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.…

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation, lacking dynamic adaptability…

Multi-agent systems rely on communication for information sharing and action coordination, which exposes a vulnerability to attacks. We investigate single-victim communication perturbation attacks against Multi-Agent Reinforcement…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vulnerability, as unreliable or Byzantine agents may sway…

Coordination between organizations on strategic, tactical and operation levels leads to more effective and efficient supply chains. Supply chain management is increasing day by day in modern enterprises. The environment is becoming…

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,…