English
Related papers

Related papers: Architecture Matters for Multi-Agent Security

200 papers

As AI agents are increasingly adopted to collaborate on complex objectives, ensuring the security of autonomous multi-agent systems becomes crucial. We develop simulations of agents collaborating on shared objectives to study these security…

Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches…

Artificial Intelligence · Computer Science 2026-05-11 Yuliang Xu , Xiang Xu , Yao Wan , Hu Wei , Tong Jia

As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper…

Artificial Intelligence · Computer Science 2026-05-05 Tanav Singh Bajaj , Nikhil Singh , Karan Anand , Eishkaran Singh

Collaboration and information sharing empower Multi-Agent Systems (MAS) but also introduce a critical security risk known as Agent Cascading Injection (ACI). In such attacks, a compromised agent exploits inter-agent trust to propagate…

Artificial Intelligence · Computer Science 2026-04-10 Hengyu An , Minxi Li , Jinghuai Zhang , Naen Xu , Chunyi Zhou , Changjiang Li , Xiaogang Xu , Tianyu Du , Shouling Ji

Modern supervisory control and data acquisition (SCADA) systems comprise variety of industrial equipment such as physical control processes, logical control systems, communication networks, computers, and communication protocols. They are…

Systems and Control · Computer Science 2015-09-29 Hosny Abbas , Samir Shaheen , Mohammed Amin

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Artificial Intelligence · Computer Science 2025-05-30 Jen-tse Huang , Jiaxu Zhou , Tailin Jin , Xuhui Zhou , Zixi Chen , Wenxuan Wang , Youliang Yuan , Michael R. Lyu , Maarten Sap

The design space of agentic AI inference spans two extremes: frontier large language models (LLMs), typically hosted in the cloud and offering strong performance across a wide range of tasks at substantially high cost, and more…

Multiagent Systems · Computer Science 2026-05-29 Corrado Rainone , Davide Belli , Bence Major , Arash Behboodi

Generative multiagent systems are rapidly emerging as transformative tools for scalable automation and adaptive decisionmaking in telecommunications. Despite their promise, these systems introduce novel risks that remain underexplored,…

Systems and Control · Electrical Eng. & Systems 2025-11-25 Zeinab Nezami , Shehr Bano , Abdelaziz Salama , Maryam Hafeez , Syed Ali Raza Zaidi

Modern distributed software systems often operate in dynamic environments in which operation conditions change continuously and subsystems may come and go at will, e.g. intelligent traffic management and multi-robot systems. To manage these…

Multiagent Systems · Computer Science 2019-09-10 Danny Weyns , Flavio Oquendo

Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the…

Multiagent Systems · Computer Science 2026-04-22 Nuo Chen , Yicheng Tong , Yuzhe Yang , Yufei He , Xueyi Zhang , Qingyun Zou , Qian Wang , Bingsheng He

The rapid development of AI agents leads to a surge in communication demands. Alongside this rise, a variety of frameworks and protocols emerge. While these efforts demonstrate the vitality of the field, they also highlight increasing…

Networking and Internet Architecture · Computer Science 2025-09-03 Chenguang Du , Chuyi Wang , Yihan Chao , Xiaohui Xie , Yong Cui

Enterprise interest in multi-agent systems has shifted from generic software agents to large-language-model (LLM) based intelligent agents that plan, use tools, maintain contextual memory, inspect intermediate results, collaborate with…

Multiagent Systems · Computer Science 2026-05-12 John deVadoss

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens,…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Cryptography and Security · Computer Science 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

The aviation literature gives relatively little guidance to practitioners about the specifics of architecting systems for safety, particularly the impact of architecture on allocating safety requirements, or the relative ease of system…

Software Engineering · Computer Science 2023-01-20 Jane Fenn , Mark Nicholson , Ganesh Pai , Michael Wilkinson

LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that…

Artificial Intelligence · Computer Science 2026-02-04 Yingxuan Yang , Chengrui Qu , Muning Wen , Laixi Shi , Ying Wen , Weinan Zhang , Adam Wierman , Shangding Gu

The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped…

Software Engineering · Computer Science 2026-01-13 Shaunak Biswas , Hiya Bhatt , Karthik Vaidhyanathan

This paper formalises the literature on emerging design patterns and paradigms for Large Language Model (LLM)-enabled multi-agent systems (MAS), evaluating their practical utility across various domains. We define key architectural…

Multiagent Systems · Computer Science 2026-01-08 Harri Renney , Maxim N Nethercott , Nathan Renney , Peter Hayes

Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strategic adaptation at scale, challenging security architectures…

Cryptography and Security · Computer Science 2025-12-30 Tao Li , Quanyan Zhu

Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…

Cryptography and Security · Computer Science 2026-03-03 Qingxiao Xu , Ze Sheng , Zhicheng Chen , Jeff Huang