Related papers: Auditing Cascading Risks in Multi-Agent Systems vi…

Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the underlying inter-agent communication topology. However, existing…

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,…

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…

Multi-agent systems (MAS) based on Large Language Models (LLMs) have the potential to solve tasks that are beyond the reach of any single LLM. However, this potential can only be realized when the collaboration mechanism between agents is…

AI systems comprise a range of interactions across the technical and organisational components of a range of actors. These components work together to provide the systems' functionality. This socio-technical assemblage is increasingly…

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a coalition and…

We address the problem of interaction topology identification in open multi-agent systems (OMAS) with dynamic node sets and fast switching interactions. In such systems, new agents join and interactions change rapidly, resulting in…

Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems, yet their performance is critically dependent on the design of their underlying collaboration topology. As MAS become increasingly deployed in web services…

Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge…

LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM agents. However, their performance often suffers from naive aggregation mechanisms that…

Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fundamental dilemma: lightweight single-auditor methods are…

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…

Ensuring safety in autonomous multi-agent systems during time-critical tasks such as rendezvous is a fundamental challenge, particularly under communication delays and uncertainty in system parameters. In this paper, we develop a…

Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity, which collectively undermine the robustness of risk…

The monitoring of large dynamic networks is a major chal- lenge for a wide range of application. The complexity stems from properties of the underlying graphs, in which slight local changes can lead to sizable variations of global prop-…

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…

We propose an extension to the OWASP Multi-Agentic System (MAS) Threat Modeling Guide, translating recent anticipatory research in multi-agent security (MASEC) into practical guidance for addressing challenges unique to large language model…

A prevailing approach for learning visuomotor policies is to employ reinforcement learning to map high-dimensional visual observations directly to action commands. However, the combination of high-dimensional visual inputs and agile…

Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically optimize agent capabilities or communication topologies. However, existing methods…

Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent…