Related papers: HARP: Measuring Harm Amplification in Multi-Agent …
Agent-based models (ABMs) have shown promise for modelling various real world phenomena incompatible with traditional equilibrium analysis. However, a critical concern is the manual definition of behavioural rules in ABMs. Recent…
It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we…
Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training these systems remains notoriously difficult due to the…
We consider a decentralized formulation of the active hypothesis testing (AHT) problem, where multiple agents gather noisy observations from the environment with the purpose of identifying the correct hypothesis. At each time step, agents…
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…
Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…
Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models…
Multi-agent hierarchical reinforcement learning (MAHRL) has been studied as an effective means to solve intelligent decision problems in complex and large-scale environments. However, most current MAHRL algorithms follow the traditional way…
The increasing operational reliance on complex Multi-Agent Systems (MAS) across safety-critical domains necessitates rigorous adversarial robustness assessment. Modern MAS are inherently heterogeneous, integrating conventional Multi-Agent…
Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an…
Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the…
Multi-Agent Reinforcement Learning (MARL) has shown clear effectiveness in coordinating multiple agents across simulated benchmarks and constrained scenarios. However, its deployment in real-world multi-agent systems (MAS) remains limited,…
State-of-the-art techniques for addressing scaling-related main memory errors identify and repair bits that are at risk of error from within the memory controller. Unfortunately, modern main memory chips internally use on-die error…
The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in the artificial intelligence (AI) research community. However, many research endeavors have been focused on…
Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy is designed to improve their health outcomes and reduce safety risks. Some large language models (LLMs) have…
We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an…
Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability, as various internal or external factors can cause agents to…
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…
Cooperative multi-agent reinforcement learning (MARL) is making rapid progress for solving tasks in a grid world and real-world scenarios, in which agents are given different attributes and goals, resulting in different behavior through the…
While large language models are capable diagnostic tools, the impact of multi-agent topology on diagnostic accuracy remains underexplored. This study evaluates four agent topologies, Control (single agent), Hierarchical, Adversarial, and…