Related papers: AdvEvo-MARL: Shaping Internalized Safety through A…

Multi-agent systems (MAS) built on multimodal large language models exhibit strong collaboration and performance. However, their growing openness and interaction complexity pose serious risks, notably jailbreak and adversarial attacks.…

Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning (MARL), on their own due to their lack of safety…

Multi-Agent Reinforcement Learning (MARL) approaches have emerged as popular solutions to address the general challenges of cooperation in multi-agent environments, where the success of achieving shared or individual goals critically…

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

Multi-agent reinforcement learning (MARL) achieves encouraging performance in solving complex tasks. However, the safety of MARL policies is one critical concern that impedes their real-world applications. Popular multi-agent benchmarks…

Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interactive feedback. Multi-Agent Reinforcement Learning (MARL), in…

In recent advancements in Multi-agent Reinforcement Learning (MARL), its application has extended to various safety-critical scenarios. However, most methods focus on online learning, which presents substantial risks when deployed in…

Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions, such as a fixed number of agents and fully synchronous…

The advancement of general-purpose intelligent agents is intrinsically linked to the environments in which they are trained. While scaling models and datasets has yielded remarkable capabilities, scaling the complexity, diversity, and…

Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL) have emerged as promising methodologies for addressing challenges in automated cyber defence (ACD). These techniques offer adaptive decision-making capabilities in…

One of the challenges for multi-agent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. While exciting progress has…

Current research in LLM-based simulation systems lacks comprehensive solutions for modeling real-world court proceedings, while existing legal language models struggle with dynamic courtroom interactions. We present AgentCourt, a…

This dissertation explores the application of multi-agent reinforcement learning (MARL) for handling deadlocks in intralogistics systems that rely on autonomous mobile robots (AMRs). AMRs enhance operational flexibility but also increase…

Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, policy-centric loop, causing attack discovery to suffer from…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Recent advancements in deep learning techniques have opened new possibilities for designing solutions for autonomous cyber defence. Teams of intelligent agents in computer network defence roles may reveal promising avenues to safeguard…

Deep Reinforcement Learning has made significant progress in multi-agent systems in recent years. In this review article, we have focused on presenting recent approaches on Multi-Agent Reinforcement Learning (MARL) algorithms. In…

Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we…

Fair workload enforcement in heterogeneous multi-agent systems that pursue shared objectives remains challenging. Fixed fairness penalties often introduce inefficiencies, training instability, and conflicting agent incentives.…

As reinforcement learning agents become increasingly integrated into complex, real-world environments, designing for safety becomes a critical consideration. We specifically focus on researching scenarios where agents can cause undesired…