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

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment…

We consider the networked multi-agent reinforcement learning (MARL) problem in a fully decentralized setting, where agents learn to coordinate to achieve the joint success. This problem is widely encountered in many areas including traffic…

Building autonomous vehicles (AVs) is a complex problem, but enabling them to operate in the real world where they will be surrounded by human-driven vehicles (HVs) is extremely challenging. Prior works have shown the possibilities of…

Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to…

Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial…

Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized training and execution (CTE),…

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…

This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps…

Safe Multi-agent reinforcement learning (safe MARL) has increasingly gained attention in recent years, emphasizing the need for agents to not only optimize the global return but also adhere to safety requirements through behavioral…

Multi-Agent Reinforcement Learning (MARL) is central to robotic systems cooperating in dynamic environments. While prior work has focused on these collaborative settings, adversarial interactions are equally critical for real-world…

Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems remains difficult. In this work, we theoretically pinpoint a key reason for…

Intraday surgical scheduling is a multi-objective decision problem under uncertainty-balancing elective throughput, urgent and emergency demand, delays, sequence-dependent setups, and overtime. We formulate the problem as a cooperative…

Action and observation delays exist prevalently in the real-world cyber-physical systems which may pose challenges in reinforcement learning design. It is particularly an arduous task when handling multi-agent systems where the delay of one…

In the real world, people/entities usually find matches independently and autonomously, such as finding jobs, partners, roommates, etc. It is possible that this search for matches starts with no initial knowledge of the environment. We…

We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator, deflector, responder, and evaluator - collaborate to…

Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited…

It is expected that autonomous vehicles(AVs) and heterogeneous human-driven vehicles(HVs) will coexist on the same road. The safety and reliability of AVs will depend on their social awareness and their ability to engage in complex social…

Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and has made progress in various fields. Specifically, cooperative MARL focuses on training a team of agents to cooperatively achieve tasks that are…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed memberships. Unlike traditional neighbor-based or fixed interaction…