Related papers: System Neural Diversity: Measuring Behavioral Hete…

This research proposes new tools for investigation of behavioral diversity in multi-robot systems and a significant body of results using these tools in simulated and real mobile robot experiments. The experiments specifically describe a…

Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample efficiency. Recent…

Generative agents, which implement behaviors using a large language model (LLM) to interpret and evaluate an environment, has demonstrated the capacity to solve complex tasks across many social and technological domains. However, when these…

Multimodal learning systems often face substantial uncertainty due to noisy data, low-quality labels, and heterogeneous modality characteristics. These issues become especially critical in human-computer interaction settings, where data…

We employ an agent-based model for cultural dynamics to investigate the effects of spatial heterogeneities on the collective behavior of a social system. We introduce heterogeneity as a random distribution of defects or imperfections in a…

Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to competently interact with diverse road users in diverse scenarios remains…

Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of…

In human society, the conflict between self-interest and collective well-being often obstructs efforts to achieve shared welfare. Related concepts like the Tragedy of the Commons and Social Dilemmas frequently manifest in our daily lives.…

Generating various strategies for a given task is challenging. However, it has already proven to bring many assets to the main learning process, such as improved behavior exploration. With the growth in the interest of heterogeneity in…

Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study…

Understanding and predicting the behavior of large-scale multi-agents in games remains a fundamental challenge in multi-agent systems. This paper examines the role of heterogeneity in equilibrium formation by analyzing how smooth…

Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environments requires detecting novel activities while continuously…

Discovering successful coordinated behaviors is a central challenge in Multi-Agent Reinforcement Learning (MARL) since it requires exploring a joint action space that grows exponentially with the number of agents. In this paper, we propose…

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

In this paper, we introduce a high-level controller synthesis framework that enables teams of heterogeneous agents to assist each other in resolving environmental conflicts that appear at runtime. This conflict resolution method is built…

While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations. Recent works have demonstrated…

Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks, demonstrating impressive performance and scalability. However, deploying MARL agents in real-world applications presents critical safety…

Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper,…

Conventional Intent Detection (ID) models are usually trained offline, which relies on a fixed dataset and a predefined set of intent classes. However, in real-world applications, online systems usually involve continually emerging new user…

In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of…