25 papers · ranked by Valyu relevance
Sarah Schömbs, Yan Zhang, Jorge Gonçalves, Wafa Johal
Recent advances in multi-agentic systems (e.g. AutoGen, OpenAI Swarm) allow users to interact with a group of specialised AI agents rather than a single general-purpose agent. Despite the promise of this new paradigm, the HCI community has yet to fully examine the opportunities, risks, and user-centred challenges it…
Corban Rivera, Edward Staley, Ashley Llorens
Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains. An emerging landscape of development environments is making powerful RL techniques more accessible for a growing community of researchers. However, most…
Roxana Rădulescu, Patrick Mannion, Diederik M. Roijers, Ann Nowé
The majority of multi-agent system (MAS) implementations aim to optimise agents' policies with respect to a single objective, despite the fact that many real-world problem domains are inherently multi-objective in nature. Multiobjective multi-agent systems (MOMAS) explicitly consider the possible trade-offs between…
Tian, Fangqiao, Luo, An + 26 more
Multi-agent AI systems (MAS) have rapidly emerged as powerful tools for addressing complex problems beyond single-agent methods, significantly impacting research and industry. However, the swift deployment of MAS has outpaced foundational clarity, leaving critical questions about their effectiveness and safety largely…
Ameer Ivoghlian, Zoran Salcic, Kevin I-Kai Wang, Henry Leung + 3 more
'Flavia C. Delicato' 'Fuhua Lin' 'Paulo F. Pires'] Wireless networks are trending towards large scale systems, containing thousands of nodes, with multiple co-existing applications. Congestion is an inevitable consequence of this scale and complexity, which leads to inefficient use of the network capacity. This paper…
Pamul Yadav, Ashutosh Mishra, Shiho Kim, Ching-Yao Chan + 3 more
Connected and automated vehicles (CAVs) require multiple tasks in their seamless maneuverings. Some essential tasks that require simultaneous management and actions are motion planning, traffic prediction, traffic intersection management, etc. A few of them are complex in nature. Multi-agent reinforcement learning…
Tongyue Li, Dianxi Shi, Songchang Jin, Zhen Wang + 3 more
'Yang Chen' 'Adam Lipowski'] Multi-agent systems often face challenges such as elevated communication demands, intricate interactions, and difficulties in transferability. To address the issues of complex information interaction and model scalability, we propose an innovative hierarchical graph attention actor-critic…
Lidong Zhai, Zhijie Qiu, Lvyang Zhang, Jiaqi Li + 4 more
'Xizhong Guo' 'Ge Sun'] Abstract—This paper proposes the "Academy of Athens" multi-agent seven-layer framework, aimed at systematically addressing challenges in multi-agent systems (MAS) within artificial intelligence (AI) art creation, such as collaboration efficiency, role allocation, environmental adaptation, and…
Raphael Köster, Edgar A. Duéñez-Guzmán, William A. Cunningham, Joel Z. Leibo
'Joel Z. Leibo'] Title: Significance The emergence of group bias has a long history in social psychology, including the positing of innate biases. Experimental evidence is fundamentally limited because every brain is both a product of experience and evolution. With cognitive models, one can control both the cognitive…
Ken Ming Lee, Sriram Ganapathi Subramanian, Mark Crowley
Independent reinforcement learning algorithms have no theoretical guarantees for finding the best policy in multi-agent settings. However, in practice, prior works have reported good performance with independent algorithms in some domains and bad performance in others. Moreover, a comprehensive study of the strengths…
Shanshan Han, Qifan Zhang, Yuhang Yao, Weizhao Jin + 2 more
'Chaoyang He'] This paper explores existing works of multi-agent systems and identify challenges that remain inadequately addressed. By leveraging the diverse capabilities and roles of individual agents within a multi-agent system, these systems can tackle complex tasks through collaboration. We discuss optimizing task…
Yusi Chen, Angela Radulescu, Herbert Zheng Wu
Understanding the intentions and beliefs of others, a phenomenon known as “theory of mind”, is a crucial element in social behavior. These beliefs and perceptions are inherently subjective and latent, making them often unobservable for investigation. Social interactions further complicate the matter, as multiple agents…
Authors not listed
This comprehensive review examines the evolution of autonomous materials synthesis laboratories that integrate artificial intelligence with advanced robotics to accelerate discovery. Traditional materials development pipelines typically require 10-20 years, but self-driving laboratories (SDLs) and Materials…
Jung In Kim, Young Jae Lee, Jongkook Heo, Jinhyeok Park + 5 more
'Jaehoon Kim' 'Sae Rin Lim' 'Jinyong Jeong' 'Seoung Bum Kim' 'Peng Guo'] Deep reinforcement learning (DRL) is a powerful approach that combines reinforcement learning (RL) and deep learning to address complex decision-making problems in high-dimensional environments. Although DRL has been remarkably successful, its low…
Qiang Wu, Jianqing Wu, Jun Shen, Binbin Yong + 1 more
With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) has expanded from one intersection to multiple intersections. In this paper, we propose…
Zack Dulberg, Rachit Dubey, Isabel M. Berwian, Jonathan Cohen
Satisfying a variety of conflicting needs in a changing environment is a fundamental challenge for any adaptive agent. Here, we show that designing an agent in a modular fashion as a collection of sub-agents, each dedicated to a separate need, powerfully enhanced the agent’s capacity to satisfy its overall needs. We…
Wei-Chen Liao, Ti-Rong Wu, I-Chen Wu
Multi-agent reinforcement Learning (MARL) is often challenged by the sight range dilemma, where agents either receive insufficient or excessive information from their environment. In this paper, we propose a novel method, called Dynamic Sight Range Selection (DSR), to address this issue. DSR utilizes an Upper…
Authors not listed
We have developed Aitomia – a platform powered by AI to assist in performing AI-driven atomistic and quantum chemical (QC) simulations. This evolving intelligent assistant platform is equipped with chatbots and AI agents to help experts and guide non-experts in setting up and running atomistic simulations, monitoring…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Dominik Fischer, Sanaz Mostaghim, Larissa Albantakis
Evolving in groups can either enhance or reduce an individual’s task performance. Still, we know little about the factors underlying group performance, which may be reduced to three major dimensions: (a) the individual’s ability to perform a task, (b) the dependency on environmental conditions, and (c) the perception…
Authors not listed
Agentic artificial intelligence (AI) is poised to redefine how science is conducted, automating not just data analysis but the entire research lifecycle, from hypothesis generation to validation. Yet most current AI agents remain domain-bound, tailored to specific applications such as materials synthesis or quantum…
Tazzio Tissot, Mike Levin, Chris Buckley, Richard Watson
How do multiple active components at one level of organisation create agential wholes at higher levels of organisation? For example, in organismic development, how does the multi-scale autonomy of the organism arise from the interactions of the molecules, cells and tissues that an organism contains? And, in the major…
Kazushi Tsutsui, Ryoya Tanaka, Kazuya Takeda, Keisuke Fujii
Collaborative hunting, in which predators play different and complementary roles to capture prey, has been traditionally believed as an advanced hunting strategy requiring large brains that involve high level cognition. However, recent findings that collaborative hunting have also been documented in smaller-brained…
Authors not listed
In recent years, the development of large language models (LLMs) has revolutionized various fields of natural science, yet their application in molecular data processing remains constrained due to the reliance on single-modality inputs and outputs. To bridge the gap between experimenters and computational tools, we…
Authors not listed
Computational methods for generating molecules with specific physiochemical properties or biolog- ical activity can greatly assist drug discovery efforts. Deep learning generative models constitute a significant step towards that direction. In this work, we introduce a novel approach that utilizes a Reinforcement…