With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment. Towards robust and flexible multi-agent application, AgentScope provides both built-in and customizable fault tolerance mechanisms. At the same time, it is also armed with system-level support for managing and utilizing multi-modal data, tools, and external knowledge. Additionally, we design an actor-based distribution framework, enabling easy conversion between local and distributed deployments and automatic parallel optimization without extra effort. With these features, AgentScope empowers developers to build applications that fully realize the potential of intelligent agents. We have released AgentScope at https://github.com/modelscope/agentscope, and hope AgentScope invites wider participation and innovation in this fast-moving field.

A multi-agent system is a network of autonomous entities called agents that share information and collaborate to solve tasks usually beyond an individual agent's scope [12]. This broad description fits well in the recent research trends like cloud computing [11], or Industry 4.0 [10], and allows multi-agent systems to find applications in many other fields. In robotics, in scenarios including groups of mobile robots or swarms of drones, it is necessary to avoid collisions or obstacles and to navigate collaboratively [9]. The agent-based approach is also used for controlling smart grids, i.e., efficient and robust power systems [6]. We can also find numerous other examples, like analyzing the traffic flow [7] or modelling purchasing decisions [3]. Inspired by these multidisciplinary applications, we formally discuss the general problem of distributed learning, with a particular focus on the modelling of nonlinearities under limited information, cf.

Decentralized agent groups typically require complex mechanisms to accomplish coordinated tasks. In contrast, biological systems can achieve intelligent group behaviors with each agent performing simple sensing and actions. We summarize our recent papers on a biologically-inspired control framework for multi-agent tasks that is based on a simple and iterative control law. We theoretically analyze important aspects of this decentralized approach, such as the convergence and scalability, and further demonstrate how this approach applies to real-world applications with a diverse set of multi-agent applications. These results provide a deeper understanding of the contrast between centralized and decentralized algorithms in multi-agent tasks and autonomous robot control.