This paper proposes a novel adaptive predefined-time control strategy for the n-link robotic multi-agent systems (MASs) to achieve the consensus tracking control. First, unlike existing research on the control problems of a single robotic manipulator system, the consensus tracking control problem of the robotic MASs is studied. Then, in contrast to the finite-time and fixed-time control theories, the controller constructed based on the predefined-time control theory enables the user to define the convergence time of each agent in advance, regardless of the initial state and parameters of the system. The radial basis function neural networks (RBFNNs) are applied to approximate the unknown functions during the controller design process. Only one parameter is updated online, which saves computational costs. Moreover, to deal with the shortage of network resources that may occur when the robotic MASs perform complex tasks, the controllers are constructed by combining the switching threshold event-triggered control (ETC) mechanism to save communication resources. Finally, a simulation example demonstrates the efficacy of the proposed control strategy.

This paper investigates the task allocation problem of aircraft swarms. Considering the information of aircraft, targets, no-fly zones, and task constraints, the local optimization performance index of the individual aircraft is designed. Then, a distributed fault-tolerant target allocation approach is proposed based on the hedonic coalition game and the maximum gain message algorithm. With this approach, the task allocation result, which is the Nash equilibrium of the game, can be obtained even under complete failure faults. Simulations further verify the effectiveness of the proposed approach.

Advancements in large language models (LLMs) have markedly improved the adaptability of artificial intelligence (AI) agents in dynamic and open environments. However, with the growing number and diversity of agents, ensuring secure, reliable, and autonomous collaboration among them has become an urgent and critical challenge. To this end, this letter proposes agent reinforced generation (ARG) to establish a multi-agent system with audit trail functionality, privacy compliance, and autonomous coordination. ARG integrates the model context protocol (MCP) and agent-to-agent (A2A) protocol to define the rules and logic governing agent-to-agent communications as well as agent-to-tool/data engagements. Decentralized autonomous organizations and operations (DAOs) are employed to enable agents to coordinate and execute tasks in a transparent and tamper-resistant manner. Additionally, the operational process of ARG is elaborated from task issuance to completion to validate the auditability and immutability of task coordination and execution. Finally, we highlight five key features of ARG, including parallelism and throughput, scalability across domains and load, fault tolerance and graceful failure, resource efficiency through delegation, as well as data security and privacy protection, positioning it as a promising paradigm for the realization of agentic intelligence.