This paper introduces \textsc{InfantAgent-Next}, a generalist agent capable of interacting with computers in a multimodal manner, encompassing text, images, audio, and video. Unlike existing approaches that either build intricate workflows around a single large model or only provide workflow modularity, our agent integrates tool-based and pure vision agents within a highly modular architecture, enabling different models to collaboratively solve decoupled tasks in a step-by-step manner. Our generality is demonstrated by our ability to evaluate not only pure vision-based real-world benchmarks (i.e., OSWorld), but also more general or tool-intensive benchmarks (e.g., GAIA and SWE-Bench). Specifically, we achieve a $\mathbf{7.27\\%}$ accuracy gain over Claude-Computer-Use on OSWorld. Codes and evaluation scripts are included in the supplementary material and will be released as open-source.

The intermittent and fluctuating output of wind turbines is increasingly recognized as a major issue affecting the power quality and stability of electrical grids. As wind power integration grows, addressing this challenge is essential. A promising solution involves using a Hybrid Energy Storage System (HESS), combining battery energy storage systems (BESS) and supercapacitors (SC). This paper presents a Q-learning based control strategy for tuning the parameters of a two-stage variable time constant low-pass filter (LPF) in a grid-connected microgrid. The proposed strategy adaptively adjusts the LPF time constant to mitigate wind power fluctuations. It also accounts for practical constraints of energy storage systems and their interfaced converters, such as preventing overcharge/discharge and adhering to maximum power conversion limits. Numerical simulations confirm the effectiveness of the two-stage variable time constant LPF in reducing output wind power fluctuations while considering the practical constraints of HESS.

This paper presents a fully distributed resilient secondary control approach for DC microgrids, designed to enhance resilience against unbounded false data injection (FDI) attacks on control inputs and communication link faults. The approach links the injected power with the current state of charge (SoC) and the observed average SoC value, adjusting the droop coefficient in secondary control level for energy storage systems (ESSs) accordingly to prevent overuse of any single ESS. Each converter employs a resilient consensus-based secondary control strategy, effectively mitigating these sophisticated threats. A rigorous Lyapunov stability analysis verifies that the framework can maintain essential DC microgrid distributed control objectives, such as voltage regulation, proportional load sharing, and SoC balancing, even under unbounded FDI attacks and communication link faults. The practical effectiveness of the framework is demonstrated through hardware-in-the-loop experiments using Typhoon HIL 604, showcasing its improved resilience against the complex challenges posed by such FDI attacks.

The problem of asymmetric bipartite consensus control is investigated within the context of nonlinear, discrete-time, networked multi-agent systems (MAS) subject to aperiodic denial-of-service (DoS) attacks. To address the challenges posed by these aperiodic DoS attacks, a data-driven event-triggered (DDET) mechanism has been developed. This mechanism is specifically designed to synchronize the states of the follower agents with the leader’s state, even in the face of aperiodic communication disruptions and data losses. Given the constraints of unavailable agents’ states and data packet loss during these attacks, the DDET control framework resiliently achieves leader-following consensus. The effectiveness of the proposed framework is validated through two numerical examples, which showcase its ability to adeptly handle the complexities arising from aperiodic DoS attacks in nonlinear MAS settings.

Recent advancements in large language models, such as GPT-4, have demonstrated remarkable capabilities in processing standard queries. Despite these advancements, their performance substantially declines in advanced mathematical problems requiring complex, multi-step logical reasoning. To enhance their inferential capabilities, current research has delved into prompting engineering, exemplified by methodologies such as the Tree of Thought and Graph of Thought. Nonetheless, these existing approaches encounter two significant limitations. Firstly, their effectiveness in tackling complex mathematical problems is somewhat constrained. Secondly, the necessity to design distinct prompts for individual problems hampers their generalizability. In response to these limitations, this paper introduces the Multi-Agent System for conditional Mining (MACM) prompting method. It not only resolves intricate mathematical problems but also demonstrates strong generalization capabilities across various mathematical contexts. With the assistance of MACM, the accuracy of GPT-4 Turbo on the most challenging level five mathematical problems in the MATH dataset increase from $\mathbf{54.68\\%} \text{ to } \mathbf{76.73\\%}$.

This article studies the attack-resilient output formation containment of general high-order heterogeneous multigroup systems under unknown unbounded attacks. The multigroup systems consist of cooperative heterogeneous leaders and followers, as well as adversarial attackers. Potential attacks on the multigroup systems consist of unknown unbounded signals generated from the attackers and injected distributedly into the actuator, the local state feedback, and communication channels of each agent to destabilize the synchronization dynamics. In contrast to the existing literature dealing with bounded disturbances, noises, and faults, which are caused unintentionally, this article studies the unknown unbounded attacks that are intentionally designed to jeopardize the system. The control objective is to make each follower's output trajectory reach the uniformly ultimately bounded (UUB) convergence to the time-varying formation reference, that is, the centroid of the multiple leaders' output trajectories while keeping a predefined time-varying offset with respect to it. Fully distributed attack-resilient control protocols are proposed, without requiring any global information. Lyapunov techniques are used to analyze the stability and UUB synchronization result of the overall closed-loop system. Comparative simulation examples are given to validate the proposed results.

This paper investigates optimal robust output containment problem of general linear heterogeneous multiagent systems (MAS) with completely unknown dynamics. A model-based algorithm using offline policy iteration (PI) is first developed, where the -copy internal model principle is utilized to address the system parameter variations. This offline PI algorithm requires the nominal model of each agent, which may not be available in most real-world applications. To address this issue, a discounted performance function is introduced to express the optimal robust output containment problem as an optimal output-feedback design problem with bounded -gain. To solve this problem online in real time, a Bellman equation is first developed to evaluate a certain control policy and find the updated control policies, simultaneously, using only the state/output information measured online. Then, using this Bellman equation, a model-free off-policy integral reinforcement learning algorithm is proposed to solve the optimal robust output containment problem of heterogeneous MAS, in real time, without requiring any knowledge of the system dynamics. Simulation results are provided to verify the effectiveness of the proposed method.

This paper studies the output containment control of linear heterogeneous multi-agent systems, where the system dynamics and even the state dimensions can generally be different. Since the states can have different dimensions, standard results from state containment control do not apply. Therefore, the control objective is to guarantee the convergence of the output of each follower to the dynamic convex hull spanned by the outputs of leaders. This can be achieved by making certain output containment errors go to zero asymptotically. Based on this formulation, two different control protocols, namely, full-state feedback and static output-feedback, are designed based on internal model principles. Sufficient local conditions for the existence of the proposed control protocols are developed in terms of stabilizing the local followers' dynamics and satisfying a certain H∞ criterion. Unified design procedures to solve the proposed two control protocols are presented by formulation and solution of certain local state-feedback and static output-feedback problems, respectively. Numerical simulations are given to validate the proposed control protocols.