The trajectory of artificial intelligence (AI) has been one of relentless acceleration, evolving from rudimentary rule-based systems to sophisticated, autonomous agents capable of complex reasoning and interaction. This whitepaper chronicles this remarkable journey, charting the key technological milestones--advancements in prompting, training methodologies, hardware capabilities, and architectural innovations--that have converged to create the AI agents of today. We argue that these agents, exemplified by systems like OpenAI's ChatGPT with plugins and xAI's Grok, represent a culminating phase in AI development, potentially constituting the "final generation" of intelligence as we currently conceive it. We explore the capabilities and underlying technologies of these agents, grounded in practical examples, while also examining the profound societal implications and the unprecedented pace of progress that suggests intelligence is now doubling approximately every six months. The paper concludes by underscoring the critical need for wisdom and foresight in navigating the opportunities and challenges presented by this powerful new era of intelligence.

This work proposes a fast heuristic algorithm for the coupled scheduling and trajectory planning of multiple Cartesian robotic arms harvesting fruits. Our method partitions the workspace, assigns fruit-picking sequences to arms, determines tight and feasible fruit-picking schedules and vehicle travel speed, and generates smooth, collision-free arm trajectories. The fruit-picking throughput achieved by the algorithm was assessed using synthetically generated fruit coordinates and a harvester design featuring up to 12 arms. The throughput increased monotonically as more arms were added. Adding more arms when fruit densities were low resulted in diminishing gains because it took longer to travel from one fruit to another. However, when there were enough fruits, the proposed algorithm achieved a linear speedup as the number of arms increased.

Decentralized optimization has become vital for leveraging distributed data without central control, enhancing scalability and privacy. However, practical deployments face fundamental challenges due to heterogeneous computation speeds and unpredictable communication delays. This paper introduces a refined model of Asynchronous Decentralized Stochastic Gradient Descent (ADSGD) under practical assumptions of bounded computation and communication times. To understand the convergence of ADSGD, we first analyze Asynchronous Stochastic Block Coordinate Descent (ASBCD) as a tool, and then show that ADSGD converges under computation-delay-independent step sizes. The convergence result is established without assuming bounded data heterogeneity. Empirical experiments reveal that ADSGD outperforms existing methods in wall-clock convergence time across various scenarios. With its simplicity, efficiency in memory and communication, and resilience to communication and computation delays, ADSGD is well-suited for real-world decentralized learning tasks.

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed memberships. Unlike traditional neighbor-based or fixed interaction graphs, our community-based framework captures flexible and abstract coordination patterns by allowing each agent to belong to multiple overlapping communities. Each community maintains shared policy and value functions, which are aggregated by individual agents according to personalized membership weights. We also design actor-critic algorithms that exploit this structure: agents inherit community-level estimates for policy updates and value learning, enabling structured information sharing without requiring access to other agents' policies. Importantly, our approach supports both transfer learning by adapting to new agents or tasks via membership estimation, and active learning by prioritizing uncertain communities during exploration. Theoretically, we establish convergence guarantees under linear function approximation for both actor and critic updates. To our knowledge, this is the first MARL framework that integrates community structure, transferability, and active learning with provable guarantees.

This paper explores the application of Hamilton's rule to altruistic decision-making in multi-agent systems. Inspired by biological altruism, we introduce a framework that evaluates when individual agents should incur costs to benefit their neighbors. By adapting Hamilton's rule, we define agent ``fitness" in terms of task productivity rather than genetic survival. We formalize altruistic decision-making through a graph-based model of multi-agent interactions and propose a solution using collaborative control Lyapunov functions. The approach ensures that altruistic behaviors contribute to the collective goal-reaching efficiency of the system. We illustrate this framework on a multi-agent way-point navigation problem, where we show through simulation how agent importance levels influence altruistic decision-making, leading to improved coordination in navigation tasks.

Radiology report generation (RRG) aims to automatically produce diagnostic reports from medical images, with the potential to enhance clinical workflows and reduce radiologists' workload. While recent approaches leveraging multimodal large language models (MLLMs) and retrieval-augmented generation (RAG) have achieved strong results, they continue to face challenges such as factual inconsistency, hallucination, and cross-modal misalignment. We propose a multimodal multi-agent framework for RRG that aligns with the stepwise clinical reasoning workflow, where task-specific agents handle retrieval, draft generation, visual analysis, refinement, and synthesis. Experimental results demonstrate that our approach outperforms a strong baseline in both automatic metrics and LLM-based evaluations, producing more accurate, structured, and interpretable reports. This work highlights the potential of clinically aligned multi-agent frameworks to support explainable and trustworthy clinical AI applications.

Value function decomposition methods for cooperative multi-agent reinforcement learning compose joint values from individual per-agent utilities, and train them using a joint objective. To ensure that the action selection process between individual utilities and joint values remains consistent, it is imperative for the composition to satisfy the individual-global max (IGM) property. Although satisfying IGM itself is straightforward, most existing methods (e.g., VDN, QMIX) have limited representation capabilities and are unable to represent the full class of IGM values, and the one exception that has no such limitation (QPLEX) is unnecessarily complex. In this work, we present a simple formulation of the full class of IGM values that naturally leads to the derivation of QFIX, a novel family of value function decomposition models that expand the representation capabilities of prior models by means of a thin "fixing" layer. We derive multiple variants of QFIX, and implement three variants in two well-known multi-agent frameworks. We perform an empirical evaluation on multiple SMACv2 and Overcooked environments, which confirms that QFIX (i) succeeds in enhancing the performance of prior methods, (ii) learns more stably and performs better than its main competitor QPLEX, and (iii) achieves this while employing the simplest and smallest mixing models.

The growing adoption of Electric Buses (EBs) represents a significant step toward sustainable development. By utilizing Internet of Things (IoT) systems, charging stations can autonomously determine charging schedules based on real-time data. However, optimizing EB charging schedules remains a critical challenge due to uncertainties in travel time, energy consumption, and fluctuating electricity prices. Moreover, to address real-world complexities, charging policies must make decisions efficiently across multiple time scales and remain scalable for large EB fleets. In this paper, we propose a Hierarchical Deep Reinforcement Learning (HDRL) approach that reformulates the original Markov Decision Process (MDP) into two augmented MDPs. To solve these MDPs and enable multi-timescale decision-making, we introduce a novel HDRL algorithm, namely Double Actor-Critic Multi-Agent Proximal Policy Optimization Enhancement (DAC-MAPPO-E). Scalability challenges of the Double Actor-Critic (DAC) algorithm for large-scale EB fleets are addressed through enhancements at both decision levels. At the high level, we redesign the decentralized actor network and integrate an attention mechanism to extract relevant global state information for each EB, decreasing the size of neural networks. At the low level, the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm is incorporated into the DAC framework, enabling decentralized and coordinated charging power decisions, reducing computational complexity and enhancing convergence speed. Extensive experiments with real-world data demonstrate the superior performance and scalability of DAC-MAPPO-E in optimizing EB fleet charging schedules.

This work investigates the problem of best arm identification for multi-agent multi-armed bandits. We consider $N$ agents grouped into $M$ clusters, where each cluster solves a stochastic bandit problem. The mapping between agents and bandits is a priori unknown. Each bandit is associated with $K$ arms, and the goal is to identify the best arm for each agent under a $δ$-probably correct ($δ$-PC) framework, while minimizing sample complexity and communication overhead. We propose two novel algorithms: Clustering then Best Arm Identification (Cl-BAI) and Best Arm Identification then Clustering (BAI-Cl). Cl-BAI uses a two-phase approach that first clusters agents based on the bandit problems they are learning, followed by identifying the best arm for each cluster. BAI-Cl reverses the sequence by identifying the best arms first and then clustering agents accordingly. Both algorithms leverage the successive elimination framework to ensure computational efficiency and high accuracy. We establish $δ$-PC guarantees for both methods, derive bounds on their sample complexity, and provide a lower bound for this problem class. Moreover, when $M$ is small (a constant), we show that the sample complexity of a variant of BAI-Cl is minimax optimal in an order-wise sense. Experiments on synthetic and real-world datasets (MovieLens, Yelp) demonstrate the superior performance of the proposed algorithms in terms of sample and communication efficiency, particularly in settings where $M \ll N$.

The rapid development of generative artificial intelligence (GenAI) presents new opportunities to advance the cartographic process. Previous studies have either overlooked the artistic aspects of maps or faced challenges in creating both accurate and informative maps. In this study, we propose CartoAgent, a novel multi-agent cartographic framework powered by multimodal large language models (MLLMs). This framework simulates three key stages in cartographic practice: preparation, map design, and evaluation. At each stage, different MLLMs act as agents with distinct roles to collaborate, discuss, and utilize tools for specific purposes. In particular, CartoAgent leverages MLLMs' visual aesthetic capability and world knowledge to generate maps that are both visually appealing and informative. By separating style from geographic data, it can focus on designing stylesheets without modifying the vector-based data, thereby ensuring geographic accuracy. We applied CartoAgent to a specific task centered on map restyling-namely, map style transfer and evaluation. The effectiveness of this framework was validated through extensive experiments and a human evaluation study. CartoAgent can be extended to support a variety of cartographic design decisions and inform future integrations of GenAI in cartography.