Robust coordination is critical for effective decision-making in multi-agent systems, especially under partial observability. A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or learn them end-to-end. We investigate this dichotomy using embodied world models. We propose and compare two communication strategies for a cooperative task-allocation problem. The first, Learned Direct Communication (LDC), learns a protocol end-to-end. The second, Intention Communication, uses an engineered inductive bias: a compact, learned world model, the Imagined Trajectory Generation Module (ITGM), which uses the agent's own policy to simulate future states. A Message Generation Network (MGN) then compresses this plan into a message. We evaluate these approaches on goal-directed interaction in a grid world, a canonical abstraction for embodied AI problems, while scaling environmental complexity. Our experiments reveal that while emergent communication is viable in simple settings, the engineered, world model-based approach shows superior performance, sample efficiency, and scalability as complexity increases. These findings advocate for integrating structured, predictive models into MARL agents to enable active, goal-driven coordination.

High-performance computing (HPC) and parallel computing increasingly rely on global collaboration among diverse teams, yet traditional computing curricula inadequately prepare students for cross-cultural teamwork essential in modern computational research environments. This paper presents Empa, an AI-powered virtual mentor that integrates intercultural collaboration training into undergraduate computing education. Built using large language models and deployed through a progressive web application, Empa guides students through structured activities covering cultural dimensions, communication styles, and conflict resolution that are critical for effective multicultural teamwork. Our system addresses the growing need for culturally competent HPC professionals by helping computing students develop skills to collaborate effectively in international research teams, contribute to global computational projects, and navigate the cultural complexities inherent in distributed computing environments. Pilot preparation for deployment in computing courses demonstrates the feasibility of AI-mediated intercultural training and provides insights into scalable approaches for developing intercultural collaboration skills essential for HPC workforce development.

Achieving consensus among noncooperative agents remains challenging in decentralized multi-agent systems, where agents often have conflicting preferences. Existing coordination methods enable agents to reach consensus without a centralized coordinator, but do not provide formal guarantees on system-level objectives such as efficiency or fairness. To address this limitation, we propose an iterative negotiation and oversight framework that augments a decentralized negotiation mechanism with taxation-like oversight. The framework builds upon the trading auction for consensus, enabling noncooperative agents with conflicting preferences to negotiate through asset trading while preserving valuation privacy. We introduce an oversight mechanism, which implements a taxation-like intervention that guides decentralized negotiation toward system-efficient and equitable outcomes while also regulating how fast the framework converges. We establish theoretical guarantees of finite-time termination and derive bounds linking system efficiency and convergence rate to the level of central intervention. A case study based on the collaborative trajectory options program, a rerouting initiative in U.S. air traffic management, demonstrates that the framework can reliably achieve consensus among noncooperative airspace sector managers, and reveals how the level of intervention regulates the relationship between system efficiency and convergence speed. Taken together, the theoretical and experimental results indicate that the proposed framework provides a general mechanism for decentralized coordination in noncooperative multi-agent systems while safeguarding system-level objectives.

The consensus strategies used in collaborative multi-agent systems (MAS) face notable challenges related to adaptability, scalability, and convergence certainties. These approaches, including structured workflows, debate models, and iterative voting, often lead to communication bottlenecks, stringent decision-making processes, and delayed responses in solving complex and evolving tasks. This article introduces a three-tier architecture, the Hierarchical Adaptive Consensus Network (\hacn), which suggests various consensus policies based on task characterization and agent performance metrics. The first layer collects the confidence-based voting outcomes of several local agent clusters. In contrast, the second level facilitates inter-cluster communication through cross-clustered partial knowledge sharing and dynamic timeouts. The third layer provides system-wide coordination and final arbitration by employing a global orchestration framework with adaptable decision rules. The proposed model achieves $\bigO(n)$ communication complexity, as opposed to the $\bigO(n^2)$ complexity of the existing fully connected MAS. Experiments performed in a simulated environment yielded a 99.9\% reduction in communication overhead during consensus convergence. Furthermore, the proposed approach ensures consensus convergence through hierarchical escalation and dynamic adaptation for a wide variety of complicated tasks.

Neural Information Processing Systems http://nips.cc/

As Multi Agent Reinforcement Learning systems are used in safety critical applications. Understanding why agents make decisions and how they achieve collective behavior is crucial. Existing explainable AI methods struggle in multi agent settings. They fail to attribute collective outcomes to individuals, quantify emergent behaviors, or capture complex interactions. We present MACIE Multi Agent Causal Intelligence Explainer, a framework combining structural causal models, interventional counterfactuals, and Shapley values to provide comprehensive explanations. MACIE addresses three questions. First, each agent's causal contribution using interventional attribution scores. Second, system level emergent intelligence through synergy metrics separating collective effects from individual contributions. Third, actionable explanations using natural language narratives synthesizing causal insights. We evaluate MACIE across four MARL scenarios: cooperative, competitive, and mixed motive. Results show accurate outcome attribution, mean phi_i equals 5.07, standard deviation less than 0.05, detection of positive emergence in cooperative tasks, synergy index up to 0.461, and efficient computation, 0.79 seconds per dataset on CPU. MACIE uniquely combines causal rigor, emergence quantification, and multi agent support while remaining practical for real time use. This represents a step toward interpretable, trustworthy, and accountable multi agent AI.

Neural Information Processing Systems http://nips.cc/

Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas.

Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains. The effectiveness of MAS is critically dependent on its collaboration topology, which has become a focal point for automated design research. However, existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures, significantly limiting their adaptability to task-specific requirements. To address these limitations, we reframe MAS design as a conditional autoregressive graph generation task, where both the system composition and structure are designed jointly. We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch. Conditioned on a natural language task query, ARG-Designer sequentially and dynamically determines the required number of agents, selects their appropriate roles from an extensible pool, and establishes the optimal communication links between them. This generative approach creates a customized topology in a flexible and extensible manner, precisely tailored to the unique demands of different tasks. Extensive experiments across six diverse benchmarks demonstrate that ARG-Designer not only achieves state-of-the-art performance but also enjoys significantly greater token efficiency and enhanced extensibility. The source code of ARG-Designer is available at https://github.com/Shiy-Li/ARG-Designer.

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g., impracticality due to the requirement of white-box information or high control authority, and a lack of stealthiness or effectiveness as they often target all agents or specific fixed agents. To address these issues, we propose AdapAM, a novel framework for adversarial attacks on black-box MAS. AdapAM incorporates two key components: (1) Adaptive Selection Policy simultaneously selects the victim and determines the anticipated malicious action (the action would lead to the worst impact on MAS), balancing effectiveness and stealthiness. (2) Proxy-based Perturbation to Induce Malicious Action utilizes generative adversarial imitation learning to approximate the target MAS, allowing AdapAM to generate perturbed observations using white-box information and thus induce victims to execute malicious action in black-box settings. We evaluate AdapAM across eight multi-agent environments and compare it with four state-of-the-art and commonly-used baselines. Results demonstrate that AdapAM achieves the best attack performance in different perturbation rates. Besides, AdapAM-generated perturbations are the least noisy and hardest to detect, emphasizing the stealthiness.