Related papers: Minimum Coverage Sets for Training Robust Ad Hoc T…

We consider a cooperative multi-agent system consisting of a team of agents with decentralized information. Our focus is on the design of symmetric (i.e. identical) strategies for the agents in order to optimize a finite horizon team…

Here we consider the communications tactics appropriate for a group of agents that need to "swarm" together in a highly adversarial environment. Specfically, whilst they need to cooperate by exchanging information with each other about…

We propose an improved algorithm by identifying and encouraging cooperative behavior in multi-agent environments. First, we analyze the shortcomings of existing algorithms in addressing multi-agent reinforcement learning problems. Then,…

We study the problem of control synthesis for multi-agent systems, to achieve complex, high-level, long-term goals that are assigned to each agent individually. As the agents might not be capable of satisfying their respective goals by…

We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual…

This paper presents an extension of the Mirror Descent method to overcome challenges in cooperative Multi-Agent Reinforcement Learning (MARL) settings, where agents have varying abilities and individual policies. The proposed…

In collaborative tasks, being able to adapt to your teammates is a necessary requirement for success. When teammates are heterogeneous, such as in human-agent teams, agents need to be able to observe, recognize, and adapt to their human…

Whether in groups of humans or groups of computer agents, collaboration is most effective between individuals who have the ability to coordinate on a joint strategy for collective action. However, in general a rational actor will only…

This paper investigates the problem of cooperative tuning of multi-agent optimal control systems, where a network of agents (i.e. multiple coupled optimal control systems) adjusts parameters in their dynamics, objective functions, or…

Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme,where all…

Real-world multi-agent systems may require ad hoc teaming, where an agent must coordinate with other previously unseen teammates to solve a task in a zero-shot manner. Prior work often either selects a pretrained policy based on an inferred…

In open multi-agent environments, the agents may encounter unexpected teammates. Classical multi-agent learning approaches train agents that can only coordinate with seen teammates. Recent studies attempted to generate diverse teammates to…

This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and…

Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels…

We address the problem of maintaining resource availability in a networked multi-robot team performing distributed tracking of unknown number of targets in an environment of interest. Based on our model, robots are equipped with sensing and…

Intent-based management will play a critical role in achieving customers' expectations in the next-generation mobile networks. Traditional methods cannot perform efficient resource management since they tend to handle each expectation…

Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts the result it claims to measure. This failure is not isolated: learned critics, trajectory-level…

Adversarial training has proven to be a highly effective method for improving the robustness of deep neural networks against adversarial attacks. Nonetheless, it has been observed to exhibit a limitation in terms of robust fairness,…

Despite the significant progress in multiagent teamwork, existing research does not address the optimality of its prescriptions nor the complexity of the teamwork problem. Without a characterization of the optimality-complexity tradeoffs,…