Related papers: Model Proficiency in Centralized Multi-Agent Syste…

Multi-agent actor-critic algorithms are an important part of the Reinforcement Learning paradigm. We propose three fully decentralized multi-agent natural actor-critic (MAN) algorithms in this work. The objective is to collectively find a…

We present three generalisations of Kernel Principal Components Analysis (KPCA) which incorporate knowledge of the class labels of a subset of the data points. The first, MV-KPCA, penalises within class variances similar to Fisher…

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…

Coupling arguments are a central tool for bounding the deviation between two stochastic processes, but traditionally have been limited to Wasserstein metrics. In this paper, we apply the shifted composition rule--an information-theoretic…

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly…

The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural frameworks, the granular…

When learning a task as a team, some agents in Multi-Agent Reinforcement Learning (MARL) may fail to understand their true impact in the performance of the team. Such agents end up learning sub-optimal policies, demonstrating undesired lazy…

This paper addresses the problem of distributed detection in fixed and switching networks. A network of agents observe partially informative signals about the unknown state of the world. Hence, they collaborate with each other to identify…

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

Uncontrollable autonomous replication of language model agents poses a critical safety risk. To better understand this risk, we introduce RepliBench, a suite of evaluations designed to measure autonomous replication capabilities. RepliBench…

In this paper, we propose a mathematical model for a Transactive Memory System (TMS) involved in the cooperative process of learning a task. The model is based on an intertwined dynamics involving both the individuals level of expertise and…

Estimating the Kullback--Leibler (KL) divergence between language models has many applications, e.g., reinforcement learning from human feedback (RLHF), interpretability, and knowledge distillation. However, computing the exact KL…

In this work, we investigate constrained multi-agent reinforcement learning (CMARL), where agents collaboratively maximize the sum of their local objectives while satisfying individual safety constraints. We propose a framework where agents…

Does reinforcement learning genuinely expand what LLM agents can do, or merely make them more reliable? For static reasoning, recent work answers the second: base and RL pass@k curves converge at large k. We ask whether this holds for…

Multi-agent systems (MASs) can autonomously learn to solve previously unknown tasks by means of each agent's individual intelligence as well as by collaborating and exploiting collective intelligence. This article considers a group of…

Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative…

The global rise in homelessness calls for urgent and alternative policy solutions. Non-profits and governmental organizations alert about the many challenges faced by people experiencing homelessness (PEH), which include not only the lack…

Multi-agent Markov Decision Processes (MMDPs) arise in a variety of applications including target tracking, control of multi-robot swarms, and multiplayer games. A key challenge in MMDPs occurs when the state and action spaces grow…