Related papers: Towards Human-Agent Communication via the Informat…

Multi-agent Large Language Model (LLM) systems face a critical bottleneck: redundant transmission of contextual information between agents consumes excessive bandwidth and computational resources. Traditional approaches discard internal…

For six decades, software engineering principles have been optimized for a single consumer: the human developer. The rise of agentic AI development, where LLM-based agents autonomously read, write, navigate, and debug codebases, introduces…

Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like generalization, interpretability, and inter-operability with human users. Inspired by the rich interactions…

This paper describes a novel design of a neural network-based speech generation model for learning prosodic representation.The problem of representation learning is formulated according to the information bottleneck (IB) principle. A…

We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or…

Semantic communication shifts the focus from bit-level accuracy to task-relevant semantic delivery, enabling efficient and intelligent communication for next-generation networks. However, existing multi-modal solutions often process all…

Bayesian Inference and Information Bottleneck are the two most popular objectives for neural networks, but they can be optimised only via a variational lower bound: the Variational Information Bottleneck (VIB). In this manuscript we show…

In the recent shift towards human-centric AI, the need for machines to accurately use natural language has become increasingly important. While a common approach to achieve this is to train large language models, this method presents a form…

Emergent communication has made strides towards learning communication from scratch, but has focused primarily on protocols that resemble human language. In nature, multi-agent cooperation gives rise to a wide range of communication that…

In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is…

Human languages provide efficient systems for expressing numerosities, but whether the sheer pressure to communicate is enough for numerical representations to arise in artificial agents, and whether the emergent codes resemble human…

Information exchange in multi-agent systems improves the cooperation among agents, especially in partially observable settings. In the real world, communication is often carried out over imperfect channels. This requires agents to handle…

Large Language Models (LLMs) have become foundational to modern AI agent systems, enabling autonomous agents to reason and plan. In most existing systems, inter-agent communication relies primarily on natural language. While this design…

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…

To effectively study complex causal systems, it is often useful to construct abstractions of parts of the system by discarding irrelevant details while preserving key features. The Information Bottleneck (IB) method is a widely used…

One of the distinguishing aspects of human language is its compositionality, which allows us to describe complex environments with limited vocabulary. Previously, it has been shown that neural network agents can learn to communicate in a…

Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and…

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn…

Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is using the Expectation Maximization (EM) algorithm. This…

Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…