Emergent Language: A Survey and Taxonomy
arXiv:2409.02645 · doi:10.1007/s10458-025-09691-y
Abstract
The field of emergent language represents a novel area of research within the domain of artificial intelligence, particularly within the context of multi-agent reinforcement learning. Although the concept of studying language emergence is not new, early approaches were primarily concerned with explaining human language formation, with little consideration given to its potential utility for artificial agents. In contrast, studies based on reinforcement learning aim to develop communicative capabilities in agents that are comparable to or even superior to human language. Thus, they extend beyond the learned statistical representations that are common in natural language processing research. This gives rise to a number of fundamental questions, from the prerequisites for language emergence to the criteria for measuring its success. This paper addresses these questions by providing a comprehensive review of 181 scientific publications on emergent language in artificial intelligence. Its objective is to serve as a reference for researchers interested in or proficient in the field. Consequently, the main contributions are the definition and overview of the prevailing terminology, the analysis of existing evaluation methods and metrics, and the description of the identified research gaps.
published in Journal of Autonomous Agents and Multi-Agent Systems
References in corpus (81)
- Natural Language Processing: State of The Art, Current Trends and Challenges
- A Survey on Large Language Model based Autonomous Agents
- Pre-trained Models for Natural Language Processing: A Survey
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- A Survey and Critique of Multiagent Deep Reinforcement Learning
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Learning Multiagent Communication with Backpropagation
- Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
- The Hanabi Challenge: A New Frontier for AI Research
- Multi-Agent Cooperation and the Emergence of (Natural) Language
- Anti-efficient encoding in emergent communication
- Cognitive Architectures for Language Agents
- BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
- Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration
- Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
- Improving Coordination in Small-Scale Multi-Agent Deep Reinforcement Learning through Memory-driven Communication
- Compositional Languages Emerge in a Neural Iterated Learning Model
- Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
- On the interaction between supervision and self-play in emergent communication
- Biases for Emergent Communication in Multi-agent Reinforcement Learning
- Emergence of Communication in an Interactive World with Consistent Speakers
- Emergent Communication in a Multi-Modal, Multi-Step Referential Game
- Developmentally motivated emergence of compositional communication via template transfer
- Measuring Compositionality in Representation Learning
- Mind the Gap: Assessing Temporal Generalization in Neural Language Models
- The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning
- The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
- Learning to Ground Multi-Agent Communication with Autoencoders
- Ease-of-Teaching and Language Structure from Emergent Communication
- Strategies for fast convergence in semiotic dynamics
- Emergence of linguistic conventions in multi-agent reinforcement learning
- Shaping representations through communication: community size effect in artificial learning systems
- Morphology Matters: A Multilingual Language Modeling Analysis
- Towards More Human-like AI Communication: A Review of Emergent Communication Research
- Emergence of Pragmatics from Referential Game between Theory of Mind Agents
- Emergent Communication Pretraining for Few-Shot Machine Translation
- Towards Human-Agent Communication via the Information Bottleneck Principle
- Emergence of Theory of Mind Collaboration in Multiagent Systems
- Networked Multi-Agent Reinforcement Learning with Emergent Communication
- Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
- Interpretable Learned Emergent Communication for Human-Agent Teams
- Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
- Measuring non-trivial compositionality in emergent communication
- Emergent Discrete Communication in Semantic Spaces
- Linking Emergent and Natural Languages via Corpus Transfer
- Establishing linguistic conventions in task-oriented primeval dialogue
- ESCELL: Emergent Symbolic Cellular Language
- Incorporating Pragmatic Reasoning Communication into Emergent Language
- Reinforcement Communication Learning in Different Social Network Structures
- Mutual influence between language and perception in multi-agent communication games
- Learning to Communicate Using Counterfactual Reasoning
- Emergent Graphical Conventions in a Visual Communication Game
- Learning to Draw: Emergent Communication through Sketching
- Inductive Bias and Language Expressivity in Emergent Communication
- A Practical Guide to Studying Emergent Communication through Grounded Language Games
- Dynamic population-based meta-learning for multi-agent communication with natural language
- Re-conceptualising the Language Game Paradigm in the Framework of Multi-Agent Reinforcement Learning
- On the role of population heterogeneity in emergent communication
- Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
- Avoiding hashing and encouraging visual semantics in referential emergent language games
- Analyzing Language Learned by an Active Question Answering Agent
- Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
- Emergence of Numeric Concepts in Multi-Agent Autonomous Communication
- Vehicle Communication Strategies for Simulated Highway Driving
- Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning
- A perspective on multi-agent communication for information fusion
- An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning
- Emergent Communication: Generalization and Overfitting in Lewis Games
- On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator
- Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability
- Winning an Election: On Emergent Strategic Communication in Multi-Agent Networks
- Biology and Compositionality: Empirical Considerations for Emergent-Communication Protocols
- Multi-Agent Curricula and Emergent Implicit Signaling
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
- Multi-Agent Reinforcement Learning as a Computational Tool for Language Evolution Research: Historical Context and Future Challenges
- Inductive Bias for Emergent Communication in a Continuous Setting
- Emergence of Writing Systems Through Multi-Agent Cooperation
- Emergent Communication in Interactive Sketch Question Answering
- Learning to Communicate with Strangers via Channel Randomisation Methods
- Multi-lingual agents through multi-headed neural networks
- Modeling Emergent Lexicon Formation with a Self-Reinforcing Stochastic Process