Emergent Linguistic Phenomena in Multi-Agent Communication Games
Not on the map. Why?
Abstract (arXiv)
In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. We demonstrate that the framework mirrors linguistic phenomena observed in natural language: i) the outcome of contact between communities is a function of inter- and intra-group connectivity; ii) linguistic contact either converges to the majority protocol, or in balanced cases leads to novel creole languages of lower complexity; and iii) a linguistic continuum emerges where neighboring languages are more mutually intelligible than farther removed languages. We conclude that intricate properties of language evolution need not depend on complex evolved linguistic capabilities, but can emerge from simple social exchanges between perceptually-enabled agents playing communication games.
Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jan 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 7; 2023: 5; 2024: 6; 2025: 6; 2026: 4.
36 papers.
Sort:
By area:
- 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 89
- 2025SPICE: Self-Play In Corpus Environments Improves Reasoningcited by 78
- 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
- 2024LLM Harmony: Multi-Agent Communication for Problem Solvingcited by 34
- 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
- 2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
- 2025Large Language Models Miss the Multi-Agent Markcited by 25
- 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
- 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
- 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
- 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
- 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
24 more
- 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
- 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
- 2021Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictabilitycited by 11
- 2021Dynamic population-based meta-learning for multi-agent communication with natural languagecited by 10
- 2023Referential communication in heterogeneous communities of pre-trained visual deep networkscited by 10
- 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
- 2021Calibrate your listeners! Robust communication-based training for pragmatic speakerscited by 9
- 2023Learning Multi-Agent Communication with Contrastive Learningcited by 9
- 2025Spontaneous Giving and Calculated Greed in Language Modelscited by 9
- 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
- 2022Trust-based Consensus in Multi-Agent Reinforcement Learning Systemscited by 6
- 2024Language Evolution with Deep Learningcited by 5
- 2022Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learningcited by 4
- 2022Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networkscited by 3
- 2023Do learned speech symbols follow Zipf's law?cited by 3
- 2022Recommendations for Systematic Research on Emergent Languagecited by 2
- 2024Bidirectional Emergent Language in Situated Environmentscited by 1
- 2025From Grunts to Lexicons: Emergent Language from Cooperative Foragingcited by 1
- 2023Emergent Communication for Rules Reasoningcited by 0
- 2024Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scalecited by 0
- 2025VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantizationcited by 0
- 2026Modeling Human-Like Color Naming Behavior in Contextcited by 0
- 2026Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketchingcited by 0
- 2026From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvementcited by 0
- 2026From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement26 Jul 2026
- 2026Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching9 Jun 2026
- 2026Modeling Human-Like Color Naming Behavior in Context28 Apr 2026
- 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs12 Feb 2026
- 2025SPICE: Self-Play In Corpus Environments Improves Reasoning28 Oct 2025
- 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning30 Jun 2025
- 2025Large Language Models Miss the Multi-Agent Mark27 May 2025
- 2025From Grunts to Lexicons: Emergent Language from Cooperative Foraging19 May 2025
- 2025VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization6 Mar 2025
- 2025Spontaneous Giving and Calculated Greed in Language Models24 Feb 2025
- 2024Bidirectional Emergent Language in Situated Environments26 Aug 2024
- 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication19 Jul 2024
24 more
- 2024A Review of the Applications of Deep Learning-Based Emergent Communication3 Jul 2024
- 2024Language Evolution with Deep Learning18 Mar 2024
- 2024Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale16 Jan 2024
- 2024LLM Harmony: Multi-Agent Communication for Problem Solving2 Jan 2024
- 2023Emergent Communication for Rules Reasoning8 Nov 2023
- 2023Do learned speech symbols follow Zipf's law?18 Sep 2023
- 2023Towards More Human-like AI Communication: A Review of Emergent Communication Research1 Aug 2023
- 2023Learning Multi-Agent Communication with Contrastive Learning3 Jul 2023
- 2023Referential communication in heterogeneous communities of pre-trained visual deep networks4 Feb 2023
- 2022Emergent Communication: Generalization and Overfitting in Lewis Games30 Sep 2022
- 2022Recommendations for Systematic Research on Emergent Language22 Jun 2022
- 2022Trust-based Consensus in Multi-Agent Reinforcement Learning Systems25 May 2022
- 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models24 May 2022
- 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?22 Apr 2022
- 2022Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning7 Mar 2022
- 2022Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks14 Jan 2022
- 2021Emergent Graphical Conventions in a Visual Communication Game28 Nov 2021
- 2021Learning to Ground Multi-Agent Communication with Autoencoders28 Oct 2021
- 2021Dynamic population-based meta-learning for multi-agent communication with natural language27 Oct 2021
- 2021Calibrate your listeners! Robust communication-based training for pragmatic speakers11 Oct 2021
- 2021The Emergence of the Shape Bias Results from Communicative Efficiency13 Sep 2021
- 2021Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability7 Jun 2021
- 2021From partners to populations: A hierarchical Bayesian account of coordination and convention12 Apr 2021
- 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communication14 Mar 2021
- 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learningcited by 89
- 2025Spontaneous Giving and Calculated Greed in Language Modelscited by 9
- 2026From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvementcited by 0
- 2026From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement26 Jul 2026
- 2025SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning30 Jun 2025
- 2025Spontaneous Giving and Calculated Greed in Language Models24 Feb 2025
- 2025SPICE: Self-Play In Corpus Environments Improves Reasoningcited by 78
- 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
- 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
- 2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
- 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
- 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
- 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
- 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
- 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
- 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
- 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
- 2021Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictabilitycited by 11
12 most cited of 30 All 30 (JSON)
- 2026Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching9 Jun 2026
- 2026Modeling Human-Like Color Naming Behavior in Context28 Apr 2026
- 2025SPICE: Self-Play In Corpus Environments Improves Reasoning28 Oct 2025
- 2025From Grunts to Lexicons: Emergent Language from Cooperative Foraging19 May 2025
- 2025VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization6 Mar 2025
- 2024Bidirectional Emergent Language in Situated Environments26 Aug 2024
- 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication19 Jul 2024
- 2024A Review of the Applications of Deep Learning-Based Emergent Communication3 Jul 2024
- 2024Language Evolution with Deep Learning18 Mar 2024
- 2024Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale16 Jan 2024
- 2023Emergent Communication for Rules Reasoning8 Nov 2023
- 2023Do learned speech symbols follow Zipf's law?18 Sep 2023
12 newest of 30 All 30 (JSON)