mlsanityData to 14 Oct 2026

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

arXiv 1804.03984 ↗First posted 11 Apr 2018cs.AI cs.CL cs.LGcited by 102

Not on the map. Why?

Abstract (arXiv)

The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent communication tasks. Here we scale up this research by using contemporary deep learning methods and by training reinforcement-learning neural network agents on referential communication games. We extend previous work, in which agents were trained in symbolic environments, by developing agents which are able to learn from raw pixel data, a more challenging and realistic input representation. We find that the degree of structure found in the input data affects the nature of the emerged protocols, and thereby corroborate the hypothesis that structured compositional language is most likely to emerge when agents perceive the world as being structured.

Key facts. Cited by 102 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 26; 2022: 16; 2023: 17; 2024: 19; 2025: 13; 2026: 11.

102 papers.

Sort:

By area:

  1. 2024Emergent social conventions and collective bias in LLM populationscited by 123
  2. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 99
  3. 2024A Scalable Communication Protocol for Networks of Large Language Modelscited by 45
  4. 2021Emergent Communication of Generalizationscited by 42
  5. 2022Fortuitous Forgetting in Connectionist Networkscited by 39
  6. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  7. 2025Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Playcited by 37
  8. 2025Enabling Agents to Communicate Entirely in Latent Spacecited by 34
  9. 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
  10. 2021Interpretable agent communication from scratch (with a generic visual processor emerging on the side)cited by 25
  11. 2021Learning to Draw: Emergent Communication through Sketchingcited by 23
  12. 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
38 more
  1. 2021Iterated learning for emergent systematicity in VQAcited by 21
  2. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  3. 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
  4. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  5. 2021Emergent Communication under Competitioncited by 18
  6. 2024Iterated Learning Improves Compositionality in Large Vision-Language Modelscited by 17
  7. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  8. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  9. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  10. 2021HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solvingcited by 15
  11. 2024On The Specialization of Neural Modulescited by 14
  12. 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
  13. 2023What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structurecited by 13
  14. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 13
  15. 2021Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communicationcited by 12
  16. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  17. 2021Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictabilitycited by 11
  18. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  19. 2021Communicating via Markov Decision Processescited by 10
  20. 2021Dynamic population-based meta-learning for multi-agent communication with natural languagecited by 10
  21. 2023EC^2: Emergent Communication for Embodied Controlcited by 10
  22. 2023Learning Multi-Agent Communication with Contrastive Learningcited by 9
  23. 2021Emergence of Theory of Mind Collaboration in Multiagent Systemscited by 8
  24. 2022Emergence of hierarchical reference systems in multi-agent communicationcited by 8
  25. 2022Towards Human-Agent Communication via the Information Bottleneck Principlecited by 8
  26. 2023Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Modelscited by 8
  27. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  28. 2022Emergent Quantized Communicationcited by 7
  29. 2024Concept-Best-Matching: Evaluating Compositionality in Emergent Communicationcited by 7
  30. 2024The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communicationcited by 7
  31. 2021The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learningcited by 6
  32. 2022MA-Dreamer: Coordination and communication through shared imaginationcited by 6
  33. 2022Trust-based Consensus in Multi-Agent Reinforcement Learning Systemscited by 6
  34. 2021The emergence of visual semantics through communication gamescited by 5
  35. 2023Visual Referential Games Further the Emergence of Disentangled Representationscited by 5
  36. 2024Language Evolution with Deep Learningcited by 5
  37. 2021Neural networks can understand compositional functions that humans do not, in the context of emergent communicationcited by 4
  38. 2021Learning to Communicate with Strangers via Channel Randomisation Methodscited by 4

50 most cited of 102 All 102 (JSON)