mlsanityData to 7 Oct 2026

Emergent Multi-Agent Communication in the Deep Learning Era

arXiv 2006.02419 ↗First posted 3 Jun 2020cs.CL cs.AIcited by 168

Not on the map. Why?

Cited by 21 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The ability to cooperate through language is a defining feature of humans. As the perceptual, motory and planning capabilities of deep artificial networks increase, researchers are studying whether they also can develop a shared language to interact. From a scientific perspective, understanding the conditions under which language evolves in communities of deep agents and its emergent features can shed light on human language evolution. From an applied perspective, endowing deep networks with the ability to solve problems interactively by communicating with each other and with us should make them more flexible and useful in everyday life. This article surveys representative recent language emergence studies from both of these two angles.

Key facts. Cited by 168 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 28; 2023: 32; 2024: 26; 2025: 28; 2026: 35.

168 papers.

Sort:

By area:

  1. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  2. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 103
  3. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 97
  4. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  5. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  6. 2024MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debatecited by 54
  7. 2024Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMscited by 52
  8. 2024A Scalable Communication Protocol for Networks of Large Language Modelscited by 43
  9. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  10. 2021Emergent Communication of Generalizationscited by 41
  11. 2023Language Model Alignment with Elastic Resetcited by 34
  12. 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
38 more
  1. 2021Interpretable agent communication from scratch (with a generic visual processor emerging on the side)cited by 25
  2. 2025Large Language Models Miss the Multi-Agent Markcited by 25
  3. 2021Symbolic Behaviour in Artificial Intelligencecited by 24
  4. 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
  5. 2021Semantics-Native Communication with Contextual Reasoningcited by 21
  6. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  7. 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
  8. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  9. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  10. 2023Generative Models as a Complex Systems Science: How can we make sense of large language model behavior?cited by 19
  11. 2021Emergent Communication under Competitioncited by 17
  12. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  13. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  14. 2025LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planningcited by 17
  15. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  16. 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
  17. 2023Computational Language Acquisition with Theory of Mindcited by 15
  18. 2024Generative Emergent Communication: Large Language Model is a Collective World Modelcited by 15
  19. 2021The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learningcited by 14
  20. 2022Learning to Mediate Disparities Towards Pragmatic Communicationcited by 14
  21. 2023What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structurecited by 13
  22. 2022Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approachescited by 12
  23. 2023Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-offcited by 12
  24. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  25. 2022Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RLcited by 11
  26. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  27. 2023Referential communication in heterogeneous communities of pre-trained visual deep networkscited by 10
  28. 2023EC^2: Emergent Communication for Embodied Controlcited by 10
  29. 2024Searching for Structure: Investigating Emergent Communication with Large Language Modelscited by 10
  30. 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
  31. 2023Learning Multi-Agent Communication with Contrastive Learningcited by 9
  32. 2023Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networkscited by 9
  33. 2025Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communicationcited by 9
  34. 2026Latent Space Communication via K-V Cache Alignmentcited by 9
  35. 2021Extending rational models of communication from beliefs to actionscited by 8
  36. 2022Emergence of hierarchical reference systems in multi-agent communicationcited by 8
  37. 2024NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communicationcited by 8
  38. 2022Towards Human-Agent Communication via the Information Bottleneck Principlecited by 7

50 most cited of 168 All 168 (JSON)