mlsanityData to 7 Oct 2026

Multi-Agent Cooperation and the Emergence of (Natural) Language

arXiv 1612.07182 ↗First posted 21 Dec 2016cs.CL cs.CV cs.GTcited by 181

Not on the map. Why?

Cited by 26 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The current mainstream approach to train natural language systems is to expose them to large amounts of text. This passive learning is problematic if we are interested in developing interactive machines, such as conversational agents. We propose a framework for language learning that relies on multi-agent communication. We study this learning in the context of referential games. In these games, a sender and a receiver see a pair of images. The sender is told one of them is the target and is allowed to send a message from a fixed, arbitrary vocabulary to the receiver. The receiver must rely on this message to identify the target. Thus, the agents develop their own language interactively out of the need to communicate. We show that two networks with simple configurations are able to learn to coordinate in the referential game. We further explore how to make changes to the game environment to cause the "word meanings" induced in the game to better reflect intuitive semantic properties of the images. In addition, we present a simple strategy for grounding the agents' code into natural language. Both of these are necessary steps towards developing machines that are able to communicate with humans productively.

Key facts. Cited by 181 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 24; 2023: 36; 2024: 24; 2025: 24; 2026: 38.

181 papers.

Sort:

By area:

  1. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  2. 2024Emergent social conventions and collective bias in LLM populationscited by 115
  3. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  4. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agentscited by 66
  5. 2024Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitatecited by 46
  6. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  7. 2021Emergent Communication of Generalizationscited by 41
  8. 2021Word Acquisition in Neural Language Modelscited by 41
  9. 2024Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent Systemcited by 40
  10. 2022Fortuitous Forgetting in Connectionist Networkscited by 39
  11. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Modelscited by 33
  12. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
38 more
  1. 2025Enabling Agents to Communicate Entirely in Latent Spacecited by 31
  2. 2022Emergent Communication: Generalization and Overfitting in Lewis Gamescited by 28
  3. 2021Interactive Learning from Activity Descriptioncited by 26
  4. 2021On the Critical Role of Conventions in Adaptive Human-AI Collaborationcited by 26
  5. 2021Interpretable agent communication from scratch (with a generic visual processor emerging on the side)cited by 25
  6. 2022Scalable Multi-Agent Model-Based Reinforcement Learningcited by 24
  7. 2021Learning to Draw: Emergent Communication through Sketchingcited by 23
  8. 2022Emergent Communication for Understanding Human Language Evolution: What's Missing?cited by 23
  9. 2021Iterated learning for emergent systematicity in VQAcited by 21
  10. 2021Semantics-Native Communication with Contextual Reasoningcited by 21
  11. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  12. 2024A social path to human-like artificial intelligencecited by 20
  13. 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
  14. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  15. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  16. 2021Collaborative Visual Navigationcited by 18
  17. 2023A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problemcited by 18
  18. 2021Emergent Communication under Competitioncited by 17
  19. 2024Iterated Learning Improves Compositionality in Large Vision-Language Modelscited by 17
  20. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  21. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  22. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  23. 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
  24. 2021Solving Common-Payoff Games with Approximate Policy Iterationcited by 15
  25. 2023Computational Language Acquisition with Theory of Mindcited by 15
  26. 2025Communicating Activations Between Language Model Agentscited by 15
  27. 2025Training Language Models for Social Deduction with Multi-Agent Reinforcement Learningcited by 15
  28. 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
  29. 2023What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structurecited by 13
  30. 2021HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messagingcited by 12
  31. 2021Active Divergence with Generative Deep Learning -- A Survey and Taxonomycited by 12
  32. 2021Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communicationcited by 12
  33. 2023Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategycited by 12
  34. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  35. 2021Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictabilitycited by 11
  36. 2022Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantizationcited by 11
  37. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  38. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11

50 most cited of 181 All 181 (JSON)