# Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

arXiv: https://arxiv.org/abs/1706.08502 · HTML: https://mlsanity.com/paper/1706.08502/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2017.

## Built on by (most cited first, 30 of 86)

- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Meta-Learning to Compositionally Generalize](https://mlsanity.com/paper/2106.04252/) (2021)
- [Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate](https://mlsanity.com/paper/2402.02769/) (2024)
- [Emergent Communication of Generalizations](https://mlsanity.com/paper/2106.02668/) (2021)
- [Deep Multiagent Reinforcement Learning: Challenges and Directions](https://mlsanity.com/paper/2106.15691/) (2021)
- [Emergent Communication: Generalization and Overfitting in Lewis Games](https://mlsanity.com/paper/2209.15342/) (2022)
- [Interactive Learning from Activity Description](https://mlsanity.com/paper/2102.07024/) (2021)
- [Interpretable agent communication from scratch (with a generic visual processor emerging on the side)](https://mlsanity.com/paper/2106.04258/) (2021)
- [Emergent Communication for Understanding Human Language Evolution: What's Missing?](https://mlsanity.com/paper/2204.10590/) (2022)
- [Iterated learning for emergent systematicity in VQA](https://mlsanity.com/paper/2105.01119/) (2021)
- [Neuro-Symbolic Causal Reasoning Meets Signaling Game for Emergent Semantic Communications](https://mlsanity.com/paper/2210.12040/) (2022)
- [Emergent Discrete Communication in Semantic Spaces](https://mlsanity.com/paper/2108.01828/) (2021)
- [Quasi-Equivalence Discovery for Zero-Shot Emergent Communication](https://mlsanity.com/paper/2103.08067/) (2021)
- [Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents](https://mlsanity.com/paper/2110.05769/) (2021)
- [Iterated Learning Improves Compositionality in Large Vision-Language Models](https://mlsanity.com/paper/2404.02145/) (2024)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication](https://mlsanity.com/paper/2409.17348/) (2024)
- [Efficacy of Language Model Self-Play in Non-Zero-Sum Games](https://mlsanity.com/paper/2406.18872/) (2024)
- [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024)
- [Learning to Mediate Disparities Towards Pragmatic Communication](https://mlsanity.com/paper/2203.13685/) (2022)
- [The Emergence of the Shape Bias Results from Communicative Efficiency](https://mlsanity.com/paper/2109.06232/) (2021)
- [What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure](https://mlsanity.com/paper/2302.12239/) (2023)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025)
- [Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication](https://mlsanity.com/paper/2111.06464/) (2021)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [Dynamic population-based meta-learning for multi-agent communication with natural language](https://mlsanity.com/paper/2110.14241/) (2021)
- [Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook](https://mlsanity.com/paper/2210.13623/) (2022)
- [Multitasking Inhibits Semantic Drift](https://mlsanity.com/paper/2104.07219/) (2021)
- [Emergence of hierarchical reference systems in multi-agent communication](https://mlsanity.com/paper/2203.13176/) (2022)

## Abstract (arXiv)

A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, all learned without any human supervision! In this paper, using a Task and Tell reference game between two agents as a testbed, we present a sequence of 'negative' results culminating in a 'positive' one -- showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional. In essence, we find that natural language does not emerge 'naturally', despite the semblance of ease of natural-language-emergence that one may gather from recent literature. We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate.