# How agents see things: On visual representations in an emergent language game

arXiv: https://arxiv.org/abs/1808.10696 · HTML: https://mlsanity.com/paper/1808.10696/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2018.

## Built on by (most cited first, 30 of 45)

- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Emergent Communication of Generalizations](https://mlsanity.com/paper/2106.02668/) (2021)
- [Few-shot Language Coordination by Modeling Theory of Mind](https://mlsanity.com/paper/2107.05697/) (2021)
- [Interpretable agent communication from scratch (with a generic visual processor emerging on the side)](https://mlsanity.com/paper/2106.04258/) (2021)
- [Quasi-Equivalence Discovery for Zero-Shot Emergent Communication](https://mlsanity.com/paper/2103.08067/) (2021)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Emergent Graphical Conventions in a Visual Communication Game](https://mlsanity.com/paper/2111.14210/) (2021)
- [The Emergence of the Shape Bias Results from Communicative Efficiency](https://mlsanity.com/paper/2109.06232/) (2021)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication](https://mlsanity.com/paper/2111.06464/) (2021)
- [Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off](https://mlsanity.com/paper/2301.13083/) (2023)
- [Referential communication in heterogeneous communities of pre-trained visual deep networks](https://mlsanity.com/paper/2302.08913/) (2023)
- [Interaction-Grounded Learning](https://mlsanity.com/paper/2106.04887/) (2021)
- [Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Models](https://mlsanity.com/paper/2305.19761/) (2023)
- [The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication](https://mlsanity.com/paper/2407.17960/) (2024)
- [Trust-based Consensus in Multi-Agent Reinforcement Learning Systems](https://mlsanity.com/paper/2205.12880/) (2022)
- [The emergence of visual semantics through communication games](https://mlsanity.com/paper/2101.10253/) (2021)
- [Language Evolution with Deep Learning](https://mlsanity.com/paper/2403.11958/) (2024)
- [Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence](https://mlsanity.com/paper/2409.09413/) (2024)
- [CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures](https://mlsanity.com/paper/2508.11915/) (2025)
- [Learning Multi-Object Positional Relationships via Emergent Communication](https://mlsanity.com/paper/2302.08084/) (2023)
- [Discrete representations in neural models of spoken language](https://mlsanity.com/paper/2105.05582/) (2021)
- [ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation](https://mlsanity.com/paper/2310.11282/) (2023)
- [What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language models](https://mlsanity.com/paper/2407.17974/) (2024)
- [Sparse Communication via Mixed Distributions](https://mlsanity.com/paper/2108.02658/) (2021)
- [Recommendations for Systematic Research on Emergent Language](https://mlsanity.com/paper/2206.11302/) (2022)
- [Mathematically Modeling the Lexicon Entropy of Emergent Language](https://mlsanity.com/paper/2211.15783/) (2022)
- [Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minima](https://mlsanity.com/paper/2303.04544/) (2023)
- [Context-dependent communication under environmental constraints](https://mlsanity.com/paper/2305.05821/) (2023)
- [Emergent Communication with Attention](https://mlsanity.com/paper/2305.10920/) (2023)

## Abstract (arXiv)

There is growing interest in the language developed by agents interacting in emergent-communication settings. Earlier studies have focused on the agents' symbol usage, rather than on their representation of visual input. In this paper, we consider the referential games of Lazaridou et al. (2017) and investigate the representations the agents develop during their evolving interaction. We find that the agents establish successful communication by inducing visual representations that almost perfectly align with each other, but, surprisingly, do not capture the conceptual properties of the objects depicted in the input images. We conclude that, if we are interested in developing language-like communication systems, we must pay more attention to the visual semantics agents associate to the symbols they use.