# Emergence of hierarchical reference systems in multi-agent communication

arXiv: https://arxiv.org/abs/2203.13176 · HTML: https://mlsanity.com/paper/2203.13176/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation](https://mlsanity.com/paper/2003.08813/) (2020)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [Comprehension-guided referring expressions](https://mlsanity.com/paper/1701.03439/) (2017)
- [EGG: a toolkit for research on Emergence of lanGuage in Games](https://mlsanity.com/paper/1907.00852/) (2019)
- [Compositional Obverter Communication Learning From Raw Visual Input](https://mlsanity.com/paper/1804.02341/) (2018)
- [Interpretable agent communication from scratch (with a generic visual processor emerging on the side)](https://mlsanity.com/paper/2106.04258/) (2021)
- [Co-evolution of language and agents in referential games](https://mlsanity.com/paper/2001.03361/) (2020)
- [Emergence of Pragmatics from Referential Game between Theory of Mind Agents](https://mlsanity.com/paper/2001.07752/) (2020)
- [Learning in the Rational Speech Acts Model](https://mlsanity.com/paper/1510.06807/) (2015)
- [Incorporating Pragmatic Reasoning Communication into Emergent Language](https://mlsanity.com/paper/2006.04109/) (2020)
- [Internal and external pressures on language emergence: least effort, object constancy and frequency](https://mlsanity.com/paper/2004.03868/) (2020)
- [The Grammar of Emergent Languages](https://mlsanity.com/paper/2010.02069/) (2020)

## Built on by (most cited first, 8 of 8)

- [Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances](https://mlsanity.com/paper/2502.16804/) (2025)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Common Ground Tracking in Multimodal Dialogue](https://mlsanity.com/paper/2403.17284/) (2024)
- [Dynamic Epistemic Friction in Dialogue](https://mlsanity.com/paper/2506.10934/) (2025)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [Emergent communication for AR](https://mlsanity.com/paper/2308.07342/) (2023)
- [Emergent Communication in Continuous Worlds: Self-Organisation of Conceptually Grounded Vocabularies at Scale](https://mlsanity.com/paper/2401.08461/) (2024)
- [Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired](https://mlsanity.com/paper/2505.22087/) (2025)

## Abstract (arXiv)

In natural language, referencing objects at different levels of specificity is a fundamental pragmatic mechanism for efficient communication in context. We develop a novel communication game, the hierarchical reference game, to study the emergence of such reference systems in artificial agents. We consider a simplified world, in which concepts are abstractions over a set of primitive attributes (e.g., color, style, shape). Depending on how many attributes are combined, concepts are more general ("circle") or more specific ("red dotted circle"). Based on the context, the agents have to communicate at different levels of this hierarchy. Our results show that the agents learn to play the game successfully and can even generalize to novel concepts. To achieve abstraction, they use implicit (omitting irrelevant information) and explicit (indicating that attributes are irrelevant) strategies. In addition, the compositional structure underlying the concept hierarchy is reflected in the emergent protocols, indicating that the need to develop hierarchical reference systems supports the emergence of compositionality.