# Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching

arXiv: https://arxiv.org/abs/2606.10582 · HTML: https://mlsanity.com/paper/2606.10582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 61 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 30 of 32)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (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)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [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)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [Off-Belief Learning](https://mlsanity.com/paper/2103.04000/) (2021)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [Countering Language Drift with Seeded Iterated Learning](https://mlsanity.com/paper/2003.12694/) (2020)
- [Countering Language Drift via Visual Grounding](https://mlsanity.com/paper/1909.04499/) (2019)
- [Environmental drivers of systematicity and generalization in a situated agent](https://mlsanity.com/paper/1910.00571/) (2019)
- [Emergent Communication of Generalizations](https://mlsanity.com/paper/2106.02668/) (2021)
- [Emergent Linguistic Phenomena in Multi-Agent Communication Games](https://mlsanity.com/paper/1901.08706/) (2019)
- [A New Formalism, Method and Open Issues for Zero-Shot Coordination](https://mlsanity.com/paper/2106.06613/) (2021)
- [Compositional Obverter Communication Learning From Raw Visual Input](https://mlsanity.com/paper/1804.02341/) (2018)
- [Emergent Communication: Generalization and Overfitting in Lewis Games](https://mlsanity.com/paper/2209.15342/) (2022)
- [Learning to Draw: Emergent Communication through Sketching](https://mlsanity.com/paper/2106.02067/) (2021)
- [Differentiable Drawing and Sketching](https://mlsanity.com/paper/2103.16194/) (2021)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence](https://mlsanity.com/paper/1611.03218/) (2016)

## Abstract (arXiv)

Generalization in emergent communication has largely focused on novel inputs or linguistic structures, yet the capacity for agents to communicate with strangers from strictly disjoint communities remains relatively unexplored. In this work, we formalize this capability as textitzero-shot mutual intelligibility (ZMI): successful communication between independently trained populations without prior exposure. Leveraging emergent sketching -- in which agents communicate through sets of drawn strokes -- as a visually grounded modality, we find that scaling the training population substantially improves ZMI across independent groups. Crucially, as we scale the population size, in-group communicative variation increases, preventing co-adaptation into homogeneity. Simultaneously, cross-group variation decreases, indicating a structural convergence toward a certain type of universality. Further analysis reveals that this universality is achieved through perceptual grounding: scaled populations increasingly anchor their emergent sketches on the objective visual resemblance of the target images. Together, these results position ZMI as a distinct axis of generalization in emergent communication and suggest a route toward socially interoperable artificial agents.