# Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning

arXiv: https://arxiv.org/abs/2605.11695 · HTML: https://mlsanity.com/paper/2605.11695/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [On the role of population heterogeneity in emergent communication](https://mlsanity.com/paper/2204.12982/) (2022)
- [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [Referential communication in heterogeneous communities of pre-trained visual deep networks](https://mlsanity.com/paper/2302.08913/) (2023)
- [Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Models](https://mlsanity.com/paper/2305.19761/) (2023)
- [ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models](https://mlsanity.com/paper/2307.00398/) (2023)
- [Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence](https://mlsanity.com/paper/2409.09413/) (2024)
- [Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference](https://mlsanity.com/paper/2504.09620/) (2025)
- [Learning to Communicate Across Modalities: Perceptual Heterogeneity in Multi-Agent Systems](https://mlsanity.com/paper/2601.22041/) (2026)

## Abstract (arXiv)

Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, asking what visual information can become shareable when agents have different visual representations. Instead of optimizing messages through a shared external communicative objective, our agents exchange only discrete token sequences and update their own models using local perceptual evidence. This setting focuses on an underexplored aspect of emergent communication, examining whether common symbols can arise without shared perceptual access, and how the similarity between private visual spaces constrains the content and symmetry of the resulting language. We instantiate this setting in the Metropolis-Hastings Captioning Game (MHCG), where two agents collaboratively form shared captions by exchanging proposed token sequences that a listener accepts or rejects using an MH-style criterion evaluated against its own visual features. We compare three pairings of frozen visual encoders, with agents starting from randomly initialized text modules. Experiments on MS-COCO show that MHCG produces visually informative shared token sequences that outperform a no-communication baseline in cross-agent alignment, visual-feature prediction, and image-text retrieval; all cross-agent metrics decline as encoder mismatch increases. Moderate encoder heterogeneity reduces the number of shared sequences while preserving per-sequence visual specificity, whereas stronger encoder heterogeneity yields fewer, coarser, and more asymmetric sequences. Ablations show that listener-side MH acceptance is critical for avoiding degenerate token formation. These results suggest that shared symbols can arise from local perceptual evaluation alone, with visual representational similarity across encoders shaping both the content and symmetry of the resulting language.