Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.22041 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914291862470656 |
|---|---|
| author | Pitzer, Naomi Mihai, Daniela |
| author_facet | Pitzer, Naomi Mihai, Daniela |
| contents | Emergent communication offers insight into how agents develop shared structured representations, yet most research assumes homogeneous modalities or aligned representational spaces, overlooking the perceptual heterogeneity of real-world settings. We study a heterogeneous multi-step binary communication game where agents differ in modality and lack perceptual grounding. Despite perceptual misalignment, multimodal systems converge to class-consistent messages grounded in perceptual input. Unimodal systems communicate more efficiently, using fewer bits and achieving lower classification entropy, while multimodal agents require greater information exchange and exhibit higher uncertainty. Bit perturbation experiments provide strong evidence that meaning is encoded in a distributional rather than compositional manner, as each bit's contribution depends on its surrounding pattern. Finally, interoperability analyses show that systems trained in different perceptual worlds fail to directly communicate, but limited fine-tuning enables successful cross-system communication. This work positions emergent communication as a framework for studying how agents adapt and transfer representations across heterogeneous modalities, opening new directions for both theory and experimentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22041 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Communicate Across Modalities: Perceptual Heterogeneity in Multi-Agent Systems Pitzer, Naomi Mihai, Daniela Multiagent Systems Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.11; I.2.6 Emergent communication offers insight into how agents develop shared structured representations, yet most research assumes homogeneous modalities or aligned representational spaces, overlooking the perceptual heterogeneity of real-world settings. We study a heterogeneous multi-step binary communication game where agents differ in modality and lack perceptual grounding. Despite perceptual misalignment, multimodal systems converge to class-consistent messages grounded in perceptual input. Unimodal systems communicate more efficiently, using fewer bits and achieving lower classification entropy, while multimodal agents require greater information exchange and exhibit higher uncertainty. Bit perturbation experiments provide strong evidence that meaning is encoded in a distributional rather than compositional manner, as each bit's contribution depends on its surrounding pattern. Finally, interoperability analyses show that systems trained in different perceptual worlds fail to directly communicate, but limited fine-tuning enables successful cross-system communication. This work positions emergent communication as a framework for studying how agents adapt and transfer representations across heterogeneous modalities, opening new directions for both theory and experimentation. |
| title | Learning to Communicate Across Modalities: Perceptual Heterogeneity in Multi-Agent Systems |
| topic | Multiagent Systems Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.11; I.2.6 |
| url | https://arxiv.org/abs/2601.22041 |