Metraipolis › archive › dc_98fd7e282875

Cultural Evolution Drives the Emergence of Conventions in Neural Emergent Communication — arXiv:2611.00006

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00006
License (as archived)
CC0-1.0
Archived
2026-11-03T10:39:39.589Z
SHA-256 of the archived text
6e92e5e2b2c3f92479eaa070418edbc344cf956969a747de6f0779eb5990a5b5
Stable URL of this page
https://metraipolis.com/documento/dc_98fd7e282875

How to cite

Cultural Evolution Drives the Emergence of Conventions in Neural Emergent Communication — arXiv:2611.00006 — arXiv (en), https://arxiv.org/abs/2611.00006 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98fd7e282875 (Metraipolis archive dc_98fd7e282875, sha256 6e92e5e2b2c3f92479eaa070418edbc344cf956969a747de6f0779eb5990a5b5)
BibTeX
@misc{dc98fd7e282875,
  title = {Cultural Evolution Drives the Emergence of Conventions in Neural Emergent Communication — arXiv:2611.00006},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00006},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98fd7e282875; sha256 6e92e5e2b2c3f92479eaa070418edbc344cf956969a747de6f0779eb5990a5b5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00006. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent studies of language evolution with neural agents often use models where agents can either speak or listen, where there are only two agents in the population, or where agents can share internal representations. These choices prevent the study of how language emerges through cultural evolution, i.e. through the cumulative adaptation of individual behaviours to fit the communicative needs of the community. We tackle this issue with a new model that trains populations of bi-directional neural agents in a fully distributed fashion to solve a referential game. We demonstrate the effectiveness of this approach on multiple image datasets and show that it is able to scale to large populations. We also show that more conventional languages are easier to learn, providing a direct advantage for cultural transmission. Overall, this work provides a novel approach to neural emergent communication that opens up new directions for evolutionary linguistics.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.00006 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:39:34.934Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).