Metraipolis › archive › dc_fb2765c81daa
The Tower of Babel in artificial intelligence: who should speak, and when it pays to listen — arXiv:2611.03020
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03020
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:59:35.431Z
- SHA-256 of the archived text
c741b8da54250851e7ec0bcb7188cb90e0cd8cc3a38e86dbb420301088e311ae- Stable URL of this page
https://metraipolis.com/documento/dc_fb2765c81daa
How to cite
The Tower of Babel in artificial intelligence: who should speak, and when it pays to listen — arXiv:2611.03020 — arXiv (en), https://arxiv.org/abs/2611.03020 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb2765c81daa (Metraipolis archive dc_fb2765c81daa, sha256 c741b8da54250851e7ec0bcb7188cb90e0cd8cc3a38e86dbb420301088e311ae)
BibTeX
@misc{dcfb2765c81daa,
title = {The Tower of Babel in artificial intelligence: who should speak, and when it pays to listen — arXiv:2611.03020},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03020},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb2765c81daa; sha256 c741b8da54250851e7ec0bcb7188cb90e0cd8cc3a38e86dbb420301088e311ae},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03020. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Two machines can each recognize an object well and still fail together. We study classifiers that see different parts of one object and send short messages to a receiver that identifies its class. Coordination asks how to design messages together; cooperation asks whether the team outperforms one sender given the whole budget. On three digit datasets, messages designed together beat messages designed apart by 18.07 to 22.68 percentage points on average with two-bit messages, with gains in all 24 configurations. A fixed agreement, you report the row and I the column, recovers about half this gain, with only the receiver learned. Senders that draw the same distinctions waste a narrow vocabulary, and senders whose distinctions cross multiply it. A team has no more possible messages than one sender with the same budget, so a partner must bring evidence the first lacks. A solvable model shows individual statistics alone cannot determine whether a partnership helps. On MNIST digits, six shared bits remove 49.54 percent of the strongest tested solo's errors on average. Paired measurements correctly predicted most sensor teams would reduce average accuracy on new participants. Who should speak is a property of the pair, and must be measured in pairs. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.03020 — 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 2026-11-03T10:59:22.315Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).