Metraipolis › archive › dc_234fc84b2fba
Modular Cognitive Architecture Emerges in Large Language Models — arXiv:2608.13567
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13567
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:20:14.900Z
- SHA-256 of the archived text
577ce5cb7a69970358a2b65b638699cd13c62a049369d9355c8f23ccd286046f- Stable URL of this page
https://metraipolis.com/documento/dc_234fc84b2fba
How to cite
Modular Cognitive Architecture Emerges in Large Language Models — arXiv:2608.13567 — arXiv (en), https://arxiv.org/abs/2608.13567 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_234fc84b2fba (Metraipolis archive dc_234fc84b2fba, sha256 577ce5cb7a69970358a2b65b638699cd13c62a049369d9355c8f23ccd286046f)
BibTeX
@misc{dc234fc84b2fba,
title = {Modular Cognitive Architecture Emerges in Large Language Models — arXiv:2608.13567},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13567},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_234fc84b2fba; sha256 577ce5cb7a69970358a2b65b638699cd13c62a049369d9355c8f23ccd286046f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13567. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models--another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains and neural networks suggests that it may be a fundamental property of intelligent systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.13567 — 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 2026-10-19T02:02:02.712Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).