Metraipolis › archive › dc_b6d65a96cf71

Claims of emergence in AI should be grounded in information decomposition — arXiv:2610.28479

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.28479
License (as archived)
CC0-1.0
Archived
2026-10-21T05:49:53.216Z
SHA-256 of the archived text
cecf347263a361b5c7555095d69e29d0cfe89be270f0fa4a01df79a7ab747d0a
Stable URL of this page
https://metraipolis.com/documento/dc_b6d65a96cf71

How to cite

Claims of emergence in AI should be grounded in information decomposition — arXiv:2610.28479 — arXiv (en), https://arxiv.org/abs/2610.28479 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6d65a96cf71 (Metraipolis archive dc_b6d65a96cf71, sha256 cecf347263a361b5c7555095d69e29d0cfe89be270f0fa4a01df79a7ab747d0a)
BibTeX
@misc{dcb6d65a96cf71,
  title = {Claims of emergence in AI should be grounded in information decomposition — arXiv:2610.28479},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.28479},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6d65a96cf71; sha256 cecf347263a361b5c7555095d69e29d0cfe89be270f0fa4a01df79a7ab747d0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28479. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When a language model develops capabilities not traceable to its individual components, when a multi-agent AI system outperforms each agent on its own, or when a human-AI pair succeeds where either fails in isolation, AI researchers describe it as a case of ``synergy'' or ``emergence''. However, these are usually informal assessments not supported by a theoretical framework, making these claims impossible to compare or even meaningfully dispute. Here we argue that \emph{information decomposition can serve as a unifying formal framework to operationalize assessments about synergy in AI systems}. Information decomposition provides a way to distinguish qualitatively different \emph{types} of information, including unique information available from individual components, redundant information shared across multiple components, and synergistic information accessible only from parts taken together. This gives claims of emergence a precise, falsifiable criterion: a system's behavior is emergent only if it carries synergistic information about task-relevant outcomes. We apply this lens to attention heads, autonomous agents, and human-AI teams, showing how it organizes existing knowledge across scales and substrates, while also generating cross-level conjectures that siloed fields would miss.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC); Information Theory (cs.IT); Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.28479 — 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 2026-10-21T05:49:52.737Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).