Newest papers

Claims of emergence in AI should be grounded in information decomposition

Christoph Riedl, Fernando E. Rosas · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28479 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

عندما يطور نموذج لغة القدرة على التعرف على المكونات الفردية، عندما يقوم نظام الذكاء الاصطناعي المتعدد الأبعاد بعمل كل عامل بنفسه، أو عندما ينجح زوج من الذكاء الاصطناعي في الحد من الفساد، فإن الباحثين في الذكاء الاصطناعيين يصفون ذلك بأنه حالة من "سيناريوهات" أو "الخطر". ومع ذلك، فإن هذه هي عادة تقييمات غير رسمية لا تدعمها إطار نظري، مما يجعل هذه الشكاوى غير قابلة للتقييم، بما في ذلك المعلومات الفريدة المتاحة من المكونات الفردية، أو حتى التناقضات المعقدة. نحن نعتقد هنا أن "تقسيم المعلومات المتاحة من أجزاء متعددة يمكن الوصول إليها فقط

Machine translation (Meta M2M100); the English original follows.

Abstract

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Falsifiability, Operationalization, Decomposition, Computer science, Artificial intelligence, Information system

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28479, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange