← Back to all news
arXiv AI By Gang Chen

Seven Sources of Physical AI Capability Formation

Read the original on arXiv AI →

The paper introduces a taxonomy of seven distinct sources that contribute to the formation of Physical AI capabilities: Recorded-Experience, Predictive-Modeling, Evaluative-Interaction, Surrogate-Environment, Mechanism-Grounded, Embodied-Coupling, and Evolution-Driven. Through a systematic review of 49 evidence records, the authors demonstrate that all identified capabilities can be explained by combinations of these sources, achieving theoretical saturation within their defined scope. The framework aims to differentiate how capabilities arise from how they appear, facilitating analysis of explanation, transfer, replication, and governance aspects.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 27

Emergent Abilities in Large Language Models: A Survey

Emergent Abilities in Large Language Models: A Survey reviews how scaling LLMs leads to previously unseen capabilities such as advanced reasoning, in-context learning, coding, and problem-solving. The paper critically examines definitions, inconsistencies, and the conditions that foster these abilities, including scaling laws, task complexity, pre‑training loss, quantization, and prompting strategies. It also discusses the extension to Large Reasoning Models and highlights safety concerns like deception, manipulation, and reward hacking, calling for improved evaluation and governance.

By Leonardo Berti, Flavio Giorgi, Gjergji Kasneci
llmsagentsreinforcement-learningroboticsefficiencysafety
More like this →
arXiv AI
Sep 11

Cognitive Amplification vs Cognitive Delegation in Human-AI Systems: A Metric Framework

The paper proposes a metric framework to differentiate cognitive amplification—where AI enhances human performance without eroding human capability—from cognitive delegation, which relies heavily on AI reasoning. It introduces four metrics (CAI*, D, HRI, HCDR) and tests them in NetLogo simulations across various reliance and dependency scenarios. The results show that positive collaborative gain is only achievable when an explicit interaction term is added, indicating that mere prevention of capability erosion is insufficient for genuine amplification.

By Eduardo Di Santi, Carla Florida
agents
More like this →