This review introduces the Mental World Model (MWM) as a new cognitive layer for Embodied AI, compares it with traditional Physical World Models, outlines 19 Theory‑of‑Mind methods, 26 evaluation benchmarks, and discusses key challenges and future research directions.
This article explores how understanding others' mental states—from basic intentions to recursive mindreading—can be modeled with Bayesian inference and applied to robots for predicting human behavior in scenarios like pedestrian crossing, shopping assistance, and multi‑agent games.
This article examines whether ChatGPT and other large language models exhibit true Theory of Mind, detailing the role of attention mechanisms, neural network architecture, emergent abilities, the Chinese‑room argument, and how compression of massive textual data underlies their apparent intelligence.
Recent research suggests GPT‑3 exhibits Theory of Mind abilities, prompting a deep dive into attention mechanisms, neural network fundamentals, emergent capabilities, and the role of compression in large language models, while examining philosophical thought experiments like the Chinese Room to question true machine intelligence.
A recent Stanford paper shows that GPT‑3.5 and its predecessor can pass classic Theory of Mind tests at levels comparable to 7‑9‑year‑old children, sparking debate over whether these abilities are genuine understanding or emergent by‑products of scaling.
