Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability
Paper recorded by Signals 4 on 2026-10-16 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-16 on arXiv · recorded by Signals 4 on 2026-10-19
Category: cs.AI · 人工智能 · first seen 2026-10-19
Abstract
Understanding and simulating how subjective cognition and mental states emerge, evolve, and shape behavior is essential for advancing artificial intelligence toward deeper social cognition and general intelligence. Existing large language models (LLMs) and Theory of Mind (ToM) methods primarily infer mental states from linguistic information, lacking unified mechanisms for subjective world constru
Read on arXiv →
Cite this page: Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability: the #268 most recent of 960 cs.AI papers we have recorded (as of 2026-10-16). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/beyond-large-language-models-a-mental-world-model-framework-for-mental-modeling-.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free