Metraipolis › archive › dc_bc89d919cd9a
Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability — arXiv:2610.23722
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23722
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:42:42.770Z
- SHA-256 of the archived text
884824b0c79dc38b6473d2bda683c04690ff111ef8126b8089303d54223bae4c- Stable URL of this page
https://metraipolis.com/documento/dc_bc89d919cd9a
How to cite
Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability — arXiv:2610.23722 — arXiv (en), https://arxiv.org/abs/2610.23722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc89d919cd9a (Metraipolis archive dc_bc89d919cd9a, sha256 884824b0c79dc38b6473d2bda683c04690ff111ef8126b8089303d54223bae4c)
BibTeX
@misc{dcbc89d919cd9a,
title = {Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability — arXiv:2610.23722},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23722},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc89d919cd9a; sha256 884824b0c79dc38b6473d2bda683c04690ff111ef8126b8089303d54223bae4c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 construction, cognitive-psychological interactions, dynamic evolution, and historical dependencies. This paper introduces the Mental World Model (MWM) and its implementation, the Multi-Branch Mental Evolution Architecture (MMEA), which explicitly constructs subjective worlds, models interactions between cognition and mental states, and simulates continuous mental evolution shaped by historical experiences. On DynToM and RecToM, MMEA achieves 96.48% and 94.00% accuracy, respectively, outperforming leading LLMs and specialized ToM methods. Additional experiments demonstrate improvements of 28.7, 39.3, and 16.6 percentage points in mental state and behavior prediction, long-sequence prediction, and implicit mental state inference, respectively. The results demonstrate that MMEA provides an interpretable framework for continuous mental modeling, enabling AI to move beyond surface-level semantic representations to infer individuals' underlying mental states from linguistic information and dynamically simulate their internal cognitive processes and evolution over time. MWM also provides a promising foundation for causal reasoning, personalized AI, sustained human-AI interaction, and future advances toward artificial general intelligence (AGI). Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.23722 — 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 2026-10-19T08:39:10.094Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).