Making large language models into world models with precondition and effect knowledge

K **e, I Yang, J Gunerli, M Riedl - arxiv preprint arxiv:2409.12278, 2024 - arxiv.org
World models, which encapsulate the dynamics of how actions affect environments, are
foundational to the functioning of intelligent agents. In this work, we explore the potential of …

Towards building specialized generalist ai with system 1 and system 2 fusion

K Zhang, B Qi, B Zhou - arxiv preprint arxiv:2407.08642, 2024 - arxiv.org
In this perspective paper, we introduce the concept of Specialized Generalist Artificial
Intelligence (SGAI or simply SGI) as a crucial milestone toward Artificial General Intelligence …

Web agents with world models: Learning and leveraging environment dynamics in web navigation

H Chae, N Kim, KT Ong, M Gwak, G Song… - The Thirteenth …, 2024 - openreview.net
Large language models (LLMs) have recently gained much attention in building
autonomous agents. However, performance of current LLM-based web agents in long …

Generative Emergent Communication: Large Language Model is a Collective World Model

T Taniguchi, R Ueda, T Nakamura, M Suzuki… - arxiv preprint arxiv …, 2024 - arxiv.org
This study proposes a unifying theoretical framework called generative emergent
communication (generative EmCom) that bridges emergent communication, world models …

Enhancing agent learning through world dynamics modeling

Z Sun, H Shi, MA Côté, G Berseth, X Yuan… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) have been increasingly applied to tasks in language
understanding and interactive decision-making, with their impressive performance largely …

Computational Poetry is Lost Poetry

M Kreminski - Proceedings of the Halfway to the Future Symposium, 2024 - dl.acm.org
The genre of “found poetry” encompasses passages of text that were first framed as poetry
by someone other than the original writer. But for something to be found, it must first be lost …

Engineering of Generative Artificial Intelligence and Natural Language Processing Models to Accurately Identify Arrhythmia Recurrence

R Feng, KA Brennan, Z Azizi, J Goyal… - Circulation …, 2025 - ahajournals.org
BACKGROUND: Large language models (LLMs) such as Chat Generative Pre-trained
Transformer (ChatGPT) excel at interpreting unstructured data from public sources, yet are …

Text2World: Benchmarking Large Language Models for Symbolic World Model Generation

M Hu, T Chen, Y Zou, Y Lei, Q Chen, M Li… - arxiv preprint arxiv …, 2025 - arxiv.org
Recently, there has been growing interest in leveraging large language models (LLMs) to
generate symbolic world models from textual descriptions. Although LLMs have been …

Trajectory World Models for Heterogeneous Environments

S Yin, J Wu, S Huang, X Su, X He, J Hao… - arxiv preprint arxiv …, 2025 - arxiv.org
Heterogeneity in sensors and actuators across environments poses a significant challenge
to building large-scale pre-trained world models on top of this low-dimensional sensor …

Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches

A Mumuni, F Mumuni - arxiv preprint arxiv:2501.03151, 2025 - arxiv.org
Generative artificial intelligence (AI) systems based on large-scale pretrained foundation
models (PFMs) such as vision-language models, large language models (LLMs), diffusion …