Cover Image

WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Levy, Guillaume, Colas, Cedric, Oudeyer, Pierre-Yves, Carta, Thomas, Romac, Clement
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
by: Gaven, Loris, et al.
Published: (2025)

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
by: Gaven, Loris, et al.
Published: (2024)

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
by: Pourcel, Julien, et al.
Published: (2025)

Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology
by: Tonga, Junior Cedric, et al.
Published: (2024)

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
by: Colas, Cédric, et al.
Published: (2020)

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
by: Colas, Cédric, et al.
Published: (2018)

Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata
by: Khajehabdollahi, Sina, et al.
Published: (2025)

ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models
by: Pourcel, Julien, et al.
Published: (2023)

Exploring Flow-Lenia Universes with a Curiosity-driven AI Scientist: Discovering Diverse Ecosystem Dynamics
by: Michel, Thomas, et al.
Published: (2025)

When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings
by: Perez, Jérémy, et al.
Published: (2024)

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
by: Carta, Thomas, et al.
Published: (2025)

Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
by: Carta, Thomas, et al.
Published: (2023)

Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice
by: Clément, Benjamin, et al.
Published: (2024)

LogProber: Disentangling confidence from contamination in LLM responses
by: Yax, Nicolas, et al.
Published: (2024)

A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
by: Sigaud, Olivier, et al.
Published: (2023)

Collective Innovation in Groups of Large Language Models
by: Nisioti, Eleni, et al.
Published: (2024)

Discovering Sensorimotor Agency in Cellular Automata using Diversity Search
by: Hamon, Gautier, et al.
Published: (2024)

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
by: Gallouédec, Quentin, et al.
Published: (2024)

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
by: Aissi, Mohamed Salim, et al.
Published: (2024)

Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?
by: Kovač, Grgur, et al.
Published: (2025)

Flow-Lenia: Emergent evolutionary dynamics in mass conservative continuous cellular automata
by: Plantec, Erwan, et al.
Published: (2025)

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning
by: Robertson, Cole, et al.
Published: (2025)

Interactive environments for training children's curiosity through the practice of metacognitive skills: a pilot study
by: Abdelghani, Rania, et al.
Published: (2024)

Code-enabled language models can outperform reasoning models on diverse tasks
by: Zhang, Cedegao E., et al.
Published: (2025)

Could you be wrong: Debiasing LLMs using a metacognitive prompt for improving human decision making
by: Hills, Thomas T.
Published: (2025)

Cultural evolution in populations of Large Language Models
by: Perez, Jérémy, et al.
Published: (2024)

What killed the cat? Towards a logical formalization of curiosity (and suspense, and surprise) in narratives
by: de Saint-Cyr, Florence Dupin, et al.
Published: (2024)

PRISM: Perception Reasoning Interleaved for Sequential Decision Making
by: Aissi, Mohamed Salim, et al.
Published: (2026)

Stick to your Role! Stability of Personal Values Expressed in Large Language Models
by: Kovač, Grgur, et al.
Published: (2024)

Policy Learning with a Language Bottleneck
by: Srivastava, Megha, et al.
Published: (2024)

Online Continual Learning for Time Series: a Natural Score-driven Approach
by: Urettini, Edoardo, et al.
Published: (2026)

A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making
by: Wu, Xiao, et al.
Published: (2025)

ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
by: Guo, Ziyang, et al.
Published: (2026)

Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning
by: Urettini, Edoardo, et al.
Published: (2025)

Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
by: Ma, Maotian, et al.
Published: (2026)

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
by: Zhou, Siyu, et al.
Published: (2024)

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
by: Hong, Jack, et al.
Published: (2025)

Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities
by: Albright, Ryan, et al.
Published: (2026)

Goal-Conditioned Agents that Learn Everything All at Once
by: Matthews, Michael, et al.
Published: (2026)

From task structures to world models: What do LLMs know?
by: Yildirim, Ilker, et al.
Published: (2023)