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

Documenti analoghi

• MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
  di: Gaven, Loris, et al.
  Pubblicazione: (2025)
• SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
  di: Gaven, Loris, et al.
  Pubblicazione: (2024)
• Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
  di: Pourcel, Julien, et al.
  Pubblicazione: (2025)
• Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology
  di: Tonga, Junior Cedric, et al.
  Pubblicazione: (2024)
• Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
  di: Colas, Cédric, et al.
  Pubblicazione: (2020)