Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies

Documenti analoghi

• Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
  di: Cheng, Sitao, et al.
  Pubblicazione: (2024)
• RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
  di: Zhou, Ruiwen, et al.
  Pubblicazione: (2024)
• LEDOM: Reverse Language Model
  di: Yin, Xunjian, et al.
  Pubblicazione: (2025)
• Differentiable Evolutionary Reinforcement Learning
  di: Cheng, Sitao, et al.
  Pubblicazione: (2025)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
  di: Yin, Xunjian, et al.
  Pubblicazione: (2024)