D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Documenti analoghi

• Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting
  di: Xu, Bowen, et al.
  Pubblicazione: (2024)
• La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
  di: Liu, Kai, et al.
  Pubblicazione: (2025)
• Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
  di: Xu, Ran, et al.
  Pubblicazione: (2025)
• CORE: A Conceptual Reasoning Layer for Large Language Models
  di: Hegde, Vishwas, et al.
  Pubblicazione: (2025)
• Agentic Tool Use in Large Language Models
  di: Hu, Jinchao, et al.
  Pubblicazione: (2026)