Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary

Documenti analoghi

• Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
  di: Wang, Rui, et al.
  Pubblicazione: (2025)
• Acting Less is Reasoning More! Teaching Model to Act Efficiently
  di: Wang, Hongru, et al.
  Pubblicazione: (2025)
• Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting
  di: Wang, Rui, et al.
  Pubblicazione: (2023)
• Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions
  di: Wang, Hongru, et al.
  Pubblicazione: (2024)
• MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
  di: Xue, Boyang, et al.
  Pubblicazione: (2024)