A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation

Documenti analoghi

• Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning
  di: Netík, Jan, et al.
  Pubblicazione: (2026)
• Research on intelligent generation of structural demolition suggestions based on multi-model collaboration
  di: Yang, Zhifeng, et al.
  Pubblicazione: (2025)
• Two are better than one: Context window extension with multi-grained self-injection
  di: Han, Wei, et al.
  Pubblicazione: (2024)
• MARS: toward more efficient multi-agent collaboration for LLM reasoning
  di: Wang, Xiao, et al.
  Pubblicazione: (2025)
• Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems
  di: Lakatos, Robert, et al.
  Pubblicazione: (2024)