Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training

Documenti analoghi

• DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities
  di: Lee, Jing Yang, et al.
  Pubblicazione: (2025)
• ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
  di: Deng, Chunyuan, et al.
  Pubblicazione: (2026)
• Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
  di: Cheng, Kewei, et al.
  Pubblicazione: (2024)
• HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
  di: Wang, Weiqi, et al.
  Pubblicazione: (2026)
• Train a Unified Multimodal Data Quality Classifier with Synthetic Data
  di: Wang, Weizhi, et al.
  Pubblicazione: (2025)