SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Documenti analoghi

• Self-Challenging Language Model Agents
  di: Zhou, Yifei, et al.
  Pubblicazione: (2025)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
  di: Zhou, Yifei, et al.
  Pubblicazione: (2024)
• Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
  di: Su, DiJia, et al.
  Pubblicazione: (2024)
• Training Large Language Models to Reason in a Continuous Latent Space
  di: Hao, Shibo, et al.
  Pubblicazione: (2024)
• DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
  di: Bai, Hao, et al.
  Pubblicazione: (2024)