Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning

Documenti analoghi

• Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
  di: Yuan, Siyu, et al.
  Pubblicazione: (2025)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
  di: Ye, Junjie, et al.
  Pubblicazione: (2025)
• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
  di: Xi, Zhiheng, et al.
  Pubblicazione: (2025)
• ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
  di: Ye, Junjie, et al.
  Pubblicazione: (2025)
• Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
  di: Xi, Zhiheng, et al.
  Pubblicazione: (2024)