Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents

Documenti analoghi

• The Majority is not always right: RL training for solution aggregation
  di: Zhao, Wenting, et al.
  Pubblicazione: (2025)
• Open-Domain Text Evaluation via Contrastive Distribution Methods
  di: Lu, Sidi, et al.
  Pubblicazione: (2023)
• Can RL Improve Generalization of LLM Agents? An Empirical Study
  di: Xi, Zhiheng, et al.
  Pubblicazione: (2026)
• Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
  di: Liu, Zhihan, et al.
  Pubblicazione: (2023)
• How Can LLM Guide RL? A Value-Based Approach
  di: Zhang, Shenao, et al.
  Pubblicazione: (2024)