ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models

Documenti analoghi

• AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards
  di: Lin, Zihan, et al.
  Pubblicazione: (2025)
• ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
  di: Lin, Zihan, et al.
  Pubblicazione: (2026)
• Rethinking Personalization in Large Language Models at the Token Level
  di: Zhang, Chenheng, et al.
  Pubblicazione: (2026)
• Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
  di: Wang, Li, et al.
  Pubblicazione: (2026)
• Are Full Rollouts Necessary for On-Policy Distillation?
  di: Zhang, Yaocheng, et al.
  Pubblicazione: (2026)