AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search

Documenti analoghi

• A$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
  di: Chen, Dingwei, et al.
  Pubblicazione: (2026)
• StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
  di: Wang, Daoyu, et al.
  Pubblicazione: (2026)
• Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models
  di: Ni, Shiwen, et al.
  Pubblicazione: (2023)
• DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
  di: Gu, Chenyang, et al.
  Pubblicazione: (2025)
• TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
  di: Li, Yizhi, et al.
  Pubblicazione: (2025)