Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

Documenti analoghi

• ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning
  di: Ren, Qingnan, et al.
  Pubblicazione: (2026)
• Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
  di: Su, Qisheng, et al.
  Pubblicazione: (2026)
• SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
  di: Ren, Qingnan, et al.
  Pubblicazione: (2026)
• ACC: Compiling Agent Trajectories for Long-Context Training
  di: Su, Qisheng, et al.
  Pubblicazione: (2026)
• CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios
  di: Huang, Shiting, et al.
  Pubblicazione: (2025)