LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

Documenti analoghi

• LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
  di: Ping, Bowen, et al.
  Pubblicazione: (2026)
• LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
  di: Chen, Guanzheng, et al.
  Pubblicazione: (2026)
• LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion
  di: Ling, Zhan, et al.
  Pubblicazione: (2025)
• Reducing Distraction in Long-Context Language Models by Focused Learning
  di: Wu, Zijun, et al.
  Pubblicazione: (2024)
• QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
  di: Wan, Fanqi, et al.
  Pubblicazione: (2025)