Reinforcement Learning for LLM-based Event Forecasting
基于强化学习的LLM事件预测
机构 * Advanced Computer Science(高级计算机科学) ; DeepSeek R1
AI总结 使用GRPO微调LLM,结合Wikipedia修订工具获取实时信息,预测未来事件,使1.5B参数模型性能超越Claude Sonnet 3.5。
Comments Submitted internally at the University of Oxford in Oct 2025, migrated to arXiv on Jun 2026