Tag
论文提出 DeepEvolve，一个基于未来事件预测的可持续进化智能体系统，通过在动态开放环境中与现实世界结果对齐实现递归自我改进（RSI），其自我改进的预测器在 FutureX 排行榜连续三周排名第一，评级提升最高达 195%。
The author comments on FutureX's prediction evaluation framework, pointing out that it only scores final answers and cannot distinguish the quality of probability calibration, and discusses finer-grained evaluation methods such as Brier score and log loss.