华为AI靠RSI通关25款游戏！操作次数比人类少56%

1. 13:48
   量子位

   Huawei AI Beats 25 Games via RSI, Using 56% Fewer Actions Than Humans

   Huawei's Noah's Ark Lab and UCL and other teams introduced Memento 3, an AI agent system built on Claude Opus 5 that cleared all 25 games and 183 levels in the ARC-AGI-3 public set without updating model weights or fine-tuning, scoring a perfect 100 RHAE. It used 7518 actions versus 17135 for humans, about 56% fewer, and also fewer than baseline1's 8347. In Atari Pong, after learning a control strategy on its own, the system stopped calling the large model and won three straight games 21:0.

The trend compares the same fully observed sources, so its range can be smaller than the current heat. Move the pointer or click for each hour. Left and right arrow keys move the point.