Memento 3 在冻结 LLM 下通关 ARC-AGI-3 全部 25 个公开游戏

Insightful paper on recursive self-improvement with a frozen LLM.

(bookmark it)

Memento 3 clears every level of all 25 public ARC-AGI-3 games and uses 44% of the human action count. The underlying LLM is never updated.

How it works:

The agent writes what it believes about the environment as a natural-language rulebook, then compiles that rulebook into code that predicts the next state. A new version is kept only if replaying the code reproduces every transition the agent has observed, cell for cell.

In an Atari Pong case study, the learned model drives a controller that wins 21 to 0 in three games without further LLM calls.

arxiv.org/abs/2610.11794

Chat with Paper: academy.dair.ai/papers/memen…