Skip to content
arXiv Game World Models & Generation· Haoyu Zhao·· 2026-10-08PickAI score46

Memento 3 Proposes Reflective Rulebooks to Let Frozen LLM Agents Continuously Revise World Models

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

AI summary

The paper proposes Memento 3, which lets a frozen large language model agent continuously learn an explicit world model through external memory: the agent maintains a natural-language rulebook recording revisable hypotheses about environment dynamics while leaving unknown parts unspecified, then compiles it into executable code for prediction and planning, using a loop of observation, reflection, rule revision, compilation, and verification to improve both the rulebook and the code via prediction error.

Why it matters

With the underlying large model frozen, continuously updating the world model via a revisable rulebook plus code verification offers a transferable methodological path for agent learning.

Source: arXiv Game World Models & Generation · arxiv.org