AI RESEARCH
LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed
arXiv CS.AI
•
ArXi:2411.08794v2 Announce Type: replace World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) as general world simulators to simulate the dynamics of the world due to their generalizability. LLMs also serve as the world model for deliberative reasoning in Reasoning via Planning (RAP) and Tree of Thought (ToT