AI RESEARCH
R-WoM: Retrieval-augmented World Model For Computer-use Agents
arXiv CS.CL
•
ArXi:2510.11892v2 Announce Type: replace Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However, this capability is fundamentally limited by LLMs' tendency toward hallucination and their reliance on static