LLMs Gain Internal World Models for Long‑Horizon Planning
The paper introduces a three‑stage training pipeline—World Model Mid‑Training, Format‑Eliciting SFT, and Foresight‑Conditioned RL—that teaches a single autoregressive LLM to generate prospective state rollouts and plan‑conditioned success estimates. The resulting agents outperform baselines on search and mathematical reasoning, shifting LLM behavior from reactive to deliberative planning.