Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models

arXiv:2601.08955v2 Announce Type: replace-cross
Abstract: Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Current methods mainly perform single-step or fixed-horizon rollouts, leaving their potential for complex task planning under-exploited. We propose Imagine-then-Plan (textttITP), a unified framework for agent learning via lookahead imagination, where an agent’s policy model interacts with the learned world model, yielding multi-step “imagined” trajectories. Since the imagination horizon may vary by tasks and stages, we introduce a novel adaptive lookahead mechanism by trading off the ultimate goal and task progress. The resulting imagined trajectories provide rich signals about future consequences, such as achieved progress and potential conflicts, which are fused with current observations, formulating a partially textitobservable and textitimaginable Markov decision process to guide policy learning. We instantiate textttITP with both training-free and reinforcement-trained variants. Extensive experiments across representative agent benchmarks demonstrate that textttITP significantly outperforms competitive baselines. Further analyses validate that our adaptive lookahead largely enhances agents’ reasoning capability, providing valuable insights into addressing broader, complex tasks. Our code and data will be publicly available at https://github.com/loyiv/ITP.