CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Abstract
AbstractWorld models enable language agents to anticipate environment dynamics and evaluate candidate actions before execution, yet they are typically frozen after training, leaving them unable to adapt to the shifting on-policy distributions induced by evolving agents. Meanwhile, agent-improvement methods often depend on external rewards or verifiers that may be unavailable in realistic interactive environments. We introduce CoMap, a framework that co-evolves textual world models and agent policies through closed-loop interaction. At each decision step, the world model predicts future environment feedback for candidate actions, while the agent performs future-aware reflection by assessing the reliability of these predictions and refining its action accordingly. The resulting on-policy trajectories are then used to improve the world model through self-distillation, enabling it to continually adapt to the agent’s evolving interaction distribution. Across embodied task planning, web navigation, and tool-use benchmarks, CoMap consistently outperforms competitive baselines (e.g., a 16.75% relative improvement with Qwen3-4B). Further analyses show that this co-evolutionary process improves both world-model capability and long-horizon decision-making. Our code and data are available at: https://github.com/loyiv/CoMAP.