WorldEvolver通过三种记忆模块让智能体的世界模型在测试时自我进化，在ALFWorld和ScienceWorld上预测准确率最高，下游成功率也领先其他方法。
WorldEvolver是一个自进化世界模型框架，在部署时通过记忆模块修正上下文，同时保持下游智能体和模型参数冻结。它包含三个模块：Episodic Memory利用检索模拟实际动作转换，Semantic Memory从预测-观测不匹配中提取启发式规则，Selective Foresight过滤低置信度预测。在ALFWorld和ScienceWorld上评估，WorldEvolver在Word2World上取得最高预测准确率，并在AgentBoard上显著提升下游智能体成功率。实验表明，测试时记忆修正同时增强了预测保真度和规划性能。
Self-Evolving World Models for LLM Agent Planning
World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unreliable foresight can be ignored, misused, or even degrade downstream decision-making. In this paper, we introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen. WorldEvolver integrates three modules: (i) Episodic Memory, which exploits real action transitions through retrieval-based simulation; (ii) Semantic Memory, which extracts persistent heuristic rules from prediction-observation mismatches; and (iii) Selective Foresight, which filters low-confidence predictions before integrating them into agent reasoning context. We evaluate WorldEvolver on ALFWorld and ScienceWorld, measuring world model prediction accuracy on Word2World and downstream agent success rate on AgentBoard. Extensive experiments show that WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate, demonstrating that test-time memory revision enhances both predictive fidelity and planning performance.