用记忆库提升文本世界模型的预测准确性，让智能体规划更可靠。
MemWM: Memory-Augmented Text-Based World Model
- 引入记忆库存储关键规则和难预测事实，指导状态演化预测。
- 在多个任务中，事实保真度提升最高达206.3%，成功率相对提高65.4%。
- 适合需要高精度环境建模与长期规划的复杂任务场景。
世界模型通过预测环境状态随智能体动作的变化来支持决策规划，但现有方法常遗漏关键信息、错误传递产品属性或应用错误转移规则。为此，我们提出MemWM——一种基于记忆增强的文本世界模型。该模型利用世界记忆库（包含经筛选的转移规则、状态缓存及难以预测的事实）来引导下一状态的想象。我们引入结构化状态保真度（SSF）评估指标，基于任务特定事实与字段评分。相比监督微调（SFT），记忆增强训练使SSF最高提升206.3%。在完整规划设置中，策略模型保持冻结，仅通过检索记忆提供任务级技能与步骤级修正指导。在ALFWorld、WebShop和ScienceWorld上，记忆增强智能体相较基线模型取得最高65.4%的相对成功率提升。敏感性分析显示，在不同记忆与动作预算下，检索记忆均能提升任务成功率与效率。
原文摘要 · Abstract (English)
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can still omit task-critical facts, corrupt product attributes, or apply incorrect transition rules. To address such systematic prediction errors, we introduce MemWM, a memory-augmented text-based world model. MemWM uses world memory, a curated memory bank of transition rules, state caches, and hard-to-predict facts, to condition next-state imagination. We evaluate factual state preservation with Structured State Fidelity (SSF), which scores predicted states through benchmark-specific facts and fields. Compared with SFT, memory-augmented training improves SSF by up to 206.3%. In the full planning setting, we keep the policy model frozen and provide policy-side world skill: retrieved task-level skills and step-wise corrective guidance for action selection. Across ALFWorld, WebShop, and ScienceWorld, memory-augmented agents improve downstream success over an SFT-trained world-model agent, with up to a 65.4% relative gain. Sensitivity analyses further show that retrieved memory improves task success and efficiency under different memory and action-budget settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。