通过知识性经验学习对齐代理世界模型
Aligning Agentic World Models via Knowledgeable Experience Learning
AI总结：
WorldMind通过知识性经验学习对齐代理世界模型，解决物理模拟中的幻觉问题，实现跨环境的高效迁移。
摘要：
当前大型语言模型（LLMs）表现出关键的模态断开：它们拥有庞大的语义知识，但缺乏对物理世界不可变定律的程序性基础。因此，尽管这些代理隐式地充当世界模型，但其模拟往往遭受物理幻觉——生成逻辑上正确但物理上不可执行的计划。现有的对齐策略主要依赖于资源密集型训练或微调，试图将动态环境规则压缩成静态模型参数。然而，这种参数封装本质上是僵化的，难以适应物理动态的开放性变化，而无需持续、昂贵的重新训练。为弥合这一差距，我们引入WorldMind，一个能够自主构建符号世界知识库的框架，通过合成环境反馈来统一过程经验以通过预测误差强制物理可行性，并通过成功轨迹引导任务最优性。在EB-ALFRED和EB-Habitat上的实验表明，WorldMind相比基线在性能上表现优异，具有显著的跨模型和跨环境迁移能力。
英文摘要：
Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of the physical world. Consequently, while these agents implicitly function as world models, their simulations often suffer from physical hallucinations-generating plans that are logically sound but physically unexecutable. Existing alignment strategies predominantly rely on resource-intensive training or fine-tuning, which attempt to compress dynamic environmental rules into static model parameters. However, such parametric encapsulation is inherently rigid, struggling to adapt to the open-ended variability of physical dynamics without continuous, costly retraining. To bridge this gap, we introduce WorldMind, a framework that autonomously constructs a symbolic World Knowledge Repository by synthesizing environmental feedback. Specifically, it unifies Process Experience to enforce physical feasibility via prediction errors and Goal Experience to guide task optimality through successful trajectories. Experiments on EB-ALFRED and EB-Habitat demonstrate that WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
