PEAM: 通过经验对比内化的参数化具身智能体记忆在Minecraft中的应用
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
AI总结：
提出PEAM框架，通过对比内化失败-纠正轨迹对，将经验转化为参数化技能，实现Minecraft中具身智能体的持续学习与高效执行。
摘要：
我们提出了PEAM，一个在Minecraft中的参数化具身智能体记忆框架，它将智能体记忆从推理时检索转变为通过经验内化的参数驻留技能。PEAM将一个用于开放推理的慢速思考LLM与一个用于反射性执行已巩固技能的快速参数化模块配对。快速模块是一个多模态专家混合LoRA架构，具有按类别物理隔离的适配器，实现了无灾难性遗忘的参数级持续学习。我们将失败视为第一类训练信号：失败-纠正轨迹对通过联合行为克隆和对比目标进行内化，因此智能体不仅学习什么成功，还学习纠正动作与失败动作的区别。为了控制巩固，PEAM引入了参数化值得分来决定哪些经验应被内化，以及一个无尺度的自触发巩固机制来决定何时内化，无需任务特定的手动调整阈值，使智能体能够自我进化，因为触发器可以在任务分布之间转移而无需重新调整。在Minecraft中的实验表明，PEAM提高了长时域任务性能，减轻了对先前巩固技能的遗忘，并提高了参数化与检索效率，优于基于检索的具身智能体和参数化记忆变体。
英文摘要：
We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deliberative LLM for open-ended reasoning with a fast parametric module for reflexive execution of consolidated skills. The fast module is a multimodal Mixture-of-Experts LoRA architecture with per-category physically isolated adapters, enabling parameter-level continual learning without catastrophic forgetting. We treat failure as a first-class training signal: failure--correction trajectory pairs are internalized through a joint behavioral-cloning and contrastive objective, so the agent learns not only what succeeds but also how corrected actions differ from failed ones. To govern consolidation, PEAM introduces a parameterization-worthiness score for deciding which experience should be internalized, and a scale-free self-triggered consolidation mechanism for deciding when to internalize without task-specific hand-tuned thresholds, making the agent self-evolving as the trigger transfers across task distributions without re-tuning. Experiments in Minecraft show that PEAM improves long-horizon task performance, mitigates forgetting on previously consolidated skills, and improves parametric-versus-retrieval efficiency over retrieval-based embodied agents and parametric memory variants.
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。
