让AI通过经验自动修正错误知识，提升游戏规划能力
Experience-based Knowledge Correction for Robust Planning in Minecraft
- 基于过往成功与失败构建动态知识图谱，主动修正错误认知
- 仅用70亿参数模型，在多个任务中超越大型闭源模型表现
- 适合需要长期规划且依赖正确知识的智能体研究者使用
基于大语言模型（LLM）的规划已推动智能体在《我的世界》等长周期环境中的发展，其中掌握目标物品依赖关系和可行动作至关重要。然而，LLM常带有错误先验，即使通过提示和反馈也难以自我修正。本文提出XENON（eXpErience-based kNOwledge correctioN），一种通过经验算法修正知识的智能体，增强对错误先验的鲁棒性及稀疏二值反馈下的适应能力。XENON整合两个机制：自适应依赖图，利用历史成功修正物品依赖；故障感知动作记忆，利用历史失败修正动作知识。二者协同使XENON在有限指导下习得复杂依赖关系。在多个《我的世界》基准测试中，XENON在知识学习与长周期规划上均优于现有智能体。尤为显著的是，仅使用70亿参数的开源模型，其性能超越依赖更大闭源模型的基线。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based planning has advanced embodied agents in long-horizon environments such as Minecraft, where acquiring latent knowledge of goal (or item) dependencies and feasible actions is critical. However, LLMs often begin with flawed priors and fail to correct them through prompting, even with feedback. We present XENON (eXpErience-based kNOwledge correctioN), an agent that algorithmically revises knowledge from experience, enabling robustness to flawed priors and sparse binary feedback. XENON integrates two mechanisms: Adaptive Dependency Graph, which corrects item dependencies using past successes, and Failure-aware Action Memory, which corrects action knowledge using past failures. Together, these components allow XENON to acquire complex dependencies despite limited guidance. Experiments across multiple Minecraft benchmarks show that XENON outperforms prior agents in both knowledge learning and long-horizon planning. Remarkably, with only a 7B open-weight LLM, XENON surpasses agents that rely on much larger proprietary models. Project page: https://sjlee-me.github.io/XENON
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。