用统一模型解决游戏智能体动作空间难题，性能超越专用模型。
OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
- 将抽象动作视为推理中间步骤，统一高层规划与底层控制
- 在800多个任务上实现新最优成功率，优于专用模型
- 开源完整工具链，支持可复现研究
动作空间的选择是构建端到端可训练智能体的关键挑战。本文首次在开放世界《我的世界》中对主流抽象动作空间和分词器进行了大规模系统性比较。分析表明，无单一动作空间通用最优，最佳抽象高度依赖任务，导致通用智能体构建困难。为此，我们提出链式动作（Chain of Action, CoA）框架，将高层规划与底层控制统一于单一视觉-语言-动作模型中。CoA将抽象动作视为中间推理步骤，而非独立策略指令，引导最终可执行动作生成。此外，基于CoA范式，在多种动作空间混合数据上训练的全功能智能体，学习到更鲁棒、泛化性更强的策略。该统一智能体在整体任务成功率上达到新基准，超越强健的专用基线模型。为促进可复现研究，我们发布OpenHA（开放层级智能体）套件，包含超800项任务的综合基准、精选数据集、源代码及所有预训练模型检查点，地址：https://github.com/CraftJarvis/OpenHA
原文摘要 · Abstract (English)
The choice of action spaces is a critical yet unresolved challenge in developing capable, end-to-end trainable agents. This paper first presents a large-scale, systematic comparison of prominent abstracted action spaces and tokenizers for Vision-Language-Action (VLA) or hierarchical agent models in the open-ended Minecraft. Our analysis reveals that no single action space is universally optimal; instead, the most effective abstraction is highly task-dependent, creating a dilemma for building generalist agents. To resolve this, we introduce Chain of Action (CoA), a novel framework that unifies high-level planning and low-level control within a single, monolithic VLA model. CoA treats an abstracted action not as a command for a separate policy, but as an intermediate reasoning step--akin to a chain of thought--that guides the generation of the final, executable action. Furthermore, we demonstrate that an All-in-One agent trained on a diverse mixture of action spaces using the CoA paradigm learns a more robust and generalizable policy. This unified agent achieves a new state-of-the-art, improving the overall task success rate over strong, specialized baselines. To foster reproducible research, we release the OpenHA (Open Hierarchical Agents) suite, which includes our comprehensive benchmark of over 800 distinct tasks, curated datasets, source code, and all pretrained model checkpoints at https://github.com/CraftJarvis/OpenHA
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。