发表机构
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University; Beihang University; School of Artificial Intelligence, Beihang University; School of Mathematical Sciences, Beihang University; Zhongguancun Laboratory（北京航空航天大学未来区块链与隐私计算高精尖创新中心; 北京航空航天大学; 北京航空航天大学人工智能学院; 北京航空航天大学数学科学学院; 中关村实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ChainClaw是基于OpenClaw的分层区块链原生智能体框架，通过三层架构解决链上执行的反应性、不可逆性和可观测性缺口，在自建基准上的安全性和任务完成度均优于代表性基线。
AI 中文摘要
通用大语言模型智能体在工具增强任务上表现出色，但它们的假设在区块链环境中不成立。链上执行具有有状态、对抗性、经济不可逆的特点，暴露出三个基本缺口：反应性、不可逆性和可观测性。我们提出ChainClaw，这是一种基于OpenClaw构建的原生区块链智能体框架，通过分层架构解决所有三个缺口，该架构包括事件驱动编排层、基于模拟的安全智能层和链上监控运行时层，由跨层内存子系统统一。ChainClaw通过事件摄入和模拟反馈弥合反应性缺口，通过包含交易模拟和动作保护的执行前安全管道弥合不可逆性缺口，通过链上读取适配器和交易监控器弥合可观测性缺口。我们在一个专门构建的基准上评估ChainClaw，该基准涵盖四个类别和五个维度的七个任务。ChainClaw在安全性和任务完成度上均持续优于代表性基线。
英文摘要
General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockchain environments. On-chain execution is stateful, adversarial, and economically irreversible, exposing three fundamental gaps: Reactivity, Irreversibility, and Observability. We propose ChainClaw, a blockchain-native agent framework built on OpenClaw, that addresses all three gaps through a layered architecture comprising an event-driven orchestration layer, a simulation-based safety intelligence layer, and an on-chain monitoring runtime layer, unified by a cross-layer memory subsystem. ChainClaw closes the Reactivity gap via event ingestion and simulation feedback, the Irreversibility gap via a pre-execution safety pipeline with transaction simulation and action guard, and the Observability gap via an on-chain read adapter and transaction monitor. We evaluate ChainClaw on a purpose-built benchmark covering seven tasks across four categories and five dimensions. ChainClaw consistently outperforms representative baselines on both safety and task completion.
Comments8 pages,3 figures
