arXiv:2608.05790cs.AIcs.CR2026-08

ChainClaw让AI代理安全执行链上操作,解决状态、对抗、不可逆三大难题。

ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution

论文配图:ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution
图 1 · 摘自论文原文
  • 分层架构:事件驱动+模拟安全+链上监控,跨层共享记忆
  • 在7类任务中,安全性和完成率均超越基线模型
  • 适合需要高可靠性的智能合约自动化场景

通用大语言模型代理在工具增强任务中表现强劲,但在区块链环境中因假设失效而面临挑战。链上执行具有状态性、对抗性和经济不可逆性,暴露反应性、不可逆性和可观测性三大根本缺陷。我们提出ChainClaw,一个基于OpenClaw的原生区块链代理框架,通过三层架构——事件驱动编排层、基于模拟的安全智能层、链上监控运行时层——并由跨层记忆系统统一整合,分别解决三类问题:通过事件摄入与模拟反馈修复反应性,通过预执行安全流水线(交易模拟+动作守卫)应对不可逆性,通过链上读取适配器和交易监控实现可观测性。我们在自建基准上评估了七项任务,覆盖四类场景与五个维度,ChainClaw在安全性和任务完成度上均持续优于代表性基线。

原文摘要 · Abstract (English)

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.

区块链智能代理安全执行链上AI

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。