paper-with-me

Papers

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

2026-08-06 · Jiacheng Wei, Zhaoxin Fan, Xin Wen, Yuqin Lan, Dongrun Li, Wenjun Wu, Faguo Wu, Xiao Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2608.05790

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models

2025-01-29 · Manish Sanwal

Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediat…

LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration

2025-03-25 · Yuyao Zhang, Jinghao Li, Yu-Wing Tai

Text-to-image (T2I) generation has made remarkable progress, yet existing systems still lack intuitive control over spatial composition, object consistency, and multi-step editing. We present $\textbf{LayerCraft}$, a mod…

Image GenerationObjectPrompt EngineeringScene Generation+2

Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions

2025-09-11 · Qinnan Hu, Yuntao Wang, Yuan Gao, Zhou Su 외 arxiv

Large language models (LLMs)-empowered autonomous agents are transforming both digital and physical environments by enabling adaptive, multi-agent collaboration. While these agents offer significant opportunities across …

Perspectives on a Reliability Monitoring Framework for Agentic AI Systems

2025-11-12 · Niclas Flehmig, Mary Ann Lundteigen, Shen Yin arxiv

The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite …

Out-of-Distribution Detection

Fetch.ai: An Architecture for Modern Multi-Agent Systems

2025-10-21 · Michael J. Wooldridge, Attila Bagoly, Jonathan J. Ward, Emanuele La Malfa 외 arxiv

Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust a…