Dart：基于DAG与区块链治理的可信LLM多智能体协作框架
原标题：DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaboration
AI 摘要
Dart 提出了一种基于有向无环图（DAG）的声誉与激励机制框架，结合区块链治理，用于可信的 LLM 多智能体协作。该框架统一了 DAG 工作流编排、能力与声誉感知的任务分配、动态行为更新、多因素激励以及智能合约问责与 IPFS 存储。实验表明，Dart 在 GSM8K 上达到 93.6% 的 Pass@1，在 150 轮纵向试验中平均任务成功率为 93.33%，并能有效隔离恶意智能体，将系统成功率恢复至 99.8%。
正文节选
Dart: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaboration Abstract Large language model (LLM)-based multi-agent systems (MAS) predominantly rely on centralized orchestration and lack formal verification mechanisms for agent reliability, participation, and system-level behavioral alignment. These shortcomings leave open environments severely vulnerable to uncooperative or malicious agents. This work proposes Dart, a Direct