探索基于黑板架构的高级大语言模型多智能体系统
Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture
AI总结：
本文将黑板架构引入大语言模型多智能体系统，通过信息共享、基于黑板内容的智能体选择及迭代执行直至共识，在多个数据集上以更少 token 实现与最先进多智能体系统相当甚至更优的平均性能。
摘要：
在本文中，我们提出将黑板架构引入大语言模型多智能体系统（MASs），从而实现：（1）在整个问题求解过程中，具有不同角色的智能体能够共享所有信息以及其他智能体的消息；（2）根据黑板当前内容选择将要采取行动的智能体；（3）选择与执行回合反复进行，直到黑板上达成共识。我们开发了该方案的首个实现，并在常识知识、推理和数学数据集上进行了实验。结果表明，我们的系统能够取得最佳平均性能，与最先进的静态和动态多智能体系统相比具有竞争力，同时消耗更少的 token。我们的方案有潜力支持复杂且动态的问题求解场景，尤其是在缺乏明确定义的结构或工作流的情况下。
英文摘要：
In this paper, we propose to incorporate the blackboard architecture into LLM multi-agent systems (MASs) so that (1) agents with various roles can share all the information and others' messages during the whole problem-solving process, (2) agents that will take actions are selected based on the current content of the blackboard, and (3) the selection and execution round is repeated until a consensus is reached on the blackboard. We develop the first implementation of this proposal and conduct experiments on commonsense knowledge, reasoning and mathematical datasets. The results show that our system can be competitive with the SOTA static and dynamic MASs by achieving the best average performance, and at the same time manage to spend less tokens. Our proposal has the potential to enable complex and dynamic problem-solving where well-defined structures or workflows are unavailable.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
