Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture
This work addresses the need for more flexible and efficient problem-solving in AI systems where predefined structures are lacking, though it is incremental as it builds on existing multi-agent frameworks.
The paper tackled the problem of improving LLM multi-agent systems by incorporating a blackboard architecture for shared information and dynamic agent selection, achieving competitive SOTA performance with lower token usage across commonsense, reasoning, and mathematical datasets.
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.