Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912461181943808 |
|---|---|
| author | Han, Bochen Zhang, Songmao |
| author_facet | Han, Bochen Zhang, Songmao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture Han, Bochen Zhang, Songmao Multiagent Systems Artificial Intelligence 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. |
| title | Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2507.01701 |