Explain-Analyze-Generate: A Sequential Multi-Agent Collaboration Method for Complex Reasoning

WenYuan Gu, JiaLe Han, HaoWen Wang, Xiang Li, Bo Cheng


Abstract
Exploring effective collaboration among multiple large language models (LLMs) represents an active research direction, with multiagent debate (MAD) emerging as a popular approach. MAD involves LLMs independently generating responses and refining their own responses by incorporating feedback from other agents in a debate manner. However,empirical experiments reveal the suboptimal performance of MAD in complex reasoning scenarios. We attribute this to the potential misleading caused by peer agents with limited individual capabilities. To address this, we propose a novel sequential collaboration framework named Explain-Analyze-Generate(EAG). By decomposing complex tasks into essential subtasks and employing a pipeline approach, EAG enable agents provide constructive assistance to peers, ultimately yielding higher performance. We conduct experiments on the comprehensive complex language reasoning benchmark: BIG-Bench-Hard (BBH). Our method achieves the highest performance on 19 out of 23 tasks, with an average improvement of 8% across all tasks, and incurs lower costs compared to MAD, demonstrating its effectiveness and efficiency.
Anthology ID:
2025.coling-main.475
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7127–7140
Language:
URL:
https://aclanthology.org/2025.coling-main.475/
DOI:
Bibkey:
Cite (ACL):
WenYuan Gu, JiaLe Han, HaoWen Wang, Xiang Li, and Bo Cheng. 2025. Explain-Analyze-Generate: A Sequential Multi-Agent Collaboration Method for Complex Reasoning. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7127–7140, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Explain-Analyze-Generate: A Sequential Multi-Agent Collaboration Method for Complex Reasoning (Gu et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.475.pdf