Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Qineng Wang, Zihao Wang, Ying Su, Hanghang Tong, Yangqiu Song
Abstract
Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experiments, where we propose a novel group discussion framework to enrich the set of discussion mechanisms. Interestingly, our results show that a single-agent LLM with strong prompts can achieve almost the same best performance as the best existing discussion approach on a wide range of reasoning tasks and backbone LLMs. We observed that the multi-agent discussion performs better than a single agent only when there is no demonstration in the prompt. Further study reveals the common interaction mechanisms of LLMs during the discussion. Our code can be found in https://github.com/HKUST-KnowComp/LLM-discussion.- Anthology ID:
- 2024.acl-long.331
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6106–6131
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.331
- DOI:
- Cite (ACL):
- Qineng Wang, Zihao Wang, Ying Su, Hanghang Tong, and Yangqiu Song. 2024. Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6106–6131, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key? (Wang et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.331.pdf