Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.10936 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908823778754560 |
|---|---|
| author | Zhao, Jiaxing Xie, Hongbin Lei, Yuzhen Song, Xuan Shi, Zhuoran Li, Lianxin Liu, Shuangxue Xie, Linguo Zhang, Haoran |
| author_facet | Zhao, Jiaxing Xie, Hongbin Lei, Yuzhen Song, Xuan Shi, Zhuoran Li, Lianxin Liu, Shuangxue Xie, Linguo Zhang, Haoran |
| contents | Large Language Models (LLMs) have demonstrated impressive performance in executing complex reasoning tasks. Chain-of-thought effectively enhances reasoning capabilities by unlocking the potential of large models, while multi-agent systems provide more comprehensive solutions by integrating the collective intelligence of multiple agents. However, both approaches face significant limitations. Single-agent with chain-of-thought, due to the inherent complexity of designing cross-domain prompts, faces collaboration challenges. Meanwhile, multi-agent systems consume substantial tokens and inevitably dilute the primary problem, which is particularly problematic in business workflow tasks. To address these challenges, we propose Cochain, a collaboration prompting framework that effectively solves the business workflow collaboration problem by combining knowledge and prompts at a reduced cost. Specifically, we construct an integrated knowledge graph that incorporates knowledge from multiple stages. Furthermore, by maintaining and retrieving a prompts tree, we can obtain prompt information relevant to other stages of the business workflow. We perform extensive evaluations of Cochain across multiple datasets, demonstrating that Cochain outperforms all baselines in both prompt engineering and multi-agent LLMs. Additionally, expert evaluation results indicate that the use of a small model in combination with Cochain outperforms GPT-4. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10936 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cochain: Balancing Insufficient and Excessive Collaboration in LLM Agent Workflows Zhao, Jiaxing Xie, Hongbin Lei, Yuzhen Song, Xuan Shi, Zhuoran Li, Lianxin Liu, Shuangxue Xie, Linguo Zhang, Haoran Computation and Language Large Language Models (LLMs) have demonstrated impressive performance in executing complex reasoning tasks. Chain-of-thought effectively enhances reasoning capabilities by unlocking the potential of large models, while multi-agent systems provide more comprehensive solutions by integrating the collective intelligence of multiple agents. However, both approaches face significant limitations. Single-agent with chain-of-thought, due to the inherent complexity of designing cross-domain prompts, faces collaboration challenges. Meanwhile, multi-agent systems consume substantial tokens and inevitably dilute the primary problem, which is particularly problematic in business workflow tasks. To address these challenges, we propose Cochain, a collaboration prompting framework that effectively solves the business workflow collaboration problem by combining knowledge and prompts at a reduced cost. Specifically, we construct an integrated knowledge graph that incorporates knowledge from multiple stages. Furthermore, by maintaining and retrieving a prompts tree, we can obtain prompt information relevant to other stages of the business workflow. We perform extensive evaluations of Cochain across multiple datasets, demonstrating that Cochain outperforms all baselines in both prompt engineering and multi-agent LLMs. Additionally, expert evaluation results indicate that the use of a small model in combination with Cochain outperforms GPT-4. |
| title | Cochain: Balancing Insufficient and Excessive Collaboration in LLM Agent Workflows |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.10936 |