Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.13932 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914050027290624 |
|---|---|
| author | Yang, Hailong Gu, Mingxian Zhao, Renhuo Hu, Fuping Deng, Zhaohong Chen, Yitang |
| author_facet | Yang, Hailong Gu, Mingxian Zhao, Renhuo Hu, Fuping Deng, Zhaohong Chen, Yitang |
| contents | Extracting implicit knowledge and logical reasoning abilities from large language models (LLMs) has consistently been a significant challenge. The advancement of multi-agent systems has further en-hanced the capabilities of LLMs. Inspired by the structure of multi-polar neurons (MNs), we propose the XAgents framework, an in-terpretable multi-agent cooperative framework based on the IF-THEN rule-based system. The IF-Parts of the rules are responsible for logical reasoning and domain membership calculation, while the THEN-Parts are comprised of domain expert agents that generate domain-specific contents. Following the calculation of the member-ship, XAgetns transmits the task to the disparate domain rules, which subsequently generate the various responses. These re-sponses are analogous to the answers provided by different experts to the same question. The final response is reached at by eliminat-ing the hallucinations and erroneous knowledge of the LLM through membership computation and semantic adversarial genera-tion of the various domain rules. The incorporation of rule-based interpretability serves to bolster user confidence in the XAgents framework. We evaluate the efficacy of XAgents through a com-parative analysis with the latest AutoAgents, in which XAgents demonstrated superior performance across three distinct datasets. We perform post-hoc interpretable studies with SHAP algorithm and case studies, proving the interpretability of XAgent in terms of input-output feature correlation and rule-based semantics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13932 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | XAgents: A Framework for Interpretable Rule-Based Multi-Agents Cooperation Yang, Hailong Gu, Mingxian Zhao, Renhuo Hu, Fuping Deng, Zhaohong Chen, Yitang Artificial Intelligence Multiagent Systems Extracting implicit knowledge and logical reasoning abilities from large language models (LLMs) has consistently been a significant challenge. The advancement of multi-agent systems has further en-hanced the capabilities of LLMs. Inspired by the structure of multi-polar neurons (MNs), we propose the XAgents framework, an in-terpretable multi-agent cooperative framework based on the IF-THEN rule-based system. The IF-Parts of the rules are responsible for logical reasoning and domain membership calculation, while the THEN-Parts are comprised of domain expert agents that generate domain-specific contents. Following the calculation of the member-ship, XAgetns transmits the task to the disparate domain rules, which subsequently generate the various responses. These re-sponses are analogous to the answers provided by different experts to the same question. The final response is reached at by eliminat-ing the hallucinations and erroneous knowledge of the LLM through membership computation and semantic adversarial genera-tion of the various domain rules. The incorporation of rule-based interpretability serves to bolster user confidence in the XAgents framework. We evaluate the efficacy of XAgents through a com-parative analysis with the latest AutoAgents, in which XAgents demonstrated superior performance across three distinct datasets. We perform post-hoc interpretable studies with SHAP algorithm and case studies, proving the interpretability of XAgent in terms of input-output feature correlation and rule-based semantics. |
| title | XAgents: A Framework for Interpretable Rule-Based Multi-Agents Cooperation |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2411.13932 |