MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914066807652352 |
|---|---|
| author | Jing, Huihao Hu, Wenbin Luo, Hongyu Yang, Jianhui Fan, Wei Li, Haoran Song, Yangqiu |
| author_facet | Jing, Huihao Hu, Wenbin Luo, Hongyu Yang, Jianhui Fan, Wei Li, Haoran Song, Yangqiu |
| contents | Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MAS with legal tasks is a crucial step. While previous studies have developed legal benchmarks for LLM agents, none are specifically designed to consider the unique advantages of MAS, such as task decomposition, agent specialization, and flexible training. In fact, the lack of evaluation methods limits the potential of MAS in the legal domain. To address this gap, we propose MASLegalBench, a legal benchmark tailored for MAS and designed with a deductive reasoning approach. Our benchmark uses GDPR as the application scenario, encompassing extensive background knowledge and covering complex reasoning processes that effectively reflect the intricacies of real-world legal situations. Furthermore, we manually design various role-based MAS and conduct extensive experiments using different state-of-the-art LLMs. Our results highlight the strengths, limitations, and potential areas for improvement of existing models and MAS architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24922 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning Jing, Huihao Hu, Wenbin Luo, Hongyu Yang, Jianhui Fan, Wei Li, Haoran Song, Yangqiu Artificial Intelligence Computation and Language Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MAS with legal tasks is a crucial step. While previous studies have developed legal benchmarks for LLM agents, none are specifically designed to consider the unique advantages of MAS, such as task decomposition, agent specialization, and flexible training. In fact, the lack of evaluation methods limits the potential of MAS in the legal domain. To address this gap, we propose MASLegalBench, a legal benchmark tailored for MAS and designed with a deductive reasoning approach. Our benchmark uses GDPR as the application scenario, encompassing extensive background knowledge and covering complex reasoning processes that effectively reflect the intricacies of real-world legal situations. Furthermore, we manually design various role-based MAS and conduct extensive experiments using different state-of-the-art LLMs. Our results highlight the strengths, limitations, and potential areas for improvement of existing models and MAS architectures. |
| title | MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.24922 |