To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915935482281984 |
|---|---|
| author | He, Pengfei Dai, Zhenwei Tang, Xianfeng Xing, Yue Liu, Hui Zeng, Jingying Peng, Qiankun Agrawal, Shrivats Varshney, Samarth Wang, Suhang Tang, Jiliang He, Qi |
| author_facet | He, Pengfei Dai, Zhenwei Tang, Xianfeng Xing, Yue Liu, Hui Zeng, Jingying Peng, Qiankun Agrawal, Shrivats Varshney, Samarth Wang, Suhang Tang, Jiliang He, Qi |
| contents | Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating their trustworthiness. While some existing studies approach trustworthiness, they focus on a single type of harmfulness rather than analyze it in a holistic approach from multiple trustworthiness perspectives. We address this gap by proposing a comprehensive definition of trustworthiness inspired by human communication theory (Grice, 1975). Our definition identifies six orthogonal trust dimensions that provide interpretable measures of trustworthiness. Building on this definition, we introduce the Attention Trust Score (A -Trust), a lightweight, attention-based method for evaluating the trustworthiness of messages. We then develop a principled trust management system (TMS) for LLM -MAS that supports both message-level and agent-level trust assessments. Experiments across diverse multi-agent settings and tasks demonstrate that our TMS significantly improves robustness against malicious inputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02546 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems He, Pengfei Dai, Zhenwei Tang, Xianfeng Xing, Yue Liu, Hui Zeng, Jingying Peng, Qiankun Agrawal, Shrivats Varshney, Samarth Wang, Suhang Tang, Jiliang He, Qi Cryptography and Security Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating their trustworthiness. While some existing studies approach trustworthiness, they focus on a single type of harmfulness rather than analyze it in a holistic approach from multiple trustworthiness perspectives. We address this gap by proposing a comprehensive definition of trustworthiness inspired by human communication theory (Grice, 1975). Our definition identifies six orthogonal trust dimensions that provide interpretable measures of trustworthiness. Building on this definition, we introduce the Attention Trust Score (A -Trust), a lightweight, attention-based method for evaluating the trustworthiness of messages. We then develop a principled trust management system (TMS) for LLM -MAS that supports both message-level and agent-level trust assessments. Experiments across diverse multi-agent settings and tasks demonstrate that our TMS significantly improves robustness against malicious inputs. |
| title | To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2506.02546 |