Autonomous Agents for Collaborative Task under Information Asymmetry
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909352278884352 |
|---|---|
| author | Liu, Wei Wang, Chenxi Wang, Yifei Xie, Zihao Qiu, Rennai Dang, Yufan Du, Zhuoyun Chen, Weize Yang, Cheng Qian, Chen |
| author_facet | Liu, Wei Wang, Chenxi Wang, Yifei Xie, Zihao Qiu, Rennai Dang, Yufan Du, Zhuoyun Chen, Weize Yang, Cheng Qian, Chen |
| contents | Large Language Model Multi-Agent Systems (LLM-MAS) have achieved great progress in solving complex tasks. It performs communication among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents' collaborations are leveraged to perform multi-person tasks, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents' communication toward effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents' task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14928 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Autonomous Agents for Collaborative Task under Information Asymmetry Liu, Wei Wang, Chenxi Wang, Yifei Xie, Zihao Qiu, Rennai Dang, Yufan Du, Zhuoyun Chen, Weize Yang, Cheng Qian, Chen Artificial Intelligence Computation and Language Human-Computer Interaction Multiagent Systems Social and Information Networks Large Language Model Multi-Agent Systems (LLM-MAS) have achieved great progress in solving complex tasks. It performs communication among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents' collaborations are leveraged to perform multi-person tasks, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents' communication toward effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents' task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes. |
| title | Autonomous Agents for Collaborative Task under Information Asymmetry |
| topic | Artificial Intelligence Computation and Language Human-Computer Interaction Multiagent Systems Social and Information Networks |
| url | https://arxiv.org/abs/2406.14928 |