AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems
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_ | 1866913234347360256 |
|---|---|
| author | Lu, Jiaying Pan, Bo Chen, Jieyi Feng, Yingchaojie Hu, Jingyuan Peng, Yuchen Chen, Wei |
| author_facet | Lu, Jiaying Pan, Bo Chen, Jieyi Feng, Yingchaojie Hu, Jingyuan Peng, Yuchen Chen, Wei |
| contents | Recently, Large Language Model based Autonomous system(LLMAS) has gained great popularity for its potential to simulate complicated behaviors of human societies. One of its main challenges is to present and analyze the dynamic events evolution of LLMAS. In this work, we present a visualization approach to explore detailed statuses and agents' behavior within LLMAS. We propose a general pipeline that establishes a behavior structure from raw LLMAS execution events, leverages a behavior summarization algorithm to construct a hierarchical summary of the entire structure in terms of time sequence, and a cause trace method to mine the causal relationship between agent behaviors. We then develop AgentLens, a visual analysis system that leverages a hierarchical temporal visualization for illustrating the evolution of LLMAS, and supports users to interactively investigate details and causes of agents' behaviors. Two usage scenarios and a user study demonstrate the effectiveness and usability of our AgentLens. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08995 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems Lu, Jiaying Pan, Bo Chen, Jieyi Feng, Yingchaojie Hu, Jingyuan Peng, Yuchen Chen, Wei Human-Computer Interaction Artificial Intelligence Recently, Large Language Model based Autonomous system(LLMAS) has gained great popularity for its potential to simulate complicated behaviors of human societies. One of its main challenges is to present and analyze the dynamic events evolution of LLMAS. In this work, we present a visualization approach to explore detailed statuses and agents' behavior within LLMAS. We propose a general pipeline that establishes a behavior structure from raw LLMAS execution events, leverages a behavior summarization algorithm to construct a hierarchical summary of the entire structure in terms of time sequence, and a cause trace method to mine the causal relationship between agent behaviors. We then develop AgentLens, a visual analysis system that leverages a hierarchical temporal visualization for illustrating the evolution of LLMAS, and supports users to interactively investigate details and causes of agents' behaviors. Two usage scenarios and a user study demonstrate the effectiveness and usability of our AgentLens. |
| title | AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2402.08995 |