AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要