AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents

TL;DR

AXIS introduces an API-first framework for LLM-based agents that significantly reduces task completion time and cognitive workload in UI interactions, advancing human-agent-computer interaction.

Contribution

The paper presents AXIS, a novel framework that prioritizes API actions over UI interactions and enables automated API expansion, improving efficiency and reliability of LLM-based agents.

Findings

Reduces task completion time by 65%-70%.

Lowers cognitive workload by 38%-53%.

Maintains high accuracy of 97%-98%.

Abstract

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low reliability due to the extensive sequential UI interactions. To address this issue, we propose AXIS, a novel LLM-based agents framework that prioritize actions through application programming interfaces (APIs) over UI actions. This framework also facilitates the creation and expansion of APIs through automated exploration of applications. Our experiments on Microsoft Word demonstrate that AXIS reduces task completion time by 65%-70% and cognitive workload by 38%-53%, while maintaining accuracy of 97%-98% compared to humans. Our work contributes to a new human-agent-computer interaction (HACI) framework and explores a fresh UI design principle for application providers to turn applications into agents in the era of LLMs, paving the way towards an agent-centric operating system (Agent OS).