Beyond Browsing: API-Based Web Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Yueqi, Xu, Frank, Zhou, Shuyan, Neubig, Graham
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908409655197696
author Song, Yueqi
Xu, Frank
Zhou, Shuyan
Neubig, Graham
author_facet Song, Yueqi
Xu, Frank
Zhou, Shuyan
Neubig, Graham
contents Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another interface designed specifically for machine interaction with online content: application programming interfaces (APIs). In this paper we ask -- what if we were to take tasks traditionally tackled by Browsing Agents, and give AI agents access to APIs? To do so, we propose two varieties of agents: (1) an API-calling agent that attempts to perform online tasks through APIs only, similar to traditional coding agents, and (2) a Hybrid Agent that can interact with online data through both web browsing and APIs. In experiments on WebArena, a widely-used and realistic benchmark for web navigation tasks, we find that API-Based Agents outperform web Browsing Agents. Hybrid Agents out-perform both others nearly uniformly across tasks, resulting in a more than 24.0% absolute improvement over web browsing alone, achieving a success rate of 38.9%, the SOTA performance among task-agnostic agents. These results strongly suggest that when APIs are available, they present an attractive alternative to relying on web browsing alone.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16464
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Browsing: API-Based Web Agents
Song, Yueqi
Xu, Frank
Zhou, Shuyan
Neubig, Graham
Computation and Language
Multiagent Systems
Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another interface designed specifically for machine interaction with online content: application programming interfaces (APIs). In this paper we ask -- what if we were to take tasks traditionally tackled by Browsing Agents, and give AI agents access to APIs? To do so, we propose two varieties of agents: (1) an API-calling agent that attempts to perform online tasks through APIs only, similar to traditional coding agents, and (2) a Hybrid Agent that can interact with online data through both web browsing and APIs. In experiments on WebArena, a widely-used and realistic benchmark for web navigation tasks, we find that API-Based Agents outperform web Browsing Agents. Hybrid Agents out-perform both others nearly uniformly across tasks, resulting in a more than 24.0% absolute improvement over web browsing alone, achieving a success rate of 38.9%, the SOTA performance among task-agnostic agents. These results strongly suggest that when APIs are available, they present an attractive alternative to relying on web browsing alone.
title Beyond Browsing: API-Based Web Agents
topic Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2410.16464