Lune

ACL Findings2025

Beyond Browsing: API-Based Web Agents

Yueqi Song, Frank F. Xu, Shuyan Zhou, Graham Neubig

摘要

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 outperform 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.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 18 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations 引用了 GPT-4V(ision) is a Generalist Web Agent, if Grounded
  • GPT-4V(ision) is a Generalist Web Agent, if Grounded 引用了 AgentBench: Evaluating LLMs as Agents
  • GPT-4V(ision) is a Generalist Web Agent, if Grounded 引用了 WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
  • AgentBench: Evaluating LLMs as Agents 引用了 WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
  • ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs 引用了 Gorilla: Large Language Model Connected with Massive APIs
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper18

  1. Self-Challenging Language Model AgentsYifei Zhou, Sergey Levine, Jason E. Weston, Xian Li 等NeurIPS 2025 · 52 次引用
  2. Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time InteractionJunhong Shen, Hao Bai, Lunjun Zhang, Yifei Zhou 等NeurIPS 2025 · 34 次引用
  3. CoAct-1: Computer-using Multi-agent System with Coding ActionsLinxin Song, Yutong Dai, Viraj Prabhu, Jieyu Zhang 等ICLR 2026 · 32 次引用
  4. Go-Browse: Training Web Agents with Structured ExplorationApurva Gandhi, Graham NeubigICLR 2026 · 30 次引用
  5. AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human DemonstrationsGaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng 等ACL 2025 · 19 次引用

它引用的 Paper28

  1. Gorilla: Large Language Model Connected with Massive APIsShishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. GonzalezNeurIPS 2024 · 1,715 次引用
  2. WebShop: Towards Scalable Real-World Web Interaction with Grounded Language AgentsShunyu Yao, Howard Chen, John Yang, Karthik NarasimhanNeurIPS 2022 · 1,477 次引用
  3. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu 等ICLR 2024 · 1,469 次引用
  4. AgentBench: Evaluating LLMs as AgentsXiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu 等ICLR 2024 · 748 次引用
  5. GPT-4V(ision) is a Generalist Web Agent, if GroundedBoyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun 等ICML 2024 · 496 次引用

相关 Paper

  1. WebArena: A Realistic Web Environment for Building Autonomous AgentsShuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou 等ICLR 2024 · 1,197 次引用
  2. Nested Browser-Use Learning for Agentic Information SeekingBaixuan Li, Jialong Wu, Wenbiao Yin, Kuan Li 等ACL 2026 · 6 次引用
  3. WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji 等ICML 2024 · 188 次引用
  4. VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web TasksJing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur 等ACL 2024 · 25 次引用
  5. Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM AgentsYueqi Song, Ketan Ramaneti, Zaid Sheikh, Ziru Chen 等ICLR 2026 · 18 次引用
黄昏的海面,两侧是细线勾勒的悬崖