GPT-4V(ision) is a Generalist Web Agent, if Grounded

• URL: http://arxiv.org/abs/2401.01614v2
• Date: Tue, 12 Mar 2024 23:14:33 GMT
• Title: GPT-4V(ision) is a Generalist Web Agent, if Grounded
• Authors: Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, Yu Su
• Abstract summary: We show that GPT-4V can successfully complete 51.1 of the tasks on live websites if we manually ground its textual plans into actions on the websites. We propose SEEACT, a web agent that harnesses the power of LMMs for integrated visual understanding and acting on the web.
• Score: 20.940613419944015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent development on large multimodal models (LMMs), especially GPT-4V(ision) and Gemini, has been quickly expanding the capability boundaries of multimodal models beyond traditional tasks like image captioning and visual question answering. In this work, we explore the potential of LMMs like GPT-4V as a generalist web agent that can follow natural language instructions to complete tasks on any given website. We propose SEEACT, a generalist web agent that harnesses the power of LMMs for integrated visual understanding and acting on the web. We evaluate on the recent MIND2WEB benchmark. In addition to standard offline evaluation on cached websites, we enable a new online evaluation setting by developing a tool that allows running web agents on live websites. We show that GPT-4V presents a great potential for web agents -- it can successfully complete 51.1 of the tasks on live websites if we manually ground its textual plans into actions on the websites. This substantially outperforms text-only LLMs like GPT-4 or smaller models (FLAN-T5 and BLIP-2) specifically fine-tuned for web agents. However, grounding still remains a major challenge. Existing LMM grounding strategies like set-of-mark prompting turns out to be not effective for web agents, and the best grounding strategy we develop in this paper leverages both the HTML structure and visuals. Yet, there is still a substantial gap with oracle grounding, leaving ample room for further improvement. All code, data, and evaluation tools are available at https://github.com/OSU-NLP-Group/SeeAct.

Related papers

• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents [52.13695464678006]
  This study enhances an LLM-based web agent by simply refining its observation and action space. AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively.
  arXiv  Detail & Related papers  (2024-10-17T17:50:38Z)
• VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? [115.60866817774641]
  Multimodal Large Language models (MLLMs) have shown promise in web-related tasks. evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks. bench is a multimodal benchmark designed to assess the capabilities of MLLMs across a variety of web tasks.
  arXiv  Detail & Related papers  (2024-04-09T02:29:39Z)
• Design2Code: How Far Are We From Automating Front-End Engineering? [83.06100360864502]
  We formalize this as a Design2Code task and conduct comprehensive benchmarking. Specifically, we manually curate a benchmark of 484 diverse real-world webpages as test cases. We develop a suite of multimodal prompting methods and show their effectiveness on GPT-4V and Gemini Pro Vision. Both human evaluation and automatic metrics show that GPT-4V performs the best on this task compared to other models.
  arXiv  Detail & Related papers  (2024-03-05T17:56:27Z)
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models [65.18602126334716]
  Existing web agents typically only handle one input modality and are evaluated only in simplified web simulators or static web snapshots. We introduce WebVoyager, an innovative Large Multimodal Model (LMM) powered web agent that can complete user instructions end-to-end by interacting with real-world websites. We show that WebVoyager achieves a 59.1% task success rate on our benchmark, significantly surpassing the performance of both GPT-4 (All Tools) and the WebVoyager (text-only) setups.
  arXiv  Detail & Related papers  (2024-01-25T03:33:18Z)
• AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models [2.234037966956278]
  We introduce AllTogether, a standardized prompt template that enhances task context representation. We evaluate the efficacy of this approach through prompt learning and instruction finetuning based on open-source Llama-2 and API-accessible GPT models.
  arXiv  Detail & Related papers  (2023-10-20T11:10:14Z)
• A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis [69.15016747150868]
  We introduce WebAgent, an agent that learns from self-experience to complete tasks on real websites. WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites. We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks.
  arXiv  Detail & Related papers  (2023-07-24T14:56:30Z)
• Mind2Web: Towards a Generalist Agent for the Web [25.363429937913065]
  Mind2Web is the first dataset for developing and evaluating generalist agents for the web. With over 2,000 open-ended tasks collected from 137 websites spanning 31 domains, Mind2Web provides three necessary ingredients for building generalist web agents. Based on Mind2Web, we conduct an initial exploration of using large language models (LLMs) for building generalist web agents.
  arXiv  Detail & Related papers  (2023-06-09T17:44:31Z)
• Multimodal Web Navigation with Instruction-Finetuned Foundation Models [99.14209521903854]
  We study data-driven offline training for web agents with vision-language foundation models. We propose an instruction-following multimodal agent, WebGUM, that observes both webpage screenshots and HTML pages. We empirically demonstrate this recipe improves the agent's ability of grounded multimodal perception, HTML comprehension, and multi-step reasoning.
  arXiv  Detail & Related papers  (2023-05-19T17:44:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.