Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents

• URL: http://arxiv.org/abs/2502.11357v2
• Date: Wed, 19 Feb 2025 01:38:06 GMT
• Title: Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
• Authors: Vardaan Pahuja, Yadong Lu, Corby Rosset, Boyu Gou, Arindam Mitra, Spencer Whitehead, Yu Su, Ahmed Awadallah,
• Abstract summary: We develop a scalable recipe to synthesize the largest and most diverse trajectory-level dataset to date. This dataset contains over 94K successful multimodal web trajectories, spanning 49K unique URLs, 720K screenshots, and 33M web elements. We demonstrate strong performance on both offline and online web agent benchmarks such as Mind2Web-Live, Multimodal-Mind2Web, and MiniWob++.
• Score: 16.161877699225986
• License:
• Abstract: Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation benchmarks, their performance still falls substantially short of human-level capabilities in more realistic online settings. A key bottleneck is the lack of diverse and large-scale trajectory-level datasets across various domains, which are expensive to collect. In this paper, we address this challenge by developing a scalable recipe to synthesize the largest and most diverse trajectory-level dataset to date, containing over 94K successful multimodal web trajectories, spanning 49K unique URLs, 720K screenshots, and 33M web elements. In particular, we leverage extensive web exploration and refinement to obtain diverse task intents. The average cost is 28 cents per successful trajectory, making it affordable to a wide range of users in the community. Leveraging this dataset, we train Explorer, a multimodal web agent, and demonstrate strong performance on both offline and online web agent benchmarks such as Mind2Web-Live, Multimodal-Mind2Web, and MiniWob++. Additionally, our experiments highlight data scaling as a key driver for improving web agent capabilities. We hope this study makes state-of-the-art LMM-based agent research at a larger scale more accessible.

Related papers

• WebWalker: Benchmarking LLMs in Web Traversal [64.48425443951749]
  We introduce WebWalkerQA, a benchmark designed to assess the ability of LLMs to perform web traversal. We propose WebWalker, which is a multi-agent framework that mimics human-like web navigation through an explore-critic paradigm.
  arXiv  Detail & Related papers  (2025-01-13T18:58:07Z)
• OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization [66.22117723598872]
  We introduce an open-source framework designed to facilitate the development of multimodal web agent. We first train the base model with imitation learning to gain the basic abilities. We then let the agent explore the open web and collect feedback on its trajectories.
  arXiv  Detail & Related papers  (2024-10-25T15:01:27Z)
• 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)
• WebQuest: A Benchmark for Multimodal QA on Web Page Sequences [10.008284460456107]
  WebQuest is a multi-page question-answering dataset that requires reasoning across multiple web pages. Our dataset evaluates information extraction, multimodal retrieval and composition of information from many web pages. We evaluate leading proprietary multimodal models like GPT-4V, Gemini Flash, Claude 3, and open source models like InstructBLIP, PaliGemma on our dataset.
  arXiv  Detail & Related papers  (2024-09-06T18:44:25Z)
• Exploring the Capabilities of Large Multimodal Models on Dense Text [58.82262549456294]
  We propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini, and various open-source LMMs. We find that even with automatically labeled training datasets, significant improvements in model performance can be achieved.
  arXiv  Detail & Related papers  (2024-05-09T07:47:25Z)
• MMInA: Benchmarking Multihop Multimodal Internet Agents [36.173995299002]
  We present MMInA, a multihop and multimodal benchmark to evaluate the embodied agents for compositional Internet tasks. Our data includes 1,050 human-written tasks covering various domains such as shopping and travel. Our method significantly improved both the single-hop and multihop web browsing abilities of agents.
  arXiv  Detail & Related papers  (2024-04-15T17:59:50Z)
• 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)
• 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.