MMInA: Benchmarking Multihop Multimodal Internet Agents

• URL: http://arxiv.org/abs/2404.09992v1
• Date: Mon, 15 Apr 2024 17:59:50 GMT
• Title: MMInA: Benchmarking Multihop Multimodal Internet Agents
• Authors: Ziniu Zhang, Shulin Tian, Liangyu Chen, Ziwei Liu,
• Abstract summary: 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.
• Score: 36.173995299002
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous embodied agents live on an Internet of multimedia websites. Can they hop around multimodal websites to complete complex user tasks? Existing benchmarks fail to assess them in a realistic, evolving environment for their embodiment across websites. To answer this question, we present MMInA, a multihop and multimodal benchmark to evaluate the embodied agents for compositional Internet tasks, with several appealing properties: 1) Evolving real-world multimodal websites. Our benchmark uniquely operates on evolving real-world websites, ensuring a high degree of realism and applicability to natural user tasks. Our data includes 1,050 human-written tasks covering various domains such as shopping and travel, with each task requiring the agent to autonomously extract multimodal information from web pages as observations; 2) Multihop web browsing. Our dataset features naturally compositional tasks that require information from or actions on multiple websites to solve, to assess long-range reasoning capabilities on web tasks; 3) Holistic evaluation. We propose a novel protocol for evaluating an agent's progress in completing multihop tasks. We experiment with both standalone (multimodal) language models and heuristic-based web agents. Extensive experiments demonstrate that while long-chain multihop web tasks are easy for humans, they remain challenging for state-of-the-art web agents. We identify that agents are more likely to fail on the early hops when solving tasks of more hops, which results in lower task success rates. To address this issue, we propose a simple memory augmentation approach replaying past action trajectories to reflect. Our method significantly improved both the single-hop and multihop web browsing abilities of agents. See our code and data at https://mmina.cliangyu.com

Related papers

• 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)
• Beyond Browsing: API-Based Web Agents [58.39129004543844]
  API-based agents outperform web browsing agents in experiments on WebArena. Hybrid Agents out-perform both others nearly uniformly across tasks. Results strongly suggest that when APIs are available, they present an attractive alternative to relying on web browsing alone.
  arXiv  Detail & Related papers  (2024-10-21T19:46:06Z)
• 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)
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks [93.85005277463802]
  VisualWebArena is a benchmark designed to assess the performance of multimodal web agents on realistic tasks. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives.
  arXiv  Detail & Related papers  (2024-01-24T18:35:21Z)
• 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)

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.