MELLON - Multimodal Enhanced LLM for Online Navigation

• URL: http://arxiv.org/abs/2608.09121v1
• Date: Mon, 10 Aug 2026 04:56:22 GMT
• Title: MELLON - Multimodal Enhanced LLM for Online Navigation
• Abstract summary: Current baselines on web navigation are either unimodal or lack strong reasoning abilities given multimodal inputs.<n>We propose three innovative enhancements: Multimodal Enhanced LLM for Online Navigation (MELLON), VQAgent, and Multimodal Ranker.<n>MELLON demonstrates a significant improvement in task completion accuracy, with a 9.26% increase after just one epoch of training.
• Score: 3.6302496232346235
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Web navigation agents are capable of addressing various types of tasks on different websites. Current baselines on web navigation are either unimodal or lack strong reasoning abilities given multimodal inputs. Focusing on the WebShop benchmark, a real-world website simulation, we explore the alignment of text and images, as well as multimodal reasoning and planning abilities, to enhance the performance of web navigation agents. We propose three innovative multimodal enhancements: Multimodal Enhanced LLM for Online Navigation (MELLON), VQAgent, and Multimodal Ranker. MELLON demonstrates a significant improvement in task completion accuracy, with a 9.26% increase after just one epoch of training. Our findings suggest the necessity of further exploration into multimodal approaches, with a focus on more extensive training and alignment strategies to enhance the effectiveness of web navigation agents.

Related papers

• Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents [16.161877699225986]
  We develop a scalable recipe to synthesize the largest and most diverse trajectory-level dataset to date.<n>This dataset contains over 94K successful multimodal web trajectories, spanning 49K unique URLs, 720K screenshots, and 33M web elements.<n>We demonstrate strong performance on both offline and online web agent benchmarks such as Mind2Web-Live, Multimodal-Mind2Web, and MiniWob++.
  arXiv  Detail & Related papers  (2025-02-17T02:13:48Z)
• AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations [18.820883566002543]
  State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks. Current strategies for building web agents rely on (i) the generalizability of underlying MLLMs and their steerability via prompting, and (ii) large-scale fine-tuning of MLLMs on web-related tasks. We introduce the AdaptAgent framework that enables both proprietary and open-weights multimodal web agents to adapt to new websites and domains using few human demonstrations.
  arXiv  Detail & Related papers  (2024-11-20T16:54:15Z)
• 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)
• 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)
• 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.<n>Our data includes 1,050 human-written tasks covering various domains such as shopping and travel.<n>We propose a novel protocol for evaluating an agent's progress in completing multihop tasks.
  arXiv  Detail & Related papers  (2024-04-15T17:59:50Z)
• On the Multi-turn Instruction Following for Conversational Web Agents [83.51251174629084]
  We introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment. We propose a novel framework, named self-reflective memory-augmented planning (Self-MAP), which employs memory utilization and self-reflection techniques.
  arXiv  Detail & Related papers  (2024-02-23T02:18:12Z)
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning [49.92517970237088]
  We tackle the problem of training a robot to understand multimodal prompts. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. We introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts.
  arXiv  Detail & Related papers  (2023-10-14T22:24:58Z)
• 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)
• Towards Versatile Embodied Navigation [120.73460380993305]
  Vienna is a versatile embodied navigation agent that simultaneously learns to perform the four navigation tasks with one model. We empirically demonstrate that, compared with learning each visual navigation task individually, our agent achieves comparable or even better performance with reduced complexity.
  arXiv  Detail & Related papers  (2022-10-30T11:53:49Z)
• Adversarial Environment Generation for Learning to Navigate the Web [107.99759923626242]
  One of the bottlenecks of training web navigation agents is providing a learnable curriculum of training environments. We propose using Adversarial Environment Generation (AEG) to generate challenging web environments in which to train reinforcement learning (RL) agents. We show that the navigator agent trained with our proposed Flexible b-PAIRED technique significantly outperforms competitive automatic curriculum generation baselines.
  arXiv  Detail & Related papers  (2021-03-02T19:19:30Z)

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.