{
  "id": 18029,
  "url": "https://arxiv.org/abs/2608.09121v1",
  "title": "MELLON - Multimodal Enhanced LLM for Online Navigation",
  "summary": "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 Enha",
  "authors": "Ruiyu Li, Haoyang Cai, Zhitong Guo, Tong Hu",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T04:56:22.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18029",
  "original_url": "https://arxiv.org/abs/2608.09121v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}