{"slug": "visualskill-multimodal-skills-for-computer-use-agents", "title": "VISUALSKILL: Multimodal Skills for Computer-Use Agents", "summary": "Researchers introduced VISUALSKILL, a multimodal skill library for computer-use agents that combines text and visual figures to improve performance on long-horizon tasks. In tests, the system achieved a 0.456 average score on CUA benchmarks, outperforming text-only skills by 8.3 points and no-skill baselines by 15.3 points. The findings demonstrate that retaining visual artifacts helps agents identify UI elements and verify workflow states.", "body_md": "arXiv:2606.18448v1 Announce Type: new\nAbstract: Computer-use agents (CUAs) approach human-level performance on standardised benchmarks but still struggle on long-horizon tasks and unseen software. Existing skill libraries address this with reusable skills, but represent the skill artifact as text only, despite the visual nature of GUI interaction. We propose VISUALSKILL: a hierarchical multimodal skill, tailored to each target application and organised as a central index over per-topic files, which the agent consumes through a load_topic MCP tool that fetches the relevant topic's text and figures on demand. We construct each skill with a two-stage pipeline that combines authored documentation with live-application UI exploration. On two CUA benchmarks, CUA-World and OSExpert-Eval, a Claude Code CLI agent backed by Claude Opus 4.6 reaches an average score of 0.456 with VISUALSKILL, a +15.3 point absolute lift over the no-skill baseline (0.303). Against a matched text-only skill that is generated from the same source content and differs from VISUALSKILL only in modality, VISUALSKILL yields a further +8.3 point absolute gain over the matched text-only skill (0.373 vs. 0.456), providing direct evidence that retaining visual figures in the skill artifact, rather than verbalizing them away, helps the agent both identify UI elements and verify workflow state after each action. Our code is available at https://github.com/XMHZZ2018/VisualSkills.", "url": "https://wpnews.pro/news/visualskill-multimodal-skills-for-computer-use-agents", "canonical_source": "https://arxiv.org/abs/2606.18448", "published_at": "2026-06-18 04:00:00+00:00", "updated_at": "2026-06-18 04:24:44.550013+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-agents", "machine-learning"], "entities": ["Claude Code CLI", "Claude Opus 4.6", "CUA-World", "OSExpert-Eval"], "alternates": {"html": "https://wpnews.pro/news/visualskill-multimodal-skills-for-computer-use-agents", "markdown": "https://wpnews.pro/news/visualskill-multimodal-skills-for-computer-use-agents.md", "text": "https://wpnews.pro/news/visualskill-multimodal-skills-for-computer-use-agents.txt", "jsonld": "https://wpnews.pro/news/visualskill-multimodal-skills-for-computer-use-agents.jsonld"}}