AI Paper Atlas

Research map / Video / Video-language understanding

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

Rui Xie, Zhi Gao, Chenrui Shi, Zirui Shang, Lu Chen, Qing Li

ECCV 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add planning knowledge from tutorial videos (ablation)Seed-1.8 · OSWorld (361 tasks)average score (%): 37.14 -> 43.93Improved
add grounding knowledge on top of planning (ablation)Seed-1.8 · OSWorld (361 tasks)average score (%): 43.93 -> 44.62Improved
add planning knowledge (ablation)Qwen3-VL-8B · OSWorld (361 tasks)average score (%): 33.90 -> 38.93Improved
add grounding on top of planning (ablation)Qwen3-VL-8B · OSWorld (361 tasks)average score (%): 38.93 -> 39.73Improved
add grounding knowledge only (no planning) (ablation)Qwen3-VL-8B · OSWorld (361 tasks)average score (%): 33.90 -> 34.31No clear effect
add GUIDE to multi-agent systemAgentS3 · OSWorld (361 tasks)average score (%): 50.18 -> 54.65Improved
add GUIDE knowledgeAgents3+GPT-5.2 · WindowsAgentArena (154 tasks)average score (%): 49.00 -> 59.21Improved
add GUIDE knowledgeQwen3-VL-32B · WindowsAgentArena (154 tasks)average score (%): 31.70 -> 44.16Improved
inject raw tutorial trajectories as ICL instead of structured knowledge (ablation)Qwen3-VL-8B-thinking · OSWorld (361 tasks)average score (%): 33.90 -> 31.96Hurt
add subtitle-derived planning knowledge only (ablation)Qwen3-VL-8B-thinking · OSWorld balanced subset (120 tasks)average score (%): 40.00 -> 42.32Improved
add visual pairwise annotation (without OmniParser) (ablation)Qwen3-VL-8B-thinking · OSWorld balanced subset (120 tasks)average score (%): 42.32 -> 47.52Improved
add OmniParser UI element graph (ablation)Qwen3-VL-8B-thinking · OSWorld balanced subset (120 tasks)average score (%): 47.52 -> 49.11Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy