Hugging Face's logo

Gnonymous
/
Web-CogReasoner

Image-Text-to-Text
Safetensors
English
Chinese
qwen2_5_vl
web
agent
model
conversational
Model card Files
xet
 Community
1
Gnonymous commited on
Commit
2a829aa
·
verified ·
1 Parent(s): 7ff6b79

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -17,6 +17,6 @@ tags:
17
 
18
  This model was the Web-CogReasoner model mentioned in the paper [Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents](https://huggingface.co/papers/2508.01858).
19
 
20
- Web-CogReasoner is trained using our [Web-CogDataset](https://huggingface.co/datasets/Gnonymous/Web-CogDataset) and evaluate on our [Web-CogBench](https://huggingface.co/datasets/Gnonymous/Web-CogBench).
21
 
22
  It achieves 84.4 @ Web-CogBench, 86.3 @ VisualWebBench, 30.2% @ WebVoyager, 17.0% and 10.1% @ Online Multimodal-Mind2Web Cross-Tasks and Cross-Webs
 
17
 
18
  This model was the Web-CogReasoner model mentioned in the paper [Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents](https://huggingface.co/papers/2508.01858).
19
 
20
+ Web-CogReasoner is trained using our [Web-CogDataset](https://huggingface.co/datasets/Gnonymous/Web-CogDataset) and evaluated on our [Web-CogBench](https://huggingface.co/datasets/Gnonymous/Web-CogBench).
21
 
22
  It achieves 84.4 @ Web-CogBench, 86.3 @ VisualWebBench, 30.2% @ WebVoyager, 17.0% and 10.1% @ Online Multimodal-Mind2Web Cross-Tasks and Cross-Webs