WebArena provides a realistic multi-domain web environment and benchmark where state-of-the-art LLM agents achieve 14.41% end-to-end task success compared to 78.24% for humans.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
PRAC redirects Computer Use Agents' product selection by concentrating attention on an adversarial patch in the vision input, generalizing from white-box creation to fine-tuned models.
VisualWebArena benchmark demonstrates that state-of-the-art multimodal agents still exhibit significant limitations on visually grounded web tasks.
citing papers explorer
-
WebArena: A Realistic Web Environment for Building Autonomous Agents
WebArena provides a realistic multi-domain web environment and benchmark where state-of-the-art LLM agents achieve 14.41% end-to-end task success compared to 78.24% for humans.
-
Preference Redirection via Attention Concentration: An Attack on Computer Use Agents
PRAC redirects Computer Use Agents' product selection by concentrating attention on an adversarial patch in the vision input, generalizing from white-box creation to fine-tuned models.
-
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
VisualWebArena benchmark demonstrates that state-of-the-art multimodal agents still exhibit significant limitations on visually grounded web tasks.