init

add_paper_here.md

@@ -310,7 +310,7 @@
     - 📅 Date: January 1, 2024
     - 📑 Publisher: ICML 2024
     - 💻 Env: [Web]
-    - 🔑 Key: [framework], [dataset], [benchmark], [generalist web agent], [grounding], [seeact]
+    - 🔑 Key: [framework], [dataset], [benchmark], [grounding], [seeact], [multimodal-mind2web]
     - 📖 TLDR: This paper explores the capability of GPT-4V(ision), a multimodal model, as a web agent that can perform tasks across various websites by following natural language instructions. It introduces the **SEEACT** framework, enabling GPT-4V to navigate, interpret, and interact with elements on websites. Evaluated using the **Mind2Web** benchmark and an online test environment, the framework demonstrates high performance on complex web tasks by integrating grounding strategies like element attributes and image annotations to improve HTML element targeting. However, grounding remains challenging, presenting opportunities for further improvement.
 
 - [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://arxiv.org/abs/2401.10935)