Upload README.md

README.md

@@ -1,6 +1,6 @@
 # InternAgent: When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification
 
-[[ Paper 📓 ]](https://arxiv.org/abs/2505.16938) [[ Website 🏠 ]](https://alpha-innovator.github.io/InternAgent-project-page/) [[ Intern·Agent Examples 🤗 ]](https://huggingface.co/U4R/InternAgent)
+[[ Paper 📓 ]](https://arxiv.org/abs/2505.16938) [[ Website 🏠 ]](https://alpha-innovator.github.io/InternAgent-project-page/) [[ InternAgent Examples 🤗 ]](https://huggingface.co/U4R/InternAgent)
 
 <i>
 From One Idea to Autonomous Experimentation
@@ -8,19 +8,20 @@ From One Idea to Autonomous Experimentation
 </div>
 
 # 🔥 News
-  - <p style='text-align:justify'><i>2025.07.17</i>: &nbsp; 🔥 InternAgent has been open-sourced.
+  - <p style='text-align:justify'><i>2025.07.17</i>: &nbsp; 🔥 InternAgent has been partially open-sourced.
   - <p style='text-align:justify'><i>2025.07.10</i>: &nbsp; NovelSeek has be renamed to <b>InternAgent</b>. This change embodies our hopeful vision for autonomous scientific research framework, and we hope it will empower all researchers to achieve great scientific discoveries.</p>
 
 ## 📖 Overview
 
-
-![InternAgent](/images/InternAgent_Fig1.png)
+<div align=center>
+<img src=https://github.com/Alpha-Innovator/InternAgent/blob/main/images/internagent_overall.png width=540 />
+</div>
 
 InternAgent can support **12** types of scientific research tasks ranging from the AI field to the science field, including reaction yield prediction, molecular dynamics, power flow estimation, time series forecasting, transcription prediction, enhancer activity prediction, sentiment classification, 2D image classification, 3D point classification, 2D semantic segmentation, 3D autonomous driving, large vision-language model fine-tuning.
 
 ## 🌟 Core Features
 
-![Framework](/images/InternAgent_pipeline.png)
+![Framework](https://github.com/Alpha-Innovator/InternAgent/blob/main/images/internagent_framework.png)
 
 InternAgent covers three main capabilities: (1) **Self-evolving idea generation with human-interactive feedback**, (2) **Idea-to-methodology construction**, and (3) **Evolutionary experimental planning and execution**. 
 
@@ -71,4 +72,3 @@ It is a unified, closed-loop multi-agent system designed to automate and acceler
 ## 🚀 Performance
 
 By leveraging multi-source knowledge injection, InternAgent intelligently generates and verifies research ideas across multiple domains. Our system has significantly improved research efficiency in Suzuki Yield Prediction, Enhancer Activity Prediction, Transcription Prediction for Perturbation Respons, and so on.
-