update readme

.github/workflows/main.yml

@@ -32,37 +32,18 @@ jobs:
           
       - name: Generate keyword grouping and update temp_readme.md
         run: |
-          # Define fixed priority keywords
-          PRIORITY_KEYWORDS="model framework dataset benchmark safety survey"
-
-          # Initialize the output for grouped papers
-          GROUPED_KEYWORDS=""
-          # Generate priority keyword sections first
-          for key in $PRIORITY_KEYWORDS; do
-            FILE="paper_by_key/paper_${key}.md"
-            if [ -f "$FILE" ]; then
-              GROUPED_KEYWORDS+="[${key^}](paper_by_key/paper_${key}.md) | "
-            fi
-          done
-          
-          # Generate sections for all other keywords dynamically
-          for file in paper_by_key/*.md; do
-            KEYWORD=$(basename "$file" .md | sed 's/^paper_//' | tr '_' ' ')
-            # Skip priority keywords already processed
-            if [[ "$PRIORITY_KEYWORDS" != *"${KEYWORD}"* ]]; then
-              GROUPED_KEYWORDS+="[${KEYWORD^}](paper_by_key/$(basename "$file" | sed 's/ /%20/g')) | "
-            fi
-          done
-
-          # Trim the trailing '| ' at the end
-          GROUPED_KEYWORDS=${GROUPED_KEYWORDS% | }
+          # Read the pre-generated keyword grouping Markdown
+          if [ -f update_template_or_data/keyword_grouping.md ]; then
+            GROUPED_KEYWORDS=$(cat update_template_or_data/keyword_grouping.md)
+          else
+            GROUPED_KEYWORDS="No keywords available"
+          fi
 
-          # Insert the content into the template
+          # Insert the keyword grouping content into the template
           sed -i '/{{insert_keyword_groups_here}}/{
             r /dev/stdin
             d
           }' update_template_or_data/update_readme_template.md <<< "$GROUPED_KEYWORDS"
-          
 
 #      - name: Generate author grouping and update temp_readme.md
 #        run: |

update_template_or_data/update_paper_list.md

@@ -178,6 +178,15 @@
     - 🔑 Key: [framework], [Auto-Intent]
     - 📖 TLDR: The paper presents Auto-Intent, a method to adapt pre-trained large language models for web navigation tasks without direct fine-tuning. It discovers underlying intents from domain demonstrations and trains an intent predictor to enhance decision-making. Auto-Intent improves the performance of GPT-3.5, GPT-4, and Llama-3.1 agents on benchmarks like Mind2Web and WebArena.
 
+- [OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization](https://doi.org/10.48550/arXiv.2410.19609)
+    - Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu
+    - 🏛️ Institutions: Zhejiang University, Tencent AI Lab, Westlake University
+    - 📅 Date: October 25, 2024
+    - 📑 Publisher: arXiv
+    - 💻 Env: [Web]
+    - 🔑 Key: [framework], [learning], [imitation learning], [exploration], [AI feedback]
+    - 📖 TLDR: The paper presents **OpenWebVoyager**, an open-source framework for training web agents that explore real-world online environments autonomously. The framework employs a cycle of exploration, feedback, and optimization, enhancing agent capabilities through multimodal perception and iterative learning. Initial skills are acquired through imitation learning, followed by real-world exploration, where the agent’s performance is evaluated and refined through feedback loops.
+
 - [AutoGLM: Autonomous Foundation Agents for GUIs](https://xiao9905.github.io/AutoGLM/)
     - Xiao Liu, Bo Qin, Dongzhu Liang, Guang Dong, Hanyu Lai, Hanchen Zhang, Hanlin Zhao, Iat Long Iong, Jiadai Sun, Jiaqi Wang, Junjie Gao, Junjun Shan, Kangning Liu, Shudan Zhang, Shuntian Yao, Siyi Cheng, Wentao Yao, Wenyi Zhao, Xinghan Liu, Xinyi Liu, Xinying Chen, Xinyue Yang, Yang Yang, Yifan Xu, Yu Yang, Yujia Wang, Yulin Xu, Zehan Qi, Yuxiao Dong, Jie Tang
     - 🏛️ Institutions: Zhipu AI, Tsinghua University
@@ -196,15 +205,6 @@
     - 🔑 Key: [dataset], [framework], [synthetic data]
     - 📖 TLDR: The *EDGE* framework proposes an innovative approach to improve GUI understanding and interaction capabilities in vision-language models through large-scale, multi-granularity synthetic data generation. By leveraging webpage data, EDGE minimizes the need for manual annotations and enhances the adaptability of models across desktop and mobile GUI environments. Evaluations show its effectiveness in diverse GUI-related tasks, contributing significantly to autonomous agent development in GUI navigation and interaction.
 
-- [OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization](https://doi.org/10.48550/arXiv.2410.19609)
-    - Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu
-    - 🏛️ Institutions: Zhejiang University, Tencent AI Lab, Westlake University
-    - 📅 Date: October 25, 2024
-    - 📑 Publisher: arXiv
-    - 💻 Env: [Web]
-    - 🔑 Key: [framework], [learning], [imitation learning], [exploration], [AI feedback]
-    - 📖 TLDR: The paper presents **OpenWebVoyager**, an open-source framework for training web agents that explore real-world online environments autonomously. The framework employs a cycle of exploration, feedback, and optimization, enhancing agent capabilities through multimodal perception and iterative learning. Initial skills are acquired through imitation learning, followed by real-world exploration, where the agent’s performance is evaluated and refined through feedback loops.
-
 - [VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks](https://doi.org/10.48550/arXiv.2410.19100)
     - Lawrence Jang, Yinheng Li, Charles Ding, Justin Lin, Paul Pu Liang, Dan Zhao, Rogerio Bonatti, Kazuhito Koishida
     - 🏛️ Institutions: CMU, MIT, NYU, Microsoft

update_template_or_data/utils/scripts/sort_by_date.py

@@ -339,6 +339,55 @@ def remove_square_brackets(s):
     except Exception as e:
         logging.error(f"Error generating keyword-based Markdown files: {str(e)}", exc_info=True)
 
+    # Generate sorted keyword grouping markdown
+    # Generate sorted keyword grouping markdown with predefined keywords prioritized
+    try:
+        # Extract and count all keywords
+        all_keywords = []
+        for _, row in papers_df.iterrows():
+            keywords = row['Keywords']
+            filtered_keywords = [remove_square_brackets(kw.strip()) for kw in keywords.split(",") if kw.strip()]
+            all_keywords.extend(filtered_keywords)
+        keyword_counter = Counter(all_keywords)
+
+        # Define predefined keywords
+        predefined_keywords = ["Model", "Framework", "Benchmark", "Dataset",  "Safety", "Survey"]
+
+        # Get counts for predefined keywords
+        predefined_keyword_counts = [(kw, keyword_counter[kw]) for kw in predefined_keywords if kw in keyword_counter]
+
+        # Find remaining top keywords excluding predefined ones
+        remaining_keywords = [
+            (kw, count) for kw, count in keyword_counter.most_common()
+            if kw not in predefined_keywords
+        ]
+
+        # Limit to top (20 - predefined_keywords) remaining keywords
+        top_num_keywords = 20 - len(predefined_keywords)
+        top_remaining_keywords = remaining_keywords[:top_num_keywords]
+
+        # Combine predefined and top remaining keywords
+        combined_keywords = predefined_keyword_counts + top_remaining_keywords
+
+        # Sort combined keywords by count in descending order (within their respective groups)
+        combined_keywords.sort(
+            key=lambda x: (-x[1], predefined_keywords.index(x[0]) if x[0] in predefined_keywords else float('inf')))
+
+        # Generate Markdown content for keywords
+        grouped_keywords_markdown = []
+        for keyword, count in combined_keywords:
+            keyword_filename = f"paper_{keyword.replace(' ', '_')}.md"
+            keyword_link = f"paper_by_key/{keyword_filename.replace(' ', '%20')}"
+            grouped_keywords_markdown.append(f"[{keyword} ({count})]({keyword_link}) | ")
+
+        # Join the Markdown content into a single string
+        grouped_keywords_markdown_str = "".join(grouped_keywords_markdown).rstrip(" | ")
+
+        # Save the sorted Markdown to a temporary file for the workflow
+        write_file("update_template_or_data/keyword_grouping.md", grouped_keywords_markdown_str)
+    except Exception as e:
+        logging.error(f"Error generating sorted keyword grouping Markdown: {str(e)}", exc_info=True)
+
     # Generate keyword word cloud
     try: