English | 中文
Author: Tiger, member from HKUST Dial
Last update: May 09, 2026
This workflow serves for tracking daily updates in arXiv.org. Paper info will be preprocessed and concluded by a series of modules. Finally, it will post to a group chat in Feishu for reading. The target audience is for education and research community.
💰 Cost: less than 0.05 CNY per workflow execution.
- 📚 Automatically fetch latest arXiv papers
- 🤖 DeepSeek-V4-powered paper summarization and filtering
- 📱 Auto-send to Feishu group chat
- ⏰ Dify Cloud internal scheduler trigger
- 🛠️ Local debugging script support
Before getting started, please ensure you have prepared the following accounts and services:
- Dify account - Free registration for building AI workflows
- Backbone LLM API - Use the latest DeepSeek-V4 as the workflow backbone LLM
- Jina API key - For web content extraction, new users get 1M free credits
- Feishu Group Bot Webhook - For message pushing
-
Open Dify Console
-
Import Workflow
- Create a new workflow by importing this DSL file
- This DSL file contains the complete logic for paper fetching, processing, and pushing
-
Configure Environment Variables
-
Configure Scheduler Trigger
- Add a scheduler trigger in Dify Workflow Studio
- Configure the trigger time according to your desired push frequency
Dify Cloud now supports scheduler triggers directly inside Workflow Studio. Use the internal scheduler trigger for automated execution.
-
Open Workflow Studio:
- Select your imported ArxivFlow workflow in Dify
-
Add Scheduler Trigger:
- Configure the schedule in the workflow trigger settings
-
Publish Workflow:
- Save and publish the workflow so Dify Cloud runs it on schedule
The previous GitHub Actions scheduler has been deprecated and archived under deprecated/github-actions-scheduler.
The scheduler will automatically:
- ✅ Execute your Dify workflow daily
- 📊 Log execution results and status
- ❌ Report execution status in Dify
- 🔄 Support workflow-level schedule configuration
FEISHU_DEV/FEISHU_PROD: Feishu Group Bot Webhook for testing/production environmentsJINA: API key for crawling arXiv search resultsKEYWORDS: Keywords for arXiv paper search, comma-separated- The number of KEYWORDS and sending frequency should match the Dify scheduler trigger configuration
- Example: If sending 4 pushes daily, KEYWORDS needs 4 keywords, and timing rules need 4 time points
PAPER_NUM_MAX: Maximum number of papers per message (limited by Feishu message length)
The /scripts folder contains scripts for local debugging and testing, simulating the processes used in Dify Workflow:
jina_extract.py: Simulates Jina API calls and paper information extraction logicsample.text: Sample data returned by Jina API for local testingextracted_papers.json: Example of structured paper data after extraction, serves as input for downstream LLM analysis in workflow
These scripts help you test and debug paper extraction logic without consuming API credits.
cd scripts
python jina_extract.py- Dify Official Guidance: Link
- Feishu - How to use Bot in Group Chat: Link (Chinese)
- AWS Workshop: Lab3-使用Dify构建AI Workflow: Link (Chinese)
- arXiv Category: Link
- Dify Schedule Project: Link - Inspiration for the deprecated GitHub Actions scheduler implementation
MIT License - See LICENSE file


