Summary

This system automates academic literature review by monitoring ArXiv and 20+ top journals. It uses LLMs to intelligently filter, score, and deeply analyze papers, track keyword trends, and generate comprehensive reports. Designed for researchers and power users, it significantly reduces manual effort in staying abreast of scientific advancements.

How It Works

The core architecture employs a dual LLM strategy: a cost-effective LLM (CHEAP_LLM) scores papers based on configurable keyword weights and dynamic thresholds, while a high-performance LLM (SMART_LLM) performs in-depth PDF analysis, extracting key dimensions like methodology, innovation, and conclusions. It automates PDF keyword extraction, AI-driven semantic normalization of keywords, and stores data in SQLite for trend visualization.

Quick Start & Requirements

Installation involves cloning the repository and installing Python dependencies (pip install -r requirements.txt). Configuration is guided via an interactive CLI wizard or a Streamlit web UI, requiring LLM API keys, research keywords, and notification credentials. Deployment options include local scripts with Cron, Docker containers, or serverless GitHub Actions. Python 3.10+ is required.

Highlighted Details

• Dual LLM approach for efficient filtering and deep analysis.
• Automated seven-dimensional PDF content extraction.
• AI-driven keyword semantic normalization and trend tracking.
• Flexible deployment across local, Docker, and CI/CD environments.
• Interactive configuration wizard and visual Streamlit management panel.
• Comprehensive Markdown/HTML reporting with multi-channel notifications.
• Production-grade features: automatic retries, concurrency, file locking.

Maintenance & Community

The project shows active development with recent major updates (v3.0 released March 2026). While specific community channels are not listed, the detailed README and changelog suggest a well-maintained project.

Licensing & Compatibility

Licensed under AGPL-3.0. This strong copyleft license permits commercial use but mandates that any modifications or derivative works, especially network services, must also be open-sourced under AGPL-3.0.

Limitations & Caveats

The system relies on external LLM APIs, incurring costs and requiring API key management. The AGPL-3.0 license's strong copyleft may pose compatibility challenges for closed-source commercial integrations, particularly for network services. PDF parsing quality can vary, with fallbacks to local methods.