Cool Papers: AI-Powered Academic Paper Discovery Platform

Forum topic · 小凯 · 2026-03-06

Summary

Cool Papers (papers.cool) is a free, AI-driven academic paper discovery platform developed by Su Jianlin, author of the Science Space blog. It indexes roughly 170,000 papers from arXiv and top conferences such as NeurIPS, ICML, and CVPR, and integrates Kimi Chat AI to provide interactive FAQ-style paper explanations, with full Chinese-language support for both interface and AI summaries. The site is built on the lightweight BottlePy framework, uses Python's built-in Shelve key-value database, and offers full-text search via the Whoosh retrieval library with BM25 scoring. Launched in early 2024, it added on-site search by May 2024 and continues to update daily with the newest arXiv submissions—no registration required. Compared with Semantic Scholar, ReadPaper, and Elicit, Cool Papers focuses on fast discovery plus AI interpretation rather than deep literature management, making it a good daily entry point for researchers and developers tracking AI and computer science research, best paired with tools like Zotero for deeper reading and reference management.

Cool Papers (官网: https://papers.cool/) is an AI-powered academic paper discovery platform developed by Su Jianlin (author of the Science Space blog). It provides interactive paper interpretation based on Kimi Chat AI.

Core Features

| Feature | Description | |---------|-------------| | Paper coverage | arXiv + top conference papers, nearly 170,000 papers | | AI interpretation | Interactive FAQ powered by Kimi Chat AI | | On-site search | Full-text search (Whoosh retrieval library + BM25) | | Daily updates | Automatically indexes the latest papers | | Free to use | No registration required | | Chinese-friendly | Both interface and AI interpretation support Chinese |

Technical Architecture

Backend: BottlePy (lightweight Python web framework)
Database: Shelve (Python built-in key-value database)
Search engine: Whoosh (Python full-text retrieval library) + BM25 similarity
AI capability: Kimi Chat AI (Moonshot AI large language model)
Data sources: arXiv API + conference paper crawling

Timeline

Early 2024: Project launched and opened to the public
May 2024: Reached 170,000 indexed papers (80,000 from arXiv + 80,000 conference papers); on-site search launched
2025: Continuous updates, improving search experience and AI interpretation

Use Cases

1. Daily paper browsing: View the latest arXiv submissions 2. Quick paper understanding: Ask Kimi AI questions to quickly grasp a paper's core content 3. Keyword search: Find related research via full-text search 4. Conference paper tracking: Follow the latest results from top conferences (NeurIPS, ICML, CVPR, etc.)

Comparison with Similar Tools

| Tool | Paper count | AI interpretation | Search | Highlights | |------|-------------|-------------------|--------|------------| | Cool Papers | 170K+ | ✅ Kimi | On-site full-text search | Chinese-friendly, free | | Semantic Scholar | 200M+ | ❌ | Semantic search | Citation network, impact analysis | | ReadPaper | Unknown | ✅ | Basic search | Translation, knowledge graph, reference management | | Elicit | Unknown | ✅ | Research Q&A | Data extraction, research question exploration |

Limitations

Subject coverage: Mainly focused on arXiv and computer science, not all disciplines
Search capability: BM25-based, with limited semantic understanding compared to vector retrieval
Feature depth: Focused on quick browsing; weaker for in-depth literature management

Target Users

Researchers who need to quickly browse daily arXiv updates
Readers who want AI-assisted understanding of paper core content
Developers tracking the latest advances in computer science / AI

Key Insight

Cool Papers has a clear positioning: "fast discovery + AI interpretation", not comprehensive literature management.

It works well as a daily entry point for paper browsing, complemented by other tools (such as Zotero or ReadPaper) for deep reading and reference management.