BAAI / Zhiyuan AI Research Papers Scraper

Extract AI research papers from BAAI (Beijing Academy of Artificial Intelligence, 智源研究院) at hub.baai.ac.cn, newest first. Every paper comes with the English abstract, the Chinese abstract and the structured editorial curator notes BAAI writes for it. The archive reaches back to December 2023, with hundreds of new papers every day.

What You Get

Each record includes:

Field	Description
paper_title_en	Paper title in English
arxiv_id	ArXiv paper ID (e.g. 2606.06624)
authors	Complete list of author names
publication_date	Release date (ISO 8601)
abstract_en	English abstract
abstract_zh	Full Chinese-language abstract
keywords_en	BAAI topic tags in English (e.g. RLHF, SFT)
keywords_zh	BAAI topic tags as shown on the Chinese site
github_repo	Code repository the authors link to (only for papers that link one, roughly one in ten)
pdf_url	Direct PDF download link (BAAI-hosted mirror; present on a minority of papers, mostly where BAAI hosts a mirror)
baai_curator_note	Structured editorial notes: [简介] abstract, [问题] problem addressed, [思路] key approach, [亮点] highlights, [相关] related work
baai_url	Canonical BAAI paper page URL
cited_by_count	BAAI hotness score
source	Always hub.baai.ac.cn

Why BAAI?

BAAI (智源研究院) is China's premier government-backed AI research institute, behind the WuDao foundation model series, the BGE embedding family, and the Aquila LLM. Its paper hub adds Chinese-language editorial summaries that are not available on arXiv.

Use cases:

• Track Chinese AI research output for competitive intelligence
• Build a joinable dataset with an ArXiv scraper (shared arxiv_id key)
• Monitor BAAI's curated AI research highlights in Chinese for sino-watchers
• Feed into downstream LLM pipelines with bilingual abstracts and summaries

Input

Parameter	Required	Default	Description
maxItems	Yes	5	Number of papers to return (at least 1), newest first, going back in time

Sample Output

{
  "paper_title_en": "Rethinking the Trust Region in LLM Reinforcement Learning",
  "arxiv_id": "2602.04879",
  "authors": ["Penghui Qi", "Xiangxin Zhou", "Zichen Liu"],
  "publication_date": "2026-02-04",
  "abstract_en": "Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models...",
  "abstract_zh": "强化学习（RL）已成为大语言模型（LLM）微调的基石...",
  "keywords_en": ["RLHF", "RL", "SFT"],
  "keywords_zh": ["RLHF", "RL", "SFT"],
  "github_repo": null,
  "pdf_url": "https://simg.baai.ac.cn/paperfile/572bbeac-4516-4c34-8bc2-15ee9ef5bbb7.pdf",
  "baai_curator_note": "[简介] 强化学习（RL）已成为大语言模型...\n\n[问题] 如何设计更合理的信任域约束...\n\n[思路] 提出散度近端策略优化（DPPO）...",
  "baai_url": "https://hub.baai.ac.cn/paper/572bbeac-4516-4c34-8bc2-15ee9ef5bbb7",
  "cited_by_count": 120,
  "source": "hub.baai.ac.cn"
}

Notes

• China-hosted: The site is hosted in China, so large runs go at a measured pace and individual requests may occasionally run long.
• No authentication required: The papers are publicly accessible without login.