SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsserper-scholar

serper-scholar

Coding & development

View repository

Updated 10-15 21:40

About this skill

Google Scholar Search Tool

An academic literature search tool based on the Google Scholar API, providing professional search capabilities for academic papers, research reports, and technical literature.

When to Activate

Automatically activated when the user mentions the following:

Academic search keywords

  • "paper", "academic", "literature", "research"
  • "search papers", "find literature", "academic research"
  • "Google Scholar", "Scholar"

Specific scenarios

  • Need to find academic papers or research reports
  • Need to understand academic progress in a certain field
  • Need to find works by a specific author
  • Need to obtain citation information and publication venues
  • Need to research the theoretical basis in the technical field

Example questions

  • "Help me search for papers about machine learning"
  • "Find the applications of deep learning in NLP"
  • "Research academic papers on the Transformer architecture"
  • "Find some literature on large model training methods"
  • "Search for related papers on Attention mechanism"

Tools

serper_scholar

Purpose: Execute academic literature search and return detailed paper information

Parameters:

  • query (required, string): search keywords
  • num (optional, number): number of results to return, default 10, maximum 20
  • gl (optional, string): country code, default cn
  • Recommended values: cn (China), us (United States), uk (United Kingdom)
  • hl (optional, string): language code, default zh-CN
  • Recommended values: zh-CN (Simplified Chinese), en (English)

Return fields:

  • title: paper title
  • url: paper link
  • snippet: abstract
  • type: document type (PDF, HTML, etc.)
  • year: publication year
  • authors: author list
  • publication: publication venue/conference
  • citationCount: citation count

Best Practices

1. Search techniques

Use professional terminology and technical keywords:

Example:

  • ✅ "Attention mechanism neural machine translation"
  • ✅ "Transformer large language models"
  • ✅ "Reinforcement learning robotics"
  • ❌ "machine learning" (too broad, too many results)

2. Add field restrictions

Clarify the research field and method:

Example:

  • ✅ "BERT semantic analysis NLP"
  • ✅ "CNN image classification computer vision"
  • ✅ "GPT text generation natural language"
  • ✅ "Q-learning reinforcement learning agent"

3. Time range search

Focus on the latest research progress:

Example:

  • ✅ "Large language models 2024 2025"
  • ✅ "Transformer architecture recent advances"
  • ✅ "Diffusion models 2023 2024"

4. Author and institution search

Find the work of a specific researcher or institution:

Example:

  • ✅ "Geoffrey Hinton deep learning"
  • ✅ "Yann LeCun CNN papers"
  • ✅ "Andrew Ng machine learning"
  • ✅ "OpenAI research papers"

5. Paper type filtering

Focus on a specific type of literature:

Example:

  • ✅ "Survey deep learning"
  • ✅ "Review transformer models"
  • ✅ "Tutorial reinforcement learning"
  • ✅ "Benchmark NLP models"

6. Choosing the number of results

Adjust according to needs:

  • Quick browse: num=5(core literature)
  • Comprehensive understanding: num=10(mainstream research)
  • In-depth investigation: num=20(comprehensive coverage)

7. Citation information analysis

Focus on highly cited papers and classic literature:

Key points:

  • Citation count:citationCount Papers with high counts are usually classics in the field
  • Publication year: newer papers represent the latest progress
  • Publication venue: Top conferences (NeurIPS, ICML, ACL) are high quality

Example Scenarios

Scenario 1: Technical research

User question: "Research papers on the Transformer architecture"

AI action:

// 搜索核心论文
serper_scholar({
  query: "Transformer architecture attention is all you need",
  num: 5
})

// 搜索后续研究
serper_scholar({
  query: "BERT transformer NLP 2018 2019",
  num: 8
})

Example reply:

核心论文：

1. **Attention Is All You Need** (2017)
   - 作者：Vaswani et al.
   - 引用：100,000+
   - 📄 [PDF]
   
后续研究：

2. **BERT: Pre-training of Deep Bidirectional Transformers** (2019)
   - 作者：Devlin et al.
   - 引用：80,000+
   - 发表：NAACL 2019
   
3. **Improving Language Understanding with Generative Pre-Training** (2018)
   - 作者：Radford et al. (OpenAI)
   - 引用：50,000+

Scenario 2: Field survey

User question: "Find some survey papers on reinforcement learning"

AI action:

serper_scholar({
  query: "Survey review reinforcement learning",
  num: 8
})

Example reply:

强化学习综述论文：

1. **Reinforcement Learning: A Survey** (2021)
   - 引用：5,000+
   - 类型：综述
   
2. **Deep Reinforcement Learning: An Overview** (2020)
   - 引用：8,000+
   - 类型：综述
   
3. **Recent Advances in Deep Reinforcement Learning** (2022)
   - 引用：2,000+
   - 类型：综述

Scenario 3: Author research

User question: "Find Geoffrey Hinton's deep learning papers"

AI action:

serper_scholar({
  query: "Geoffrey Hinton deep learning backpropagation",
  num: 10
})

Example reply:

Geoffrey Hinton 的经典论文：

1. **Deep Learning** (2015)
   - 合作：LeCun, Bengio
   - 发表：Nature
   - 引用：50,000+
   
2. **Backpropagation Applied to Handwritten Zip Code Recognition** (1989)
   - 引用：10,000+
   
3. **Reducing the Dimensionality of Data with Neural Networks** (2006)
   - 引用：30,000+

Scenario 4: Latest progress

User question: "What new progress has been made in large models from 2024-2025"

AI action:

serper_scholar({
  query: "Large language models 2024 2025 advances",
  num: 10
})

Example reply:

2024-2025 大模型研究进展：

1. **Scaling Laws for Neural Language Models** (2024)
   - 持续探索模型规模与性能关系
   
2. **Instruction Tuning for Large Language Models** (2024)
   - 指令微调方法改进
   
3. **Chain-of-Thought Prompting** (2024)
   - 推理链提示技术

Scenario 5: Interdisciplinary search

User question: "Search for papers on the application of machine learning in medical diagnosis"

AI action:

serper_scholar({
  query: "Machine learning medical diagnosis healthcare",
  num: 8
})

Example reply:

医疗诊断中的机器学习：

1. **Deep Learning for Medical Image Analysis** (2021)
   - 引用：8,000+
   - 应用：影像诊断
   
2. **Machine Learning in Clinical Diagnosis** (2022)
   - 引用：3,000+
   - 应用：辅助诊断
   
3. **AI in Healthcare: A Survey** (2023)
   - 引用：2,000+
   - 类型：综述

Limitations

  • Search result source: Google Scholar, may be affected by region
  • Access restrictions: Some papers require a subscription or paid access
  • Number of results: Up to 20
  • Update delay: The latest papers may take some time to be indexed
  • Language preference: There are far more papers in English than in Chinese

Configuration

Environment variable configuration

Edit ~/.openclaw/gateway.env：

SERPER_API_KEY=your-api-key-here

Get API Key

Visit https://serper.dev/ to register and get an API Key.

Free quota: 2,500 calls per month (shared by Web and Scholar).

Related Tools

  • serper_search： General web search
  • web_fetch： Get the detailed content of a single webpage

Tips

  • Mixed use: First use serper_search to understand concepts, then use serper_scholar for in-depth research
  • Citation priority: Prioritize reading highly cited papers (usually classics in the field)
  • Pay attention to the year: Balance classic literature and the latest research
  • Track authors: After finding an important author, search for all their works
  • PDF access: Try to access the paper page and look for a free version

Version History

  • v1.0 (2026-02-06): Initial version, basic academic search functionality
    • Support for Google Scholar API
    • Provide detailed paper information (authors, year, citations, etc.)
    • Integration with the OpenClaw Skill system

💡 Tip: When doing academic searches, try to use English keywords; the quantity and quality of English papers are usually higher.