Praison AI

arXiv Agent

arXiv research paper search and analysis tools for AI agents.

python
from praisonaiagents import Agent
from praisonai_tools import search_arxiv

agent = Agent(name="Researcher", tools=[search_arxiv])
agent.start("Find recent papers on retrieval-augmented generation")

The user asks for literature; the agent searches arXiv and returns relevant papers.

Diagram

Input

Agent

Tool

Output

Diagram
arXiv AgentAgentUserarXiv AgentAgentUserRequestProcess requestResultResponse

arXiv Tools

Use arXiv Tools to search and analyze research papers with AI agents.

  1. Install Dependencies

    First, install the required packages:

    bash
    pip install praisonaiagents praisonai-tools arxiv
  2. Import Components

    Import the necessary components:

    python
    from praisonaiagents import Agent, Task, AgentTeam
from praisonai_tools import search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category
  3. Create Agent

    Create a research agent:

    python
    research_agent = Agent(
    name="ResearchAgent",
    role="Scientific Literature Specialist",
    goal="Find and analyze relevant scientific papers.",
    backstory="Expert in academic research and literature review.",
    tools=[search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category],
    reflection=False
)
  4. Define Task

    Define the research task:

    python
    research_task = Task(
    description="Search for recent papers on 'quantum machine learning' and summarize key findings.",
    expected_output="List of relevant papers with summaries.",
    agent=research_agent,
    name="quantum_research"
)
  5. Run Agent

    Initialize and run the agent:

    python
    agents = AgentTeam(
    agents=[research_agent],
    tasks=[research_task],
    process="sequential"
)
agents.start()

Understanding arXiv Tools

What are arXiv Tools?

arXiv Tools provide scientific paper search capabilities for AI agents: – Paper search functionality – Author-based search – Category filtering – Abstract retrieval – PDF download options

Available Functions

python
from praisonai_tools import search_arxiv
from praisonai_tools import get_arxiv_paper
from praisonai_tools import get_papers_by_author
from praisonai_tools import get_papers_by_category

Function Details

search_arxiv(query: str, max_results: int = 10, sort_by: str = “relevance”, sort_order: str = “descending”, include_fields: Optional[List[str]] = None)

Search arXiv for papers:

  • Flexible query support
  • Customizable results
  • Multiple sorting options
  • Field selection
python
from praisonai_tools import search_arxiv

# Basic search
papers = search_arxiv("quantum computing")

# Advanced search
papers = search_arxiv(
    query="quantum computing",
    max_results=5,
    sort_by="submittedDate",
    sort_order="descending",
    include_fields=["title", "authors", "summary"]
)

get_arxiv_paper(paper_id: str, include_fields: Optional[List[str]] = None)

Get specific paper details:

  • Direct ID lookup
  • Full paper metadata
  • Customizable fields
  • PDF/Abstract links
python
from praisonai_tools import get_arxiv_paper

# Get paper by ID
paper = get_arxiv_paper("2401.00123")

# Get specific fields
paper = get_arxiv_paper(
    paper_id="2401.00123",
    include_fields=["title", "authors", "pdf_url"]
)

get_papers_by_author(author: str, max_results: int = 10)

Search papers by author:

  • Author-specific search
  • Publication timeline
  • Sort options
python
from praisonai_tools import get_papers_by_author

# Get author's papers
papers = get_papers_by_author("Yoshua Bengio", max_results=5)

get_papers_by_category(category: str, max_results: int = 10)

Search papers by category:

  • Category-specific search
  • Latest publications
  • Sort options
python
from praisonai_tools import get_papers_by_category

# Get papers in category
papers = get_papers_by_category("cs.AI", max_results=5)

Examples

Basic Research Agent

python
from praisonaiagents import Agent, Task, AgentTeam
from praisonai_tools import search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category

# Create research agent
research_agent = Agent(
    name="PaperSearcher",
    role="Scientific Literature Specialist",
    goal="Find relevant scientific papers on specified topics.",
    backstory="Expert in academic research and literature analysis.",
    tools=[search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category],
    reflection=False
)

# Define research task
research_task = Task(
    description="Search for papers on 'transformer models in NLP' from the last year.",
    expected_output="List of relevant papers with abstracts and key findings.",
    agent=research_agent,
    name="nlp_research"
)

# Run agent
agents = AgentTeam(
    agents=[research_agent],
    tasks=[research_task],
    process="sequential"
)
agents.start()

Advanced Research with Multiple Agents

python
from praisonaiagents import Agent, Task, AgentTeam
from praisonai_tools import search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category

# Create research agent
research_agent = Agent(
    name="Researcher",
    role="Literature Specialist",
    goal="Gather comprehensive scientific literature.",
    tools=[search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category],
    reflection=False
)

# Create analysis agent
analysis_agent = Agent(
    name="Analyzer",
    role="Research Analyst",
    goal="Analyze and synthesize research findings.",
    backstory="Expert in scientific literature analysis.",
    reflection=False
)

# Define tasks
research_task = Task(
    description="Search for papers on quantum computing applications in cryptography.",
    agent=research_agent,
    name="quantum_research"
)

analysis_task = Task(
    description="Analyze the papers and identify key trends and breakthroughs.",
    agent=analysis_agent,
    name="research_analysis"
)

# Run agents
agents = AgentTeam(
    agents=[research_agent, analysis_agent],
    tasks=[research_task, analysis_task],
    process="sequential"
)
agents.start()

Best Practices

Agent Configuration

Configure agents with clear research focus:

python
from praisonai_tools import search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category

Agent(
    name="Researcher",
    role="Literature Specialist",
    goal="Find relevant scientific papers",
    tools=[search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category]
)
Task Definition

Define specific research objectives:

python
Task(
    description="Find papers on 'deep learning in healthcare' from top authors",
    expected_output="Curated list of papers with impact analysis"
)

Common Patterns

Literature Review

python
from praisonaiagents import Agent, Task, AgentTeam
from praisonai_tools import search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category

# Literature search agent
searcher = Agent(
    name="Searcher",
    role="Literature Specialist",
    tools=[search_arxiv, get_arxiv_paper, get_papers_by_author, get_papers_by_category]
)

# Review agent
reviewer = Agent(
    name="Reviewer",
    role="Research Reviewer"
)

# Define tasks
search_task = Task(
    description="Find papers on AI ethics",
    agent=searcher
)

review_task = Task(
    description="Review and summarize findings",
    agent=reviewer
)

# Run workflow
agents = AgentTeam(
    agents=[searcher, reviewer],
    tasks=[search_task, review_task]
)

Related

Custom Tools

Build your own agent tools

 Tools Overview

Browse PraisonAI tool documentation