A research agent is an AI system that autonomously searches the web, evaluates sources, chains multiple queries together (multi-hop retrieval), synthesizes findings, and produces cited reports. Systems like Perplexity, OpenAI Deep Research, and Google Gemini Deep Research demonstrate the power of this pattern. This guide covers the architecture and working code for building your own.

Research agents follow an iterative search-synthesize loop. Unlike simple RAG (retrieve once, generate once), a research agent dynamically generates follow-up queries based on what it has already found, evaluates source quality, and builds a comprehensive answer across multiple retrieval hops.

Complex questions are broken into atomic sub-questions. “What is the best framework for building multi-agent systems in 2026?” becomes:

• What multi-agent frameworks exist as of 2026?
• What are the benchmarks for each?
• What do production users report about reliability?

The agent needs a search tool that returns snippets with URLs. Options include SerpAPI, Tavily, Exa, Brave Search API, or Google Custom Search.

Not all search results are equal. The agent should score sources by:

• Recency: Prefer recent content for fast-moving fields
• Authority: Prefer official docs, academic papers, established publications
• Relevance: Semantic similarity to the sub-question
• Diversity: Avoid over-relying on a single source

The PRISM pattern (Precision-Recall Iterative Selection Mechanism) uses three specialized sub-agents:

• Question Analyzer: Decomposes the query into sub-questions
• Selector: Filters evidence for precision (removes noise)
• Adder: Recovers missing facts for recall (fills gaps)

The final step combines all gathered evidence into a coherent answer with inline citations.

A complete research agent using the OpenAI API and Tavily for web search.

import json, os
from openai import OpenAI
import requests
 
client = OpenAI()
MODEL = "gpt-4o"
TAVILY_API_KEY = os.environ["TAVILY_API_KEY"]
MAX_HOPS = 3
 
def web_search(query: str, max_results: int = 5) -> list[dict]:
    """Search the web using Tavily API."""
    response = requests.post(
        "https://api.tavily.com/search",
        json={
            "api_key": TAVILY_API_KEY,
            "query": query,
            "max_results": max_results,
            "include_raw_content": False,
        },
    )
    results = response.json().get("results", [])
    return [
        {"title": r["title"], "url": r["url"], "content": r["content"]}
        for r in results
    ]
 
def evaluate_sources(sources: list[dict], query: str) -> list[dict]:
    """Score and rank sources by relevance."""
    prompt = f"""Rate each source 1-10 for relevance to: {query}
    Return JSON array with url and score fields only.
    Sources: {json.dumps(sources)}"""
 
    response = client.chat.completions.create(
        model=MODEL,
        messages=[{"role": "user", "content": prompt}],
        response_format={"type": "json_object"},
    )
    scored = json.loads(response.choices[0].message.content)
    return sorted(scored.get("sources", scored.get("results", [])),
                  key=lambda x: x.get("score", 0), reverse=True)
 
TOOLS = [
    {
        "type": "function",
        "function": {
            "name": "search",
            "description": "Search the web for information on a topic.",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "Search query"}
                },
                "required": ["query"],
            },
        },
    }
]
 
def research(question: str) -> str:
    """Run multi-hop research on a question."""
    all_sources = []
    evidence = []
 
    messages = [
        {
            "role": "system",
            "content": (
                "You are a research agent. Search for information to answer "
                "the question thoroughly. Make multiple searches to cover "
                "different angles. When you have enough evidence, provide "
                "a comprehensive answer with citations [1], [2], etc."
            ),
        },
        {"role": "user", "content": question},
    ]
 
    for hop in range(MAX_HOPS * 3):  # Allow multiple searches per hop
        response = client.chat.completions.create(
            model=MODEL, messages=messages, tools=TOOLS
        )
        msg = response.choices[0].message
        messages.append(msg)
 
        if not msg.tool_calls:
            # Agent is done -- attach source list
            source_list = "\n".join(
                f"[{i+1}] {s['title']} - {s['url']}"
                for i, s in enumerate(all_sources)
            )
            return f"{msg.content}\n\nSources:\n{source_list}"
 
        for tc in msg.tool_calls:
            args = json.loads(tc.function.arguments)
            results = web_search(args["query"])
            all_sources.extend(results)
 
            content_block = "\n\n".join(
                f"[{r['title']}]({r['url']}): {r['content']}"
                for r in results
            )
            messages.append({
                "role": "tool",
                "tool_call_id": tc.id,
                "content": content_block,
            })
 
    return "Research incomplete -- max hops reached."
 
if __name__ == "__main__":
    report = research("What are the best patterns for building AI agents in 2026?")
    print(report)

Using LangGraph for a stateful, multi-hop research workflow with explicit graph-based control flow.

import os, json, operator
from typing import Annotated, TypedDict
from langgraph.graph import StateGraph, END
from langchain_openai import ChatOpenAI
from langchain_community.tools.tavily_search import TavilySearchResults
 
llm = ChatOpenAI(model="gpt-4o")
search_tool = TavilySearchResults(max_results=5)
 
class ResearchState(TypedDict):
    question: str
    sub_questions: list[str]
    current_hop: int
    max_hops: int
    evidence: Annotated[list[dict], operator.add]
    sources: Annotated[list[dict], operator.add]
    answer: str
 
def decompose_question(state: ResearchState) -> ResearchState:
    """Break the question into sub-questions."""
    response = llm.invoke(
        f"Break this question into 3-5 specific sub-questions that "
        f"would help research a thorough answer:\n{state['question']}\n"
        f"Return as JSON array of strings."
    )
    subs = json.loads(response.content)
    return {"sub_questions": subs, "current_hop": 0}
 
def search_evidence(state: ResearchState) -> ResearchState:
    """Search for each sub-question."""
    new_evidence = []
    new_sources = []
    for sq in state["sub_questions"]:
        results = search_tool.invoke(sq)
        for r in results:
            new_evidence.append({"query": sq, "content": r["content"]})
            new_sources.append({"url": r["url"], "title": r.get("title", "")})
    return {
        "evidence": new_evidence,
        "sources": new_sources,
        "current_hop": state["current_hop"] + 1,
    }
 
def evaluate_completeness(state: ResearchState) -> str:
    """Decide if we have enough evidence or need more hops."""
    if state["current_hop"] >= state["max_hops"]:
        return "synthesize"
    response = llm.invoke(
        f"Question: {state['question']}\n"
        f"Evidence gathered: {len(state['evidence'])} items\n"
        f"Do we have enough evidence for a thorough answer? "
        f"Reply ONLY 'yes' or 'no'."
    )
    return "synthesize" if "yes" in response.content.lower() else "search_more"
 
def generate_followups(state: ResearchState) -> ResearchState:
    """Generate follow-up questions based on gaps."""
    evidence_summary = "\n".join(e["content"][:200] for e in state["evidence"][-5:])
    response = llm.invoke(
        f"Original question: {state['question']}\n"
        f"Evidence so far: {evidence_summary}\n"
        f"What 2-3 follow-up questions would fill gaps? JSON array of strings."
    )
    followups = json.loads(response.content)
    return {"sub_questions": followups}
 
def synthesize(state: ResearchState) -> ResearchState:
    """Produce final answer with citations."""
    evidence_text = "\n\n".join(
        f"Source {i+1}: {e['content']}" for i, e in enumerate(state["evidence"])
    )
    seen_urls = set()
    unique_sources = []
    for s in state["sources"]:
        if s["url"] not in seen_urls:
            seen_urls.add(s["url"])
            unique_sources.append(s)
 
    response = llm.invoke(
        f"Write a comprehensive answer to: {state['question']}\n\n"
        f"Use this evidence (cite as [1], [2], etc.):\n{evidence_text}\n\n"
        f"Be thorough, accurate, and well-structured."
    )
    source_list = "\n".join(
        f"[{i+1}] {s.get('title', 'Source')} - {s['url']}"
        for i, s in enumerate(unique_sources)
    )
    return {"answer": f"{response.content}\n\nSources:\n{source_list}"}
 
# Build the graph
workflow = StateGraph(ResearchState)
workflow.add_node("decompose", decompose_question)
workflow.add_node("search", search_evidence)
workflow.add_node("followup", generate_followups)
workflow.add_node("synthesize", synthesize)
 
workflow.set_entry_point("decompose")
workflow.add_edge("decompose", "search")
workflow.add_conditional_edges("search", evaluate_completeness, {
    "synthesize": "synthesize",
    "search_more": "followup",
})
workflow.add_edge("followup", "search")
workflow.add_edge("synthesize", END)
 
app = workflow.compile()
 
# Run research
result = app.invoke({
    "question": "What are the best agentic search patterns in 2026?",
    "sub_questions": [],
    "current_hop": 0,
    "max_hops": 3,
    "evidence": [],
    "sources": [],
    "answer": "",
})
print(result["answer"])

Research from 2025-2026 has identified several effective patterns:

1. Iterative Deepening: Start broad, then narrow. First search gives an overview; follow-up searches target specific claims or gaps.

2. Multi-Source Triangulation: For factual claims, search across 3+ independent sources. Only include claims confirmed by multiple sources.

3. Temporal Filtering: For fast-moving topics (AI, policy), filter results by date. Information older than 6 months may be outdated.

4. Adversarial Verification: After forming an initial answer, search for counter-evidence. “Why might X be wrong?” queries catch biases.

5. PRISM Pattern: Separate precision (filtering noise) from recall (finding missing facts) into distinct agent roles. This produces compact yet comprehensive evidence sets.

• Deduplicate sources: Track URLs to avoid citing the same source multiple times
• Cap search depth: Set a maximum hop count (3-5) to prevent infinite research loops
• Evaluate before synthesizing: Have the agent assess evidence completeness before writing
• Include source diversity: Ensure answers draw from multiple domains, not just one site
• Handle search failures: Retry with rephrased queries when search returns no useful results
• Rate limit awareness: Implement backoff for search API rate limits
• Token budget: Track total tokens consumed and stop gracefully when approaching limits

• PRISM: Precision-Recall Iterative Selection Mechanism - arXiv
• SerpAPI Web Research Agent - GitHub
• Deep Research: Local Deep Search Agent - GitHub
• Chain of Agents - Google Research
• Best Semantic Search APIs for AI Applications 2026 - Firecrawl

• How to Build a Coding Agent
• How to Build a Multi-Agent System
• How to Build a Data Analysis Agent