Iterative Search: Refining Research Through Multiple Rounds

In the previous lesson, you learned how DeepResearcher could take a research question, generate search queries, and extract useful information from web pages—all in a single round. However, real research often requires digging deeper: using what you’ve found to guide further searching. In this lesson, we’ll focus on the key modifications that transform DeepResearcher from a single-pass tool into an iterative, multi-round research assistant.

Previously, DeepResearcher worked as follows:

• It generated a list of search queries from the user’s question.
• It searched the web for each query and evaluated the usefulness of each page.
• It extracted relevant information from useful pages.
• All of this happened in just one round—no follow-up searches based on what was found.

While this approach works for simple questions, it often misses deeper or related information that only becomes apparent after reviewing initial results.

Let’s walk through the key modifications that enable DeepResearcher to perform iterative, multi-round research.

Before:
DeepResearcher performed all its work in a single pass.

Now:
A while loop has been added to the perform_iterative_research function. This loop allows the tool to repeat the search-extract-plan cycle multiple times, up to a user-defined limit.

def perform_iterative_research(user_query: str, new_search_queries: list, all_search_queries: list, iteration_limit: int):
    aggregated_contexts = []
    iteration = 0

    while iteration < iteration_limit:
        print(f"\n=== Iteration {iteration + 1} ===")
        iteration_contexts = []
        # ...search, extract, and plan...
        iteration += 1

    return aggregated_contexts

Before:
Extracted information was stored in a single list for one round.

Now:
A new list, aggregated_contexts, collects all useful information found across every round. Each iteration’s new findings are added to this master list, ensuring nothing is lost as the research progresses.

    # Inside the while loop
    if iteration_contexts:
        aggregated_contexts.extend(iteration_contexts)
    else:
        print("No useful context found this round.")