add deep research agent as an example #679
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
There was a problem hiding this comment.
Pull Request Overview
This PR introduces a comprehensive deep research agent implementation as an example within the AgentScope framework. The agent performs sophisticated multi-step research tasks by decomposing complex queries, conducting web searches, and generating detailed reports.
Key changes include:
- Implementation of a DeepResearchAgent class with advanced research capabilities
- Supporting utilities for web search result processing and prompt management
- Structured data models for task decomposition and result formatting
- Comprehensive prompt templates for various research phases
Reviewed Changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated 7 comments.
Show a summary per file
| File | Description |
|---|---|
deep_research_agent.py |
Main agent implementation extending ReActAgent with deep research capabilities |
main.py |
Entry point demonstrating agent usage with DashScope model and Tavily search |
utils.py |
Helper functions for prompt loading, search result truncation, and structured output |
promptmodule.py |
Pydantic models defining structured output schemas for research tasks |
prompt_*.md |
Detailed prompt templates for different research phases and tool usage |
README.md |
Documentation explaining setup, usage, and configuration options |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Luohh5
force-pushed
the
deepresearch_agent
branch
2 times, most recently
from
b6fcc87 to
8933eed
Compare
Co-authored-by: Yuexiang Xie <[email protected]>
Luohh5
force-pushed
the
deepresearch_agent
branch
from
8933eed to
6deaa72
Compare
DavdGao
approved these changes
Aug 19, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
name: Creating deep research agent as an example
Description
Creating deep research agent as an example
Core Components
deep_research_agent.py: The main agent class.main.py: The main function to start the application with deep research agent.README.md: The readme file.utils.py: Additional functions for agent.built_in_prompt/*.md: Detailed prompts for deep research agent.built_in_prompt/promptmodule.py: Json schema for structure ourput.Checklist
Please check the following items before code is ready to be reviewed.