Multi-Agent Dev Team for Performance Optimization
This challenge involves building an multi-agent system. The goal is to simulate a collaborative development team focused on optimizing Python code for performance. A 'Lead Developer' agent, 'Code Reviewer' agent, and 'Performance Tester' agent, all powered by Gemini 3, will collaborate through A2A communication. They will generate, refactor, and benchmark code, using adaptive thinking budgets to manage complexity in optimization tasks and graph-based workflows for task delegation and feedback loops.
What you are building
The core problem, expected build, and operating context for this challenge.
Orchestrate an AutoGen multi-agent system with Gemini 3 for collaborative code optimization, leveraging A2A communication and adaptive thinking budgets.
How work is evaluated
Evaluation will assess the multi-agent system's ability to generate functional code, identify performance bottlenecks, successfully optimize the code, and demonstrate effective agent collaboration and adaptive reasoning.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Design and implement a multi-agent system using AutoGen for collaborative code development.
Facilitate agent-to-agent communication for iterative code generation and review.
Integrate automated testing and benchmarking tools into the agent workflow.
Utilize Gemini 3 (or Gemini 2.5 Pro) for advanced code generation, refactoring, and analysis.
Implement adaptive thinking budgets to manage the complexity of optimization tasks.
Reference links and supporting material
Sample data for 2 tasks
Challenge setup
Evaluation will assess the multi-agent system's ability to generate functional code, identify performance bottlenecks, successfully optimize the code, and demonstrate effective agent collaboration and adaptive reasoning.
Challenge input
{'problematic_function_description': 'string', 'initial_code': 'string', 'optimization_target': 'speed|memory'}
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{'optimized_code': 'string', 'original_performance_metrics': {'runtime_ms': 'float', 'memory_mb': 'float'}, 'optimized_performance_metrics': {'runt...
- Ensure optimized code produces correct results for test cases.
- Verify that optimized code shows a measurable improvement over original.
- Optimization Ratio target: 75
- Python execution harness
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- Ensure optimized code produces correct results for test cases.
- Verify that optimized code shows a measurable improvement over original.
Metrics
- Optimization_Ratio · Target 75
- Code_Quality_Score · Target 0.85
- Collaboration_Efficiency · Target 5
Workflow tasks
- Task 1
Input: {'problematic_function_description': 'string', 'initial_code': 'string', 'optimization_target': 'speed|memory'}
Output: {'optimized_code': 'string', 'original_performance_metrics': {'runtime_ms': 'float', 'memory_mb': 'float'}, 'optimized_performance_metrics': {'runtime_ms': 'float', 'memory_mb': 'float'}, 'optimization_report': 'string'}
Execution harness: Python
- Task 2
Input: {'generated_code': 'string', 'review_criteria': ['string']}
Output: {'reviewed_code': 'string', 'review_comments': [{'line': 'int', 'comment': 'string', 'severity': 'low|medium|high'}]}
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.