MCP-Enabled Drug Design Agent
Develop a cutting-edge multi-agent system designed to accelerate computer-aided drug discovery or battery material design. This challenge focuses on building a sophisticated R&D workflow using graph-based agent orchestration, advanced RAG, and MCP-enabled tool integration. Agents will autonomously research, hypothesize, simulate, and refine designs by interacting with specialized scientific databases and simulation APIs. The system will employ GPT-5 for its advanced reasoning capabilities, leveraging an 'extended thinking' pattern with adaptive reasoning budgets to tackle complex scientific problems. LangGraph will define the sequential and parallel execution of agents, allowing for dynamic re-evaluation and iterative design cycles. LlamaIndex will manage an optimized RAG pipeline over vast scientific literature, ensuring agents have access to the most current and relevant data. Participants will implement MCP for seamless integration with external computational chemistry or materials simulation tools, enabling agents to execute experiments and analyze results within the defined workflow. This project simulates a real-world application of generative AI and agentic systems in scientific discovery, pushing the boundaries of autonomous research.
AI Research & Mentorship
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a cutting-edge multi-agent system designed to accelerate computer-aided drug discovery or battery material design. This challenge focuses on building a sophisticated R&D workflow using graph-based agent orchestration, advanced RAG, and MCP-enabled tool integration. Agents will autonomously research, hypothesize, simulate, and refine designs by interacting with specialized scientific databases and simulation APIs. The system will employ GPT-5 for its advanced reasoning capabilities, leveraging an 'extended thinking' pattern with adaptive reasoning budgets to tackle complex scientific problems. LangGraph will define the sequential and parallel execution of agents, allowing for dynamic re-evaluation and iterative design cycles. LlamaIndex will manage an optimized RAG pipeline over vast scientific literature, ensuring agents have access to the most current and relevant data. Participants will implement MCP for seamless integration with external computational chemistry or materials simulation tools, enabling agents to execute experiments and analyze results within the defined workflow. This project simulates a real-world application of generative AI and agentic systems in scientific discovery, pushing the boundaries of autonomous research.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master LangGraph for building stateful Directed Acyclic Graph (DAG) agent workflows, including loop handling and dynamic branching for iterative design processes.
Implement an advanced RAG pipeline using LlamaIndex with vector databases (e.g., Chroma, Weaviate) and GPT-5 for retrieving and synthesizing information from dense scientific papers.
Design and implement MCP-enabled tool integration for external scientific APIs (e.g., molecular dynamics simulators, DFT calculators), ensuring secure and efficient data exchange.
Build a 'Hypothesis Generator' agent leveraging GPT-5's 'extended thinking' pattern, utilizing adaptive reasoning budgets to explore novel drug compounds or material compositions.
Develop a 'Simulation Analyst' agent that interprets results from external scientific tools via MCP and provides feedback to other agents for design refinement.
Orchestrate agent-to-agent communication within LangGraph to facilitate collaborative problem-solving between specialized research and analysis agents.
Deploy a robust system capable of tracking experiment metadata and results, ensuring reproducibility and iterative improvement in scientific design.
Participation status
You haven't started this challenge yet
Operating window
Key dates and the organization behind this challenge.
Find another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.