Accelerate R&D with Co-Scientist and AlphaEvolve agents

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Co-Scientist and AlphaEvolve are Google-developed agents that accelerate research and development processes. These agents leverage Gemini to automate complex scientific reasoning and algorithmic discovery.

Note: Access to these agents is restricted. To request access, contact your Google account team. Your account team provides detailed product documentation once they grant access.

Overview of Co-Scientist agent

Co-Scientist is a multi-agent AI system built on Gemini, designed to act as a virtual scientific collaborator. The system helps researchers uncover original knowledge and formulate novel research hypotheses and experimental proposals. By combining AI reasoning with the scientific method, Co-Scientist enables scientists to navigate literature, synthesize insights across domains, and accelerate biomedical discoveries.

How it works

Co-Scientist is built on a multi-agent architecture and an asynchronous task execution framework to scale test-time computation. This design allows the system to reason, debate, and improve outputs iteratively.

When you provide a research goal in natural language, Co-Scientist coordinates the following specialized agents:

• Generation agent: Explores literature using web search, synthesizes findings, and formulates initial hypotheses.
• Reflection agent: Acts as a peer reviewer to examine the correctness, quality, and safety of generated hypotheses.
• Ranking agent: Evaluates and prioritizes research proposals using an Elo-based tournament.
• Evolution agent: Refines top-ranked hypotheses by grounding them in literature and combining innovative ideas.
• Proximity agent: Organizes tournament matches and deduplicates hypotheses using a proximity graph.
• Meta-review agent: Synthesizes insights from all reviews and debates into a comprehensive research roadmap.

A dedicated Supervisor agent orchestrates the process, allocates resources, and manages the worker queue to maintain a self-improving loop of scientific reasoning.

Use cases

Co-Scientist solves complex problems across multiple scientific disciplines, specifically those requiring deep subject matter expertise and trans-disciplinary insights. Example use cases include:

• Drug repurposing: Identify novel therapeutic indications for approved drugs by analyzing molecular signatures, signaling pathways, and literature-based information.

• Target discovery: Propose new biological components and epigenetic targets for complex diseases and streamline hypothesis selection for experimental validation.

• Mechanistic explanations: Generate hypotheses for intricate problems, such as antimicrobial resistance, by synthesizing fragmented scientific data.

For more information and additional use cases, see the Accelerating scientific breakthroughs with an AI Co-Scientist blog.

Overview of AlphaEvolve agent

AlphaEvolve is a Gemini-powered evolutionary coding agent that discovers general-purpose algorithms and optimizes code. It combines Gemini's generative capabilities with automated evaluators to propose, verify, and improve entire codebases for complex problems in computing, operations research, and mathematics.

How it works

AlphaEvolve uses an evolutionary framework and an ensemble of Gemini models to refine programmatic solutions through an iterative process:

1. Generation: Gemini models propose novel computer programs to implement algorithmic solutions, maximizing the breadth of explored ideas.

2. Evaluation: The system assesses each solution's functional correctness and performance using objective, quantifiable metrics.

3. Evolutionary improvement: An evolutionary algorithm selects high-scoring programs from a database to serve as inputs for subsequent iterations.

Use cases

AlphaEvolve is effective in domains where progress is systematically measurable through verifiable, objective scoring. Example use cases include:

• AI training and inference acceleration: Optimize vital operations and low-level GPU instructions for AI training and inference.

• Hardware design assistance: Suggest and verify modifications in chip design languages, such as reducing bits in arithmetic circuits for Google's custom Tensor Processing Units (TPUs).

• Logistics and supply chain optimization: Solve large-scale combinatorial challenges in supply chain operations.

• Computing infrastructure optimization: Improve system-level operations and operational efficiency.

• Mathematical algorithm discovery: Propose solutions to open problems in geometry, combinatorics, and number theory.

For more use cases and results, see the AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms blog.

Next steps

To register your interest in the Early Access Program for Co-Scientist or AlphaEvolve, contact your Google Cloud account team.