A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols

2026-06-30 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Life Sciences & Biology · Depth: Expert, quick

Summary

ProtoPilot is a self-evolving multi-agent system developed for autonomous wet-lab experimentation, designed to align biological intent, quantitative procedures, device constraints, and experimental feedback from protocol design to physical execution. It incorporates layer-wise verifiability, multi-agent orchestration, and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code, and revise workflows based on wet-lab feedback. The system was evaluated using an expert-grounded benchmark covering 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols. ProtoPilot achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5%, and an Opentrons pass rate of 88.24%, significantly outperforming OpenTrons-AI's 32.35%. Wet-lab validation confirmed interpretable readouts and Sanger-confirmed products, establishing a verifiable route to autonomous experimentation.

Key takeaway

For Robotics Engineers or Research Scientists developing autonomous wet-lab systems, ProtoPilot's architecture offers a robust framework for verifiable protocol automation. You should consider integrating multi-agent orchestration and runtime-updated skill libraries to enhance system adaptability and feedback-guided revision. This approach can significantly improve the reliability and success rates of your automated biological experiments, moving beyond simple text generation to validated physical execution.

Key insights

ProtoPilot demonstrates a verifiable route to autonomous wet-lab experimentation through a self-evolving multi-agent system.

Principles

• Multi-agent orchestration improves experimental automation.
• Runtime-updated skill libraries enhance system adaptability.
• Layer-wise verifiability is crucial for biological protocols.

Method

ProtoPilot generates protocols, expands SOPs, synthesizes SDK-compliant code, and revises workflows by integrating multi-agent orchestration, layer-wise verifiability, and a runtime-updated skill library, guided by wet-lab feedback.

In practice

• Automate biological protocol generation.
• Synthesize Opentrons-compatible experimental code.
• Implement feedback-guided workflow revisions.

Topics

• Autonomous Wet-Lab Experimentation
• Multi-Agent Systems
• Biological Protocols
• Synthetic Biology
• Molecular Biology
• Opentrons Automation

Best for: AI Scientist, Robotics Engineer, Research Scientist

Related on AIssential

• LAP: An Agent-to-Instrument Protocol for Autonomous Science — LAP provides a standardized protocol for AI agents to safely and reliably control physical scientific instruments, filling a critical gap in autonomous science infrastructure.
• GPT-5 lowers the cost of cell-free protein synthesis — GPT-5 connected to a robotic lab significantly reduced cell-free protein synthesis costs through autonomous closed-loop optimization.
• AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing — AutoNumerics autonomously designs and verifies transparent PDE solvers from natural language using a multi-agent framework.
• A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline — AI agents show promise for individual scientific pipeline stages but struggle with scientific judgment and end-to-end integration.
• From Data to Theory: Autonomous Large Language Model Agents for Materials Science — Autonomous LLM agents can perform end-to-end scientific theory development, from equation selection to code execution and validation.
• Autogenesis: A Self-Evolving Agent Protocol — Autogenesis Protocol enables self-evolving LLM agents through structured resource management and auditable closed-loop evolution.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.