MGI Tech and Shanghai AI Laboratory unveil ProtoPilot and BioLab Bench, pioneering physical AI for life sciences
by MGI · News-MedicalProtoPilot: A Full-Chain Agent System That Learns from Failure
ProtoPilot is a self-evolving multi-agent system that covers the entire experimental lifecycle:
Design2Protocol → Protocol2Code → Device Execution → Wet-Lab Feedback
It learns from failure. When a PCA assembly step failed, ProtoPilot diagnosed the issue (antibiotic resistance screening failure) and autonomously regenerated a corrected protocol - proving true Physical AI is here.
On ProtocolQA, one of the most representative public benchmarks for evaluating AI experimental reasoning capabilities (built by AI4S leader Future House):
- GPT-5.6-sol scored 43.5%
- Human expert level stands at 54%
- ProtoPilot achieved 52.38% - approaching expert-level performance!
Image Credit: MGI
BioLab Bench: The First Real-Task Evaluation System for Life Science Agents
BioLab Bench sets a new industry standard. It’s the first evaluation system that measures not just “correct answers,” but whether an agent can actually execute tasks on real automation equipment.
Key features include:
- Real-World Task Coverage: BioLab Bench spans from fundamental operations to complex multi-step workflows, stratified across three difficulty levels (L1–L3).
- Full-Chain Assessment: Rather than merely checking whether an agent generates a plausible protocol, BioLab Bench evaluates each step - intent interpretation, protocol design, device-agnostic SOP generation, device-specific SOP translation, machine code production, and successful execution gate verification.
- Cross-Device Transferability: The benchmark can be deployed on different automated laboratory platforms to test whether an AI agent can comprehend experimental tasks and generate executable actions adapted to varying hardware configurations, thus assessing cross-device generalization capability.
Image Credit: MGI
Toward 7×24 Unattended Smart Laboratories
Moving forward, BioAgents will no longer improve solely through text-based training. Instead, through the Physical AI experimental loop, they will continuously accumulate real research tasks, automation operations, expert validations, failure cases, and wet-lab feedback. This massive corpus of physical experimental data will enable BioAgents to develop integrated reasoning, execution, and validation capabilities - ultimately powering 7×24 unattended intelligent laboratories.
Built on Real-World Lab Experience
The new Physical AI initiative builds on MGI’s unique hardware-native advantages with deep integration across its automation platforms, and real-world deployment expertise gained from over 3,800 users globally.
About Genoria AI
About Shanghai Artificial Intelligence Laboratory
The Shanghai AI Laboratory was officially unveiled at the World AI Conference (WAIC) in July 2020 and positioned as a national-level new-type research institute. Our vision is to build a world-class AI laboratory, with pioneering contributions on original theories and key technologies.
Source: