We are happy to introduce k-agents: our knowledge-centred laboratory automation framework 🤖.
⚛️ Quantum computers are becoming more powerful—but also more complex.
🤔 How do we build AI systems that know how to operate them?
📄 Read the paper: https://arxiv.org/abs/2412.07978
#AI #LLM #QuantumComputing
⚛️ Quantum computers are becoming more powerful—but also more complex.
🤔 How do we build AI systems that know how to operate them?
📄 Read the paper: https://arxiv.org/abs/2412.07978
#AI #LLM #QuantumComputing
Comments
It helps organize laboratory knowledge and embeds it into LLM-based agents for running experiments on state machines:
✅ AI agents execute each experiment step
👀 Visual LLMs analyze results
➡️ Select the next experiment based on the result
♾️ Support a huge number of steps
Our agents calibrated and operated a superconducting quantum processor—conducting multi-hour experiments to create and characterize entangled quantum states.
🌟 More than quantum!
k-agents is a general framework that could help lab automation across various disciplines.
💻 Explore the code: https://github.com/EvoEvolver/k_agents
😀 Happy to be part of the team @aspuru.bsky.social @scao.me