Towards autonomous quantum physics research using LLM agents with access to intelligent tools

2025-11-13

AI Summary

This study addresses the challenge of reducing human centrality in quantum physics research to enable autonomous scientific ideation and experimental realization. We propose the first integrated AI system that unifies literature comprehension, creative hypothesis generation, and experimental design—built upon a large language model (LLM)-based agent architecture and augmented with a domain-specific quantum toolchain. The system extracts novel conceptual insights from vast scientific corpora and models experimentally testable protocols. Key contributions include: (i) a novel quantum teleportation protocol; (ii) quantum network primitives under indefinite causal order; and (iii) a geometric phase formalism grounded in information recycling. The system generated multiple original proposals, two of which have matured into peer-reviewed publications. This work provides the first empirical demonstration of end-to-end autonomous AI-driven research in quantum physics, establishing feasibility for AI-led discovery across the full research lifecycle—from hypothesis formation to experimental validation.

Technology Category

• Machine Learning: Quantum Machine Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Artificial intelligence (AI) is used in numerous fields of science, yet the initial research questions and targets are still almost always provided by human researchers. AI-generated creative ideas in science are rare and often vague, so that it remains a human task to execute them. Automating idea generation and implementation in one coherent system would significantly shift the role of humans in the scientific process. Here we present AI-Mandel, an LLM agent that can generate and implement ideas in quantum physics. AI-Mandel formulates ideas from the literature and uses a domain-specific AI tool to turn them into concrete experiment designs that can readily be implemented in laboratories. The generated ideas by AI-Mandel are often scientifically interesting - for two of them we have already written independent scientific follow-up papers. The ideas include new variations of quantum teleportation, primitives of quantum networks in indefinite causal orders, and new concepts of geometric phases based on closed loops of quantum information transfer. AI-Mandel is a prototypical demonstration of an AI physicist that can generate and implement concrete, actionable ideas. Building such a system is not only useful to accelerate science, but it also reveals concrete open challenges on the path to human-level artificial scientists.

Problem

• Automating scientific idea generation and implementation in quantum physics
• Transforming literature concepts into concrete experiment designs
• Developing autonomous AI physicist agents for accelerated research

Innovation

• LLM agent autonomously generates quantum physics ideas
• Uses domain-specific AI tool for experiment design
• Demonstrates automated idea generation and implementation system