Researchers have developed a multi-agent AI system that converts plain-language research questions into executed, checked and reproducible quantum simulations using several specialist software packages
Quantum simulations are computer models used to study systems governed by quantum mechanics. Researchers use them to calculate molecular energies, investigate new materials, model energy transfer and decoherence, test quantum-computing algorithms, and predict how quantum systems evolve over time. Such calculations can provide information that is difficult to obtain analytically or experimentally, but they often require specialist numerical methods and familiarity with multiple software tools.
AI agents are being developed to automate parts of this work. These agents can plan multistep tasks, consult documentation, run programs, examine results, and revise their approach. In physics, experimental systems such as SciExplorer have inferred equations and Hamiltonians from simulated observations. Related agent-based approaches are also being explored in mathematics, including the search for mathematical proofs.
El Agente Cuántico applies this approach to quantum simulation. A coordinating agent delegates work to specialist agents associated with different software packages, producing code, numerical results and figures for problems ranging from molecular-energy calculations to quantum error correction.
The researchers demonstrated the system’s capabilities on molecular-energy calculations, entangled states, dissipative dynamics, time crystals, error correction, and hardware-resource estimation. In repeated tests of five tasks, its average scores in expert assessments ranged from 97 to 100 out of 100. A small number of runs nevertheless departed from the instructions, for example by calculating the wrong observable or preparing an initial state using the wrong sampling procedure.
This approach could allow researchers to concentrate more on physical assumptions and interpretation, and less on software syntax. The authors present the agents as an aid to scientific judgement, not a replacement for it.