Reimagining computational quantum research with AI scientists
Organizations: College of Computing and Data Science, Nanyang Technological University, Singapore 639798, Singapore · School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 639798, Singapore
Abstract
AI scientists are expanding automated research across scientific domains, yet their ability to turn the scientific record into a foundation for autonomous discovery remains elusive. Here we uncover a fundamental barrier to this transition and demonstrate a route to overcome it in computational quantum science, where advances shape both what we can learn from complex quantum systems and what quantum computing can ultimately deliver. To identify this barrier, we introduce OmniQ, an expert-audited virtual research environment that converts published studies into executable reproduction tasks. Across 59 papers spanning classical simulation, quantum algorithms and quantum-property characterization, we systematically evaluate five agentic systems powered by large language models and six third-party agent harnesses. Our findings reveal that current AI scientists often fail to reproduce published results, exposing a fundamental mismatch between what scientific papers communicate and what autonomous agents require. By contrast, human expert intervention can turn these failures into successful reproductions, showing that the missing information can be identified and converted into reusable research experience. Guided by this observation, we develop Residual Agents (RA), a quantum-tailored self-improving AI scientist that distils externally verified workflow repairs into such experience. RA substantially improves research performance under fixed base models and limited adaptation budgets. For example, RA raises DeepSeek V4.1 Flash performance from 68% to 85%, matching Claude Code with Opus 5 at a third of its cost despite using a weaker base model. We integrate all reproduced results into an extensible platform built on the model context protocol, making verified research workflows directly accessible to AI scientists and allowing new scientific papers to be continuously incorporated.
Figures & tables
Appendix figures & tables19 assets
Supplementary material from the paper’s appendix.
Appendix
| Classical simulation of quantum systems | |||||
| Subcategory | Paper ID | Paper title | Journal | Fig. | Code |
| Tensor network | #2 | Efficient tensor network simulation of IBM’s Eagle kicked Ising experiment [ 14 ] | PRX Quantum | 3 | N |
| #7 | Matrix product states and first quantization [ 199 ] | PRL | 4 | N | |
| #8 | Low-rank quantics tensor train representations of Feynman diagrams for multiorbital electron-phonon models [ 200 ] | PRL | 1 | N | |
| #14 | Stable iPEPO tensor-network algorithm for dynamics of two-dimensional open quantum lattice models [ 201 ] | PRX | 5 | N | |
| Neural quantum state | #16 | Predicting topological entanglement entropy in a Rydberg analog simulator [ 204 ] | Nat. Phys. | 6 | Y |
| Level | Paper | Issue | Handling |
|---|---|---|---|
| I | #39 [ 222 ] | The reported results reflect an idealized setting rather than the actual execution of the algorithm described in the paper | Re-judge |
| #40 [ 162 ] | Underspecified experimental details in the paper and overly restrictive figure-based evaluation criteria | Re-judge | |
| #26 [ 218 ] | The initial criteria require the classical model to have at least ten times lower error than the quantum models, a requirement not explicitly stated in the paper, and incorrectly marks quantum-model results with errors below the prescribed range as failures. | Re-judge | |
| #9 [ 209 ] | The excited-state convention is reversed relative to the standard qubit convention | Re-judge | |
| #14 [ 201 ] | Hamiltonian bond-counting convention differs from the standard interpretation | Re-judge | |
| #51 [ 225 ] | Underspecified experimental details in the paper and overly restrictive figure-based evaluation criteria | Re-judge |
| DSH | mini-swe- agent | live-swe- agent | Intern- Agent | Deep- Code | HGM | Meta- Harness | |
| Reproduced tasks | 29 | 28 | 18 | 16 | 21 | 24 | 11 |
| Failed runs | 30 | 31 | 41 | 43 | 38 | 35 | 48 |
| No report | 6 | 0 | 1 | 13 | 0 | 1 | 1 |
| Substitution or fabrication | 4 | 8 | 14 | 7 | 4 | 9 | 13 |
| Reduced problem | 6 | 6 | 13 | 7 | 15 | 7 | 18 |
| Implementation error | 9 | 13 | 22 | 13 | 12 | 10 | 11 |
AI Agents for Scientific Discovery
AI agents for scientific discovery use language models, tools, and experiments to generate, test, and refine scientific knowledge.
See all 320 papers