FUSION: a skill-based research agent for publicly obtainable nuclear-physics codes
Abstract
Running an unfamiliar nuclear-physics code is rarely difficult because of the physics alone. One must find and build the program, learn its input conventions, and decide whether a plausible output is actually correct. A general-purpose coding agent helps with the first two tasks but may make the last one harder: it can write an input file that runs with the wrong physical convention. FUSION addresses this problem with code-specific skills. A skill obtains the code from its public source, starts from a verified input, runs and parses the calculation, records known failure modes, and must reproduce a stated benchmark to a stated tolerance before reporting a result. The current release covers twenty codes, spanning optical models and reactions, nuclear structure, fission and statistical models, astrophysics and R-matrix analysis, and heavy-ion transport. It also includes an offline, searchable collection of 61 167 pages derived from the nucl-th literature. User notes and credentials remain outside the public repository. FUSION is available under the MIT license at https://github.com/jinleiphys/FUSION; documentation is at https://vibeinscience.com. Here I describe the design, the checks behind the current release, and one complete calculation from input to comparison with measured data.
Related
- Towards Stellarator Geometry Optimisation for Nuclear Fusion
- Concern about the editorial of Nuclear Physics News, Vol 36, issue of April-June 2026
- [SUPERSEDED] Physics-Informed AI and Quantum Technologies for Certifiable Real-Time Control of Compact Fusion Generators
- Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study
- Maximization of nuclear fusion reactivity via optimal energy distributions
BibTeX
@misc{lei2026fusion,
title = {{FUSION: a skill-based research agent for publicly obtainable nuclear-physics codes}},
author = {Jin Lei},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.04742},
eprint = {2609.04742},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04742},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FUSION: a skill-based research agent for publicly obtainable nuclear-physics codes
AU - Jin Lei
PY - 2026
DA - 2026/10/24
PB - arXiv
DO - 10.48550/arxiv.2609.04742
UR - https://arxiv.org/abs/2609.04742
AB - Running an unfamiliar nuclear-physics code is rarely difficult because of the physics alone. One must find and build the program, learn its input conventions, and decide whether a plausible output is actually correct. A general-purpose coding agent helps with the first two tasks but may make the last one harder: it can write an input file that runs with the wrong physical convention. FUSION addresses this problem with code-specific skills. A skill obtains the code from its public source, starts from a verified input, runs and parses the calculation, records known failure modes, and must reproduce a stated benchmark to a stated tolerance before reporting a result. The current release covers twenty codes, spanning optical models and reactions, nuclear structure, fission and statistical models, astrophysics and R-matrix analysis, and heavy-ion transport. It also includes an offline, searchable collection of 61 167 pages derived from the nucl-th literature. User notes and credentials remain outside the public repository. FUSION is available under the MIT license at https://github.com/jinleiphys/FUSION; documentation is at https://vibeinscience.com. Here I describe the design, the checks behind the current release, and one complete calculation from input to comparison with measured data.
ER -