Metraipolis › archive › dc_5bc9b8ff9bd2

Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge — arXiv:2609.01095

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01095
License (as archived)
CC0-1.0
Archived
2026-10-17T06:57:07.013Z
SHA-256 of the archived text
b1760058a47bacf7f424cb361037828a597f1f910cf78bb59fe27896fc86d9af
Stable URL of this page
https://metraipolis.com/documento/dc_5bc9b8ff9bd2

How to cite

Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge — arXiv:2609.01095 — arXiv (en), https://arxiv.org/abs/2609.01095 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bc9b8ff9bd2 (Metraipolis archive dc_5bc9b8ff9bd2, sha256 b1760058a47bacf7f424cb361037828a597f1f910cf78bb59fe27896fc86d9af)
BibTeX
@misc{dc5bc9b8ff9bd2,
  title = {Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge — arXiv:2609.01095},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01095},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bc9b8ff9bd2; sha256 b1760058a47bacf7f424cb361037828a597f1f910cf78bb59fe27896fc86d9af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01095. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Extracting physics information from modern particle-physics experiments requires multistage analyses implemented on top of large and highly interconnected software ecosystems. General-purpose large language models (LLMs) often produce unreliable programs for such tasks because a user request alone rarely specifies the required APIs, dependencies, and usage conventions. We organize these software relations before generation and retrieve task-relevant knowledge at inference time. Using the open-source ROOT framework as a representative and reproducible testbed, we evaluate a complete grounding system that combines hybrid retrieval over a heterogeneous software knowledge graph, skill-selected workflow examples, and execution-guided repair. On a benchmark of 275 ROOT tasks, grounding improves first-attempt execution from 58.5% to 76.0% under Claude Code orchestration and from 51.3% to 64.0% under standalone orchestration. Final success increases from 90.5% to 96.0% and from 78.9% to 90.9%, respectively, while the average generation cost per successful task increases by only 1.3% and 3.2%. The gains persist under a strong coding agent, indicating that explicit software knowledge remains valuable even when agentic scaffolding is already in place. Because the method captures software relations common to large codebases rather than facts specific to ROOT or a particular model, it should transfer to other experiment frameworks and proprietary software, especially where documentation is sparse or internal dependencies are complex.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-02 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE) ; High Energy Physics - Experiment (hep-ex).
Pagina del lavoro: https://arxiv.org/abs/2609.01095 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:43:00.617Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).