TY  - EJOUR
AU  - Kostunin, Dmitriy
AU  - Sotnikov, Vladimir
AU  - Golovachev, Sergo
AU  - Mehta, Abhay
AU  - Holch, Tim Lukas
AU  - Jones, Elisa
TI  - Agent-based code generation for the Gammapy framework
IS  - arXiv:2509.26110
M1  - PUBDB-2026-00668
M1  - arXiv:2509.26110
PY  - 2025
N1  - ICRC2025 proceedings PoS(ICRC2025)753
AB  - Software code generation using Large Language Models (LLMs) is one of the most successful applications of modern artificial intelligence. Foundational models are very effective for popular frameworks that benefit from documentation, examples, and strong community support. In contrast, specialized scientific libraries often lack these resources and may expose unstable APIs under active development, making it difficult for models trained on limited or outdated data. We address these issues for the Gammapy library by developing an agent capable of writing, executing, and validating code in a controlled environment. We present a minimal web demo and an accompanying benchmarking suite. This contribution summarizes the design, reports our current status, and outlines next steps.
LB  - PUB:(DE-HGF)25
UR  - https://bib-pubdb1.desy.de/record/645890
ER  -