TY - CONF 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 JO - Proceedings of Science / International School for Advanced Studies VL - (ICRC2025) IS - arXiv:2509.26110 SN - 1824-8039 CY - Trieste PB - SISSA M1 - PUBDB-2025-04934 M1 - arXiv:2509.26110 SP - 753 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resources and may expose unstable APIs under active development, making it difficult for models trained on limited or outdated data.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. T2 - 39th International Cosmic Ray Conference CY - 14 Jul 2025 - 24 Jul 2025, Geneva (Switzerland) Y2 - 14 Jul 2025 - 24 Jul 2025 M2 - Geneva, Switzerland LB - PUB:(DE-HGF)16 ; PUB:(DE-HGF)8 DO - DOI:10.22323/1.501.0753 UR - https://bib-pubdb1.desy.de/record/641203 ER -