# Agent-based code generation for the Gammapy framework

arXiv: https://arxiv.org/abs/2509.26110 · HTML: https://mlsanity.com/paper/2509.26110/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 5 of 5)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [AI Agents for Ground-Based Gamma Astronomy](https://mlsanity.com/paper/2503.00821/) (2025)

## Built on by (most cited first, 2 of 2)

- [Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis](https://mlsanity.com/paper/2510.01299/) (2025)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)

## Abstract (arXiv)

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resources and may expose unstable APIs under active development, making it difficult for models trained on limited or outdated data.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.