CLAPP: The CLASS LLM Agent for Pair Programming
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913979753824256 |
|---|---|
| author | Casas, Santiago Fidler, Christian Bolliet, Boris Villaescusa-Navarro, Francisco Lesgourgues, Julien |
| author_facet | Casas, Santiago Fidler, Christian Bolliet, Boris Villaescusa-Navarro, Francisco Lesgourgues, Julien |
| contents | We introduce CLAPP (CLASS LLM Agent for Pair Programming), an interactive AI assistant designed to support researchers working with the Einstein-Boltzmann solver CLASS. CLAPP leverages large language models (LLMs) and domain-specific retrieval to provide conversational coding support for CLASS-answering questions, generating code, debugging errors, and producing plots. Its architecture combines multi-agent LLM orchestration, semantic search across CLASS documentation, and a live Python execution environment. Deployed as a user-friendly web application, CLAPP lowers the entry barrier for scientists unfamiliar with AI tools and enables more productive human-AI collaboration in computational and numerical cosmology. The app is available at https://classclapp.streamlit.app |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CLAPP: The CLASS LLM Agent for Pair Programming Casas, Santiago Fidler, Christian Bolliet, Boris Villaescusa-Navarro, Francisco Lesgourgues, Julien Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Artificial Intelligence Multiagent Systems We introduce CLAPP (CLASS LLM Agent for Pair Programming), an interactive AI assistant designed to support researchers working with the Einstein-Boltzmann solver CLASS. CLAPP leverages large language models (LLMs) and domain-specific retrieval to provide conversational coding support for CLASS-answering questions, generating code, debugging errors, and producing plots. Its architecture combines multi-agent LLM orchestration, semantic search across CLASS documentation, and a live Python execution environment. Deployed as a user-friendly web application, CLAPP lowers the entry barrier for scientists unfamiliar with AI tools and enables more productive human-AI collaboration in computational and numerical cosmology. The app is available at https://classclapp.streamlit.app |
| title | CLAPP: The CLASS LLM Agent for Pair Programming |
| topic | Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2508.05728 |