{"ID":2885360,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05728","arxiv_id":"2508.05728","title":"CLAPP: The CLASS LLM Agent for Pair Programming","abstract":"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","short_abstract":"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, gene...","url_abs":"https://arxiv.org/abs/2508.05728","url_pdf":"https://arxiv.org/pdf/2508.05728v1","authors":"[\"Santiago Casas\",\"Christian Fidler\",\"Boris Bolliet\",\"Francisco Villaescusa-Navarro\",\"Julien Lesgourgues\"]","published":"2025-08-07T17:35:06Z","proceeding":"astro-ph.IM","tasks":"[\"astro-ph.IM\",\"astro-ph.CO\",\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\"]","project_urls":"[\"https://classclapp.streamlit.app\"]","has_code":false}