CLAPP: The CLASS LLM Agent for Pair Programming
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
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
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 3 of its 13 references that are in the map. First posted on arXiv 7 Aug 2025.
Builds on
3 of 13 references.
Closest ancestors · 1
Same direction, newest first
- 2025Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery9 Jul
Other references · 2
- 2023GPT-4 Technical Reportcited by 18,396
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
- 2025Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning
- 2025PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation
- 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
- 2026HepScript: A Dual-Use DSL for Human-AI Collaborative Data Analysis Workflows in High-Energy Physics
- 2025Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis
- 2025Can Theoretical Physics Research Benefit from Language Agents?
- 2026AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents