MARVEL: Multi-Agent Research Validator & Enabler using LLMs

MARVEL v1.1.0 — Updated public release (accompanying MARVEL manuscript) This release is the archival, citeable snapshot of the MARVEL codebase accompanying the manuscript: arXiv:2601.03436 "MARVEL: A Multi‑Agent Research Validator and Enabler using LLMs" The MARVEL framework is a locally deployable, open-source system for domain-aware QA and assisted research with a fast path for simple queries and an optional DeepSearch mode for multi-step retrieval and synthesis. A public demo is available at: https://ligogpt.mit.edu/marvel What's included in this release marvel.py — Streamlit application (MARVEL-Standard + MARVEL-DeepSearch) config/ — configuration YAMLs (models, retrieval, data, prompts, etc.) scripts/ — setup + evaluation tooling Evaluation datasets: scripts/evaluation/datasets/ See: scripts/evaluation/datasets/README.md for file descriptions + schema Quickstart (minimal) Create conda environment (Linux/macOS/Windows): See README.md → "Conda environment setup" Helper: scripts/setup/setup_conda_env.py Local inference (recommended): install Ollama + pull default models: See README.md → "Local LLM inference with Ollama" Defaults are defined in config/models.yaml Select/build a FAISS vector store: Choose dataset via config/data.yaml (DocPDF, LatexData, TextData, JSONLData, or combined ALL_V2) FAISS stores persist under ./faiss/ / Launch: streamlit run marvel.py Optional services Groq (cloud LLM inference): set GROQ_API_KEY in config/retrieval.yaml Tavily (web search): set TAVILY_API_KEY in config/retrieval.yaml Citation arXiv DOI : 10.48550/arXiv.2601.03436 Zenodo DOI for this release: 10.5281/zenodo.18156827 Zenodo DOI for latest release: 10.5281/zenodo.18156826 Use GitHub "Cite this repository" (CITATION.cff) or cite the arXiv paper.