Tashan SciSpark Research Assistant

Automates scientific research workflows by integrating arXiv and Google Scholar for paper discovery, employing collaborative AI analysis through Mixture of Agents approach to generate novel research hypotheses, comprehensive literature reviews, and complete paper drafts across multiple scientific domains.

Tashan SciSpark automates scientific paper discovery, analysis, and idea generation through integration with arXiv, Google Scholar, and multiple LLM providers including OpenAI, DeepSeek, and Gemini. The system employs a Mixture of Agents approach for collaborative idea refinement, combining Bayesian reasoning, automated feature engineering, and transformer-based analysis to generate novel research hypotheses and comprehensive paper drafts. Built with FastAPI and Celery for scalable processing, it includes specialized prompt templates for entity extraction, hypothesis generation, and technical optimization.