MyArxivPodcast orchestrates an end-to-end AI pipeline to transform scholarly content into engaging audio shows. First, it polls arXiv APIs for new research submissions in user-defined categories and retrieves metadata and abstracts. Next, it invokes OpenAI's GPT-4 model to craft clear and concise summaries, highlighting key contributions and results. Summaries are fed into a TTS engine such as Amazon Polly or Google Cloud Text-to-Speech, producing natural-sounding narration. The agent automatically tags and organizes the generated audio, compiles episodes, updates an RSS feed, and handles file hosting integration. Advanced settings allow custom voice selection, summary length control, publication schedules, and distribution via popular podcast platforms, providing researchers and listeners with seamless, up-to-date scientific audio briefings.

ResearchGPT automates end-to-end academic research workflows by integrating paper retrieval, PDF parsing, NLP-based text extraction, and GPT-4 powered summarization. Starting with a user-defined research topic, it queries Semantic Scholar and arXiv APIs to gather relevant papers, downloads and parses PDF content, and employs GPT-4 to distill key concepts, methodologies, and results. The agent compiles individual paper insights into a cohesive, structured report, supporting exports in Markdown or PDF formats. Advanced configuration options allow users to tailor search filters, define custom summarization prompts, and adjust output styles. By orchestrating these steps, ResearchGPT reduces manual effort, accelerates literature reviews, and ensures comprehensive coverage of academic sources.