Mukul Negi, Rajdeep Ramola, Vipul Bijalwan, Gopal Datt, Aakanksha Pundir
The rapid growth of scholarly publications makes it difficult for researchers and students to locate relevant evidence, compare findings, and produce source-grounded answers efficiently. This paper presents Deep Research Agent, an AI-powered system for the automated analysis of research papers and the generation of citation-based answers. The system ingests uploaded PDF research papers, extracts and cleans the text, segments the content into retrievable passages, generates semantic embeddings using Sentence-BERT, stores the vectors in ChromaDB, and combines dense retrieval with BM25 keyword matching. Retrieved evidence is passed to a large language model via citation-aware prompts, ensuring that generated answers remain linked to the source passages. A Neo4j knowledge graph layer supports exploration of entity and topic relationships, while a Streamlit interface provides an accessible workflow for uploading papers and asking research questions. Compared with generic RAG assistants, the proposed system focuses specifically on local scholarly-paper analysis, hybrid retrieval, explicit evidence mapping, and citation-grounded responses. The revised manuscript also discusses practical deployment issues, including document quality, retrieval latency, privacy, evaluation, and scalability.