Deep Research Agent: An AI-Powered System for Automated Research Paper Analysis and Citation-Based Answer Generation

Mukul Negi; Rajdeep Ramola; Vipul Bijalwan; Gopal Datt; Aakanksha  Pundir

doi:10.65890/race.v2i2.204

Authors

Mukul Negi Department of Computer Science and Engineering, Shivalik College of Engineering, Dehradun, Uttarakhand, India
Rajdeep Ramola Department of Computer Science and Engineering, Shivalik College of Engineering, Dehradun, Uttarakhand, India
Vipul Bijalwan Department of Computer Science and Engineering, Shivalik College of Engineering, Dehradun, Uttarakhand, India
Gopal Datt Department of Computer Science and Engineering, Shivalik College of Engineering, Dehradun, Uttarakhand, India
Aakanksha Pundir Department of Computer Science and Engineering, Shivalik College of Engineering, Dehradun, Uttarakhand, India

DOI:

https://doi.org/10.65890/race.v2i2.204

Keywords:

Deep Research Agent, Retrieval-Augmented Generation, Large Language Models, Citation-Aware Generation, Scholarly Retrieval, ChromaDB, Neo4j.

Abstract

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.

References

1. Lewis P., Perez E., Piktus A., Petroni F., Karpukhin V., Goyal N., et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems. 2020.

2. Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of EMNLP-IJCNLP. 2019. DOI: https://doi.org/10.18653/v1/D19-1410

3. Robertson S., Zaragoza H. The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends in Information Retrieval. 2009. DOI: https://doi.org/10.1561/1500000019

4. Luan Y., Eisenstein J., Toutanova K., Collins M. Sparse, Dense, and Attentional Representations for Text Retrieval. Transactions of the Association for Computational Linguistics. 2021. DOI: https://doi.org/10.1162/tacl_a_00369

5. Gao Y., Xiong Y., Gao X., Jia K., Pan J., Bi Y., et al. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv:2312.10997. 2023.

6. Fan W., Ding Y., Ning L., Wang S., Li H., Yin D., Chua T.-S., Li Q. A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models. arXiv:2405.06211. 2024. DOI: https://doi.org/10.1145/3637528.3671470

7. Huang Y., Huang J. A Survey on Retrieval-Augmented Text Generation for Large Language Models. arXiv:2404.10981. 2024.

8. Zhao P., Zhang H., Yu Q., Wang Z., Geng Y., Fu F., et al. Retrieval-Augmented Generation for AI-Generated Content: A Survey. arXiv:2402.19473. 2024.

9. Li W., Li J., Ma W., Liu Y. Citation-Enhanced Generation for LLM-based Chatbots. arXiv:2402.16063. 2024. DOI: https://doi.org/10.18653/v1/2024.acl-long.79

10. Qian H., Fan Y., Zhang R., Guo J. On the Capacity of Citation Generation by Large Language Models. arXiv:2410.11217. 2024. DOI: https://doi.org/10.1007/978-981-96-1710-4_9

11. Wang Y., Ma X., Nie P., Zeng H., Lyu Z., Zhang Y., et al. ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations. arXiv:2504.00824. 2025.

12. Jiang P., Ouyang S., Jiao Y., Zhong M., Tian R., Han J. A Survey on Retrieval and Structuring Augmented Generation with Large Language Models. arXiv:2509.10697. 2025. DOI: https://doi.org/10.1145/3711896.3736557

13. Fingleton Z., Siavash N., Moin A. Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation. arXiv:2604.15270. 2026.