Aug 2026· International Journal for Research in Applied Science and Engineering Technology· Vol 14, pp. 897-906· 0 citations
TL;DR
The AI Research Partner is presented, a full-stack MERN web platform that unifies the research-reading workflow — comprehension, synthesis, and ideation — into a single authenticated system, demonstrating that a single, prompt-engineered platform can reasonably reproduce the core stages of expert research reading within one coherent, collaborative interface.
Abstract
The rapid growth of published research literature has made manual, unaided reading a bottleneck for students and
early-stage researchers, who must extract structured understanding from unstructured PDF documents while operating at
varying levels of comprehension. This paper presents the AI Research Partner, a full-stack MERN (MongoDB, Express.js,
React, Node.js) web platform that unifies the research-reading workflow — comprehension, synthesis, and ideation — into a
single authenticated system. The platform ingests a PDF, extracts its text, and uses the Google Gemini large language model to
generate multi-level (basic, medium, technical) section summaries, an interactive D3.js concept knowledge graph, novelty-rated
research ideas, citation recommendations, auto-generated quizzes, and abstract/slide drafts, while a Socket.io-based real-time
layer enables collaborative annotation among multiple users. The system was implemented end-to-end, evaluated through
functional testing across eight modules, and benchmarked for AI feature response latency and concurrent-user scalability.
Results indicate pass rates above 87% across all modules, typical AI response times of 3-17 seconds depending on feature
complexity, and stable real-time note-broadcast latency under load, demonstrating that a single, prompt-engineered platform can
reasonably reproduce the core stages of expert research reading within one coherent, collaborative interface.
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.
Mukul Negi, Rajdeep Ramola, Vipul Bijalwan et al.· Revolutionary Advances in Co...· 0 citations
Artificial intelligence has become an essential part of academic writing, where researchers rely on it at nearly
every stage of the research, writing and publication process. This review works through 13 widely used AI
research tools. These tools are GitMind, SciSpace, Consensus, Paperpal, Jenni, CitedEvidence, Elicit, Scite,
Logically, Genspark, Gemini Notebook, Julius, and Claude. The review is organized into two complementary
parts. The first part maps each tool to the stage of academic writing where it performs several tasks such as
idea generation, literature searching, evidence verification, drafting, language editing, data analysis, citation
management, peer-review preparation, and journal selection. The second part involves a hands-on look at each
platform on its own, covering its main features, interface, supported workflows, and export options. Finally,
a comparative workflow, quick-reference tables, and a worked case study show how several tools can fit
together into one coherent research work flow. The review also addresses some of the common limitations,
citation inaccuracies, AI hallucinations, and data privacy concerns. It emphasizes on the case that human
judgment and verification still matter more than ever. It closes with a summary of current recommendations
from major publishing organizations on transparency and disclosure around AI-assisted writing. Rather than
favoring any platform, this article provides researchers, graduate students, and educators with a practical
framework for choosing appropriate AI tools and integrating them responsibly across the full academic writing
lifecycle.
Abdulmajid Hesham, Asma Sharfeddin· South Mediterranean Universi...· 0 citations
The design realization and evaluation of an Automated Summarization Tool (AST) is presented which is a document intelligence platform based on google gemini 2.5 flash that outperforms the strongest fine-tuned transformer baselines (PEGASUS, BART) by ~14 points and is clearly ahead of BERTSUM-ext (a strong transformer baseline), Pointer-Generator Network, TextRank.
K. Kumar, A. Amandeep, Dharmender Kumar et al.· International Journal of Inn...· 0 citations
The growing number of scientific publications requires tools that can automatically convert raw PDF research papers into structured, searchable knowledge. This paper introduces the Research AI Pipeline, a five-layer automated system for analysing academic PDF documents from start to finish. Layer 1 ingests PDFs through a FastAPI gateway that streams data in real time. Layer 2 extracts text using a combination of pdfplumber, PyMuPDF and pytesseract to create a normalised JSON schema that includes sections, tables, figures and numerical data. Layer 3 conducts a thorough quality audit with thirty-two checks across six validation groups, producing a severity score on a one-hundred-point scale. Layer 4 employs local large language model reasoning using DeepSeek-V3 via Ollama, with prompts tailored to maintain numerical accuracy in six types of summarised sections and a final synthesis. Layer 5 organises the output and supports an interactive QA interface that streams responses based on the extracted content. Tested on fifty research papers across various fields, the system achieves an F1-score of 0.89 for section boundary detection, 0.91 for figure caption matching and 88 percent accuracy in factual QA, all while operating locally without relying on cloud APIs. The average processing time is 87 seconds per paper.
S. C, Yogaraj S, Y. G et al.· Indian Journal of Computer S...· 0 citations
This work presents DocMaster, a hierarchical structure-aware document analysis system that parses documents into hierarchical document trees preserving original layouts and constructs a structure-aware semantic index that enables accurate document filtering and in-depth analysis.
Ziqi Chen, Yingli Zhou, Fangyuan Zhang et al.· 0 citations
This study provides an AI- Based document analyzer with a question-answer system that makes use of Natural Language Processing approaches that is affordable, scalable, and suitable for business, education, and research.
Radhika Sharma, Devraj Gautam· Revolutionary Advances in Co...· 0 citations
