Research Agents

Nubint offers 13 AI Research Agents in four groups: Design, Search, Writing, and Review. They cover the full workflow from topic recommendation and hypothesis generation to literature review, draft writing, and peer review, all accessible through AI Chat.

Open AI Chat and pick an agent from the list above the chat input, or click an agent in the left sidebar. Each run deducts credits based on your plan, and results are saved to your chat history, library, and documents for later reference.

The Topic Generator analyzes over 280 million papers to find trends and gaps from a single keyword. It highlights under-explored areas to suggest unique topics, and you can refine results by adding conditions like population or region before moving to the Hypothesis Generator.

The Hypothesis Generator agent draws on over 280 million papers to propose multiple testable hypothesis candidates for your topic. You can refine them by specifying variable relationships or scope, and results pass directly to the Hypothesis Evaluator agent.

The Hypothesis Evaluator agent scores your hypothesis on four criteria: originality, feasibility, clarity, and significance, with specific feedback for each. It detects weak points and suggests improvements so you can refine your hypothesis before moving to Literature Review.

The Survey Generator analyzes prior research based on your hypothesis and designs survey structure, items, and scales. It selects scales like Likert, semantic differential, and multiple choice, and you can adjust item count or change scales through the chat.

The Literature Review agent collects related papers and analyzes up to 40 at once, organizing findings, methodologies, and trends into a structured report with auto-generated references. You can export results as a document and continue to the Research Gap Finder agent.

The Research Gap Finder classifies gaps into four types: theoretical, methodological, empirical, and application, rating each by importance and feasibility. It can also analyze library papers, and discovered gaps carry forward to the Hypothesis Generator or Methodology Advisor.

The Advisor Paper Analyzer agent scans over 280 million papers by researcher name to compile their 5-year publications, core keywords, top-cited papers, and co-author network. It produces a single report covering the researcher's full trajectory and institutional partnerships.

The Research Flow Explorer agent traces a paper's citation network by splitting it into upstream (papers it cites) and downstream (papers that cite it). This reveals the foundational work and subsequent influence, showing how a study fits within its field.

The Citation Finder agent analyzes your sentence context and recommends relevant papers ranked by reliability from over 280 million entries. Each paper includes a DOI link, and formats like APA, MLA, and Chicago are applied automatically with BibTeX export for LaTeX.

The Methodology Advisor agent analyzes your research question to recommend qualitative, quantitative, or mixed methods with real paper examples and tool guides. Recommendations are based on methodologies used in similar studies, and results carry forward to the Survey Generator.

The Draft Writer agent plans the structure of each section and generates a full draft based on your research topic and hypothesis. It references library papers to include citations, and the generated draft can be edited directly in the AI Paper Editor.

The Peer Reviewer agent evaluates your paper across four areas: structure, logical flow, methodology, and citations. It analyzes strengths and weaknesses from a journal-review perspective with improvement suggestions for each, after which you can finish with the Proofreader.

The Proofreader agent reviews grammar, academic expressions, sentence structure, and terminology consistency with specific corrections for each. It converts informal language to academic tone and simplifies complex sentences, best used after Peer Review for a final polish.

The stop button in AI Chat immediately halts any ongoing response, while toggles let you control external and library paper search independently. Keep external search on during exploration and switch to library-only during writing to focus on papers you already have.

The Add Context button lets you select specific papers or collections from your library so AI bases its responses on those materials. Use it when asking about a specific paper, analyzing a collection, or specifying references for AI editing. Contexts appear as removable chips.

Click the New Chat button at the top of the chat panel to start a fresh conversation while auto-saving the previous one. Use it when switching research questions or when a conversation loses focus, and return to previous chats anytime from the chat list.