April 2026

What's New in ResearchBuddy AI

See the evidence behind every claim — the Argument Heat Map is here, plus a sharper reading experience across the app.

🔥
NEWApril 2026

Argument Heat Map — See How Strong Your Evidence Really Is

Every literature review now comes with an Argument Heat Map. Two AI models (GPT + Claude) independently analyse your sources, then we cross-validate: each claim is scored by real citation data — not the AI grading itself. You instantly see which arguments are rock-solid, which need more sources, and where the research community disagrees.

How to use it

1
Generate a Literature Review
Go to the chat and run a Literature Review as usual. The heat map is built automatically.
2
Check the verdict
A plain-English verdict tells you the overall strength of your argument — no jargon, no guessing.
3
Explore claims by theme
Claims are grouped by topic. Each shows its strength (Strong / Verified / Thin / Unverified / Debated), the sources backing it, citation counts, and whether both models agreed.
4
Find gaps and conflicts
Scroll down to see where the literature disagrees and where research hasn't caught up — so you know exactly where to dig deeper.
Included with every Literature Review
🤖
NEWMarch 2026

Agent Mode — 6-Agent Research Pipeline

Submit a research question and watch 6 specialised AI agents work in parallel — decomposing your query, searching peer-reviewed papers, scraping the web, analysing, writing, and fact-checking — all automatically.

How to use it

1
Open Agent Mode
Click the sidebar toggle and select "Agent Mode", or go directly to /app?mode=agent.
2
Type your research question
Write your question as you would ask a human researcher — no special syntax needed. Example: "What is the impact of quantitative easing on long-run inflation?"
3
Watch the agents run
Six agent cards appear in real time: Query Analyst → Academic Search + Web Research (parallel) → Analysis Agent → Writing Agent → Validation Agent.
4
Get your validated report
The final output is a structured markdown report with inline citations drawn only from real, verified papers. No hallucinated references.
65 credits per run
🗂️
NEWMarch 2026

Research Workspace

A unified project space where you can run all research tools — Literature Review, Paper Audit, Peer Review, Reference Check — inside a single organised session, with results saved to one project.

How to use it

1
Open the Workspace
Navigate to /workspace or click "Workspace" in the sidebar tools section.
2
Create or open a project
Name your project (e.g. "PhD Chapter 3 — Methodology"). All tools you run inside it are saved to that project automatically.
3
Run tools in context
Use the Literature Review, Audit, Peer Review, or Reference tools from inside the workspace. Results are linked to your project.
4
Export or share
Download a full project report as PDF, or copy individual outputs. Your work is saved to your account history.

Recent Updates

Bigger Chat Fonts & Better Loading Experience

April 2026

Chat text is now larger and easier to read (16px body, improved heading hierarchy). The loading state has been completely redesigned — a pulsing card with a live progress bar and phase descriptions so you always know what ResearchBuddy is doing while it works.

🎯

Auto-Focus on Every Tool Page

April 2026

When you open Peer Review, Prompt Coach, Paper Audit, or Upload Draft, the input area is now automatically focused and scrolled into view — no extra clicks to get started.

🔬

Domain-Aware Deep Audit

February 2026

The Audit engine now detects your paper's domain and applies the right methodology rubric automatically. Econometrics papers get checked for OLS assumptions, heteroskedasticity, unit roots, and cointegration. Medical papers follow CONSORT/PRISMA. ML papers are validated against SOTA benchmarks and ablation requirements.

Triple-Model Cross-Validation

February 2026

Deep Audit now runs three independent models — OpenAI o4-mini, Claude Sonnet 4.6, and Gemini 2.5 Flash — in parallel, then averages their scores. A finding only makes it into your report if multiple models agree. Fewer false positives, higher confidence.

📚

Real Reference Verification

January 2026

References are now verified against CrossRef and Semantic Scholar APIs in real time. You get the DOI, journal, citation count, and publication year for every paper cited — not just a title the AI made up.

🎨

Full Dark / Light Theme

January 2026

The entire app now respects your theme preference consistently — including all inner pages (Audit, Peer Review, Uploads, History). Toggle from your profile in the sidebar.

📄

AI Peer Review

December 2025

Upload your paper and get structured reviewer feedback — Abstract clarity, Introduction framing, Methodology rigour, Results interpretation, and Discussion depth — formatted as a standard journal peer review.

🚀

Ready to try it?

Run a Literature Review to see the Argument Heat Map in action, or try Agent Mode for a full automated research run.