Blog
From the Agent Bayes team
Product updates, research workflows, and how we think about building tools you can actually trust with your literature.

Confidential AI peer review before submission: what tools miss and wrongly flag
Choose an AI tool for confidential pre-submission peer review, then check its findings and look for omissions before sending your paper to a journal.
Guy Zana
November 13, 2026 · 5 min read

Do I still need a reference manager when AI finds the papers?
A reference manager keeps the sources AI finds organized and ready to cite. Check each claim against the paper before relying on it.
Guy Zana
November 11, 2026 · 4 min read

Hallucinated citations: arXiv's one-year ban, the misconduct debate, and what reference checks miss
arXiv bans authors for a year over unchecked AI references, and a Nature correspondence calls hallucinated citations misconduct. A reference check catches fake papers. It misses real papers cited for claims they never made.
Guy Zana
November 9, 2026 · 5 min read

ChatGPT deep research vs dedicated academic research agents: what AstaBench measured
ChatGPT deep research vs dedicated academic research agents: a 2025 benchmark compared their cited answers to computer science questions. Learn what the scores mean for checking sources.
Guy Zana
November 7, 2026 · 5 min read

AI vs human peer review: AI caught more planted errors, and still needs checking
AI models scored 53% to 96% at detecting planted major errors, against 27% for untrained human reviewers, and editors preferred AI reviews 26 of 30 times. What that means for checking your own paper.
Guy Zana
November 5, 2026 · 6 min read

Undermind vs Agent Bayes: one finds the papers, the other shows the page
In its own test, Undermind found 73% of the relevant papers in 10 minutes. Agent Bayes cites each claim to the passage and the page number printed on the article, then checks your wording against it. What each one is for, task by task.
Guy Zana
November 4, 2026 · 8 min read

Zotero AI tools: which read your PDFs and which only see titles and abstracts
Litmaps syncs records but not PDFs, SciSpace skips papers without a DOI, Elicit imports once. 16 Zotero AI tools compared by what they read and where their citations take you.
Guy Zana
November 3, 2026 · 8 min read

Journal page number or PDF page number: how Agent Bayes keeps both
Journal page number or PDF page number? A citation needs the published label, while a PDF reader needs the file position. Agent Bayes stores both and uses neighbouring pages to infer missing labels.
Guy Zana
November 1, 2026 · 7 min read

How to check if a citation supports a claim
A real paper can still be the wrong source for a sentence. To check if a citation supports a claim, compare the wording with the cited passage, including its limits.
Guy Zana
October 31, 2026 · 6 min read

How accurate are AI research assistants? Agent Bayes on three public benchmarks
How accurate is an AI research assistant that answers from your papers? Agent Bayes beat every published result on IRPAPERS, gave zero wrong answers on LitQA2, and scored 5 of 5 for factual correctness on ResearchQA.
Guy Zana
October 28, 2026 · 4 min read

Using AI to peer review a paper: a page-cited referee report in three minutes
An AI referee report is only useful if every concern points to a page you can check. On a 25-page randomized experiment, Agent Bayes wrote one in under three minutes, with page-cited major concerns. You still verify, rank, and follow the journal's rules.
Guy Zana
October 22, 2026 · 5 min read

AI peer review: check every claim against its sources
What the AI peer review feature in Agent Bayes does, how it works, and how we tested it: we planted seven citation mistakes in a short draft and checked every claim against the cited papers. The check caught all seven.
Guy Zana
October 22, 2026 · 6 min read

Gemini 4 Argon or Claude Opus 5.5 for academic research writing?
Claude Opus 5.5 kept 75% of its cited claims fully inside the source. Gemini 4 Argon kept 31%, at under half the cost per task until November 30. We judged both blind on five research questions and a 10-page essay.
Guy Zana
October 14, 2026 · 18 min read

GPT-6.1 Sol, GPT-6 Astra, or Claude Opus 5.5 for cited research?
We gave three models the same five research questions three times each and judged 540 cited claims blind. Opus cites the most sources but drops the sources' hedges more often. Sol stays as close to its sources as Astra at a fifth of the cost.
Guy Zana
October 7, 2026 · 9 min read

Why research may matter more as AI makes software cheap to build
AI made familiar software cheap to build. A startup that wants to stand out may need new knowledge, and the tools to produce it are changing: agents that run research at scale.
Guy Zana
October 5, 2026 · 4 min read

Connect Claude Code to your indexed papers, figures included
The Agent Bayes MCP server lets Claude Code or any MCP client search your papers, get cited answers, and build mindmaps. It can now also look at PDF pages and the images on mindmap nodes, so maps and charts are no longer blind spots.
Guy Zana
September 25, 2026 · 7 min read

Gemini 3.8 Flash, GPT-5.4, or GPT-5.6 Terra for cited research synthesis?
We benchmarked Gemini 3.8 Flash, GPT-5.4, and GPT-5.6 Terra on citation-grounded synthesis over 150 indexed archaeology papers. Gemini weaves twice as many sources into each paragraph as Terra, and Terra's sentences stay closest to what the cited passage states. GPT-5.4 sits between them at two to three times the cost.
Guy Zana
September 8, 2026 · 12 min read

Most AI research tools are not competing with each other
We compared thirteen of them. The useful split is not which one is smartest. It is what corpus each tool reads, what its citations point at, and what you are left holding when you close the tab.
Guy Zana
August 3, 2026 · 9 min read

Evidence matrix template and example for a literature review
An evidence matrix puts your sources in rows and your themes in columns, with a page reference in every cell. Copy the blank template and see one filled in.
Guy Zana
August 2, 2026 · 14 min read

We gave our research agent a glossary it builds from your papers, not the dictionary
Domain terms are local and overloaded. A small terminology graph gives a research agent an inspectable, corpus-relative glossary: top supporting passages and neighboring concepts, as evidence to reason over, not a canned definition to paste.
Guy Zana
August 1, 2026 · 9 min read

Our Customers Now Get 3x More Indexed Papers, for the Same Price
We moved the pipeline that reads and indexes your PDFs to OpenAI's gpt-5.6-luna. Indexing costs about 60% less, runs in under half the time, and we measured it against our own evaluation loop before shipping to make sure nothing got worse.
Guy Zana
July 31, 2026 · 2 min read

GraphRAG uses five LLM indexing stages. We use one extraction pass.
One LLM pass extracts scholarly terms and scores how informative each passage is. LLM-reconstructed semantic chunks make co-occurrences less noisy, while agents resolve meaning from evidence at query time and no glossary definition is committed.
Guy Zana
July 15, 2026 · 13 min read

Imposter syndrome in academia: what the research says, and where our AI misread it
A citation-backed tour of what the research actually says about imposter syndrome in academia: how common it is, whether it is even a real condition, and the one place our AI research assistant got a citation wrong while mapping the literature.
Guy Zana
July 5, 2026 · 7 min read

AI should help researchers think deeper, not think less
The useful role for AI in research is not replacing judgment. It is helping a human stay immersed in a problem, keep evidence and disagreement visible, and build knowledge that compounds over time.
Guy Zana
July 2, 2026 · 11 min read

Token accounting and cancellation in durable agent workflows
Closing an LLM stream is not the same as stopping the work behind it. Durable agents need cancellation paths that settle application state and credit accounting before the UI declares victory.
Guy Zana
July 2, 2026 · 9 min read

Introducing Agent Bayes: research you can actually trust
Why we built a multi-agent research assistant around a shared, citation-backed mindmap, and how it fixes what generic chatbots get wrong about working with literature.
Guy Zana
July 1, 2026 · 8 min read