OpenAcademicPaperGen: Open Multi-Agent Tool That Verifies Citations Against Full Text
量子位 · wechat · 2026-10-10
A new GitHub project, OpenAcademicPaperGen, is a multi-agent workflow for drafting academic papers, splitting the process into nine stages: scoping, literature search across OpenAlex/Crossref/SemanticScholar/arXiv, dedup and filtering, trend analysis, angle selection, outline, writing, verification, and export to Markdown/LaTeX with BibTeX.
Its standout feature is citation verification: with full text available, it locates the relevant passages and judges whether the source actually supports the claim, annotating the corresponding PDF page — checking not just that a paper exists, but that it really says what's cited. Three checks cover pool membership, DOI identity via Crossref/doi.org, and passage-level support; insufficient evidence is marked 'undetermined' rather than passed. A 'novelty diagnosis' stage flags the closest prior work and simulates reviewer objections. Supports OpenAI and Zhipu GLM, though verification and mock review require an OpenAI API key. Built by solo developer 'Maoshu'.
More from coding & agent
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23
- New data marketplace lets vendors list repos; coding agents access via MCP server — testingcatalog · 2026-10-23
- Tie code approvals to content hashes so agent 'one more small fix' voids review — Ambitious_Answer6857 · 2026-10-23