What problem does it solve?
Turning research results into a submission-ready academic paper requires coordinating outlining, figure generation, LaTeX writing, compilation, and iterative review, which is slow and error-prone when done manually.
Core Features & Use Cases
- End-to-End Pipeline Orchestration: Chains paper-plan, paper-figure, paper-write, paper-compile, and an auto-improvement loop into one automated workflow.
- Venue-Aware Output: Supports ICLR, NeurIPS, ICML, CVPR, ACL, AAAI, ACM, and IEEE journal/conference formats with page-limit and citation-style handling.
- Automated Review Loop: Runs two GPT-5.4 review-and-fix rounds, producing round-by-round PDFs and an improvement log.
- Use Case: Given a NARRATIVE_REPORT.md with claims, experiments, and results, generate a polished, compiled paper PDF with figures, bibliography, and review-driven revisions ready for submission.
Quick Start
Run the paper writing pipeline on my NARRATIVE_REPORT.md targeting ICLR and produce the final compiled PDF.