Abstract
Recent advances in large language models have enabled automated manuscript generation; however, existing systems suffer from three critical deficiencies:
- Generated claims are not deterministically grounded in verifiable literature;
- Experimental results are frequently fabricated rather than executed;
- There exists no standardized, multi-dimensional framework to assess whether AI-generated manuscripts meet the quality and rigor required for real-world publication.
We present Prompt-to-Paper, a multi-agent framework that directly addresses this evaluation gap through three integrated innovations:
-
Deterministic retrieval-augmented generation pipeline: This grounds every claim in a verifiable corpus of 60-100 papers using section-aware relevance scoring and snowball citation expansion.
-
Autonomous coding agent: This executes real computational biology experiments, replacing synthetic outputs with genuine numerical results.
-
Eight-dimensional automated quality scorer: This is benchmarked with approximate reference statistics from published papers and augmented with explicit hallucination penalties, providing standardized, reproducible quality assessments.
The quality-driven improvement loop utilizes a context-rich reviser that routes each iteration to one of three researcher actions and triggers a deep research cycle every ten iterations to re-run experiments and re-manuscript from stronger outputs.
We validate the system on five bioinformatics case studies; all five cases compiled submission-formatted PDFs with zero out-of-range citations. The improvement loop raises manuscript quality by an average of +17.96 points on a 0-100 scale (maximum +26.04). As partial external checks, a human reviewer scored the five manuscripts at an average of 7.0 out of 10. Complete manuscripts are produced at approximately 0.31 USD per paper.
Blogger's Review: The Prompt-to-Paper system addresses the critical quality issues of AI-generated manuscripts in bioinformatics through its innovative multi-agent framework. Its unique quality scoring mechanism and genuine experimental execution capabilities provide robust support for future research, enhancing the credibility of manuscripts and opening new possibilities for academic publishing.