Researchers propose Prompt-to-Paper, an agentic AI system for automating bioinformatics manuscript generation

A new arXiv preprint introduces Prompt-to-Paper, a multi-agent framework designed to automate manuscript generation in bioinformatics while addressing three documented deficiencies in prior systems: unverifiable claims, fabricated experimental results, and the lack of standardized quality assessment frameworks.

The system integrates three core components: a deterministic retrieval-augmented generation pipeline that grounds every claim in a verifiable corpus of 60–100 papers using section-aware relevance scoring and snowball citation expansion; an autonomous coding agent that executes real computational biology experiments to replace synthetic outputs with genuine numerical results; and an eight-dimensional automated quality scorer benchmarked against approximate reference statistics from published papers, with explicit hallucination penalties.

A quality-driven improvement loop uses a context-rich reviser to route iterations to one of three researcher actions and triggers a deep research cycle every ten iterations to re-run experiments and regenerate manuscripts from stronger outputs. In validation on five bioinformatics case studies, the system compiled submission-formatted PDFs with zero out-of-range citations. The improvement loop increased manuscript quality by an average of +17.96 points on a 0–100 scale, with a maximum improvement of +26.04 points.

As partial external validation, a human reviewer scored the five generated manuscripts at an average of 7.0 out of 10. The system produced complete manuscripts at an estimated cost of approximately 0.31 USD per paper.