scientific-writing

CoAuthorAI is a human-in-the-loop system that combines retrieval-augmented generation and hierarchical outlines to enable accurate, coherent scientific book writing, achieving 98% recall and 82% human satisfaction in evaluations.

This paper proposes SciRM, cost-efficient open-source reward models tailored for evaluating scientific writing through a two-stage training framework that optimizes evaluation preferences and reasoning capabilities. The models generalize across diverse scientific writing tasks without requiring task-specific retraining, addressing limitations of existing LLM-based judges on domain-specific evaluation criteria.

OpenAI introduces Prism, a free AI-native workspace for scientific writing and collaboration powered by GPT-5.2, integrating advanced mathematical reasoning directly into a LaTeX-native environment to streamline research workflows.