Tag
This PNAS study of 7.3 million academic papers finds that by 2025, over half show LLM influence, with significant inequality in adoption across lower-prestige and non-English institutions.
Prompt-to-Paper is a multi-stage multi-agent AI framework for automated bioinformatics manuscript generation that uses deterministic retrieval-augmented generation, an autonomous coding agent for real experiments, and an eight-dimensional quality scorer to produce submission-formatted PDFs at low cost, with validated quality improvements.
Introduce 5 Codex Skills to improve research efficiency, including paper framework construction, image to PPT conversion, scientific diagram editing, academic writing assistance, and learning high-level paper structures, emphasizing turning repetitive processes into reusable skills.
This paper examines how estimates of AI use in scientific writing can be biased when evaluation methods ignore contextual differences across countries and fields, and proposes context-aware benchmarks for more accurate measurement.
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.