20260212.0001v1Application
CSPaper Review: Fast, Rubric-Faithful Conference Feedback
Lele Cao, Lei You, Kai Xie, Weiping Ding, Yong Du, Sven Salmonsson, Yumin Zhou, Vilhelm von Ehrenheim
Abstract
CSPaper Review (CSPR) is a free, AI-powered tool for rapid, conference-specific peer review in Computer Science (CS). Addressing the bottlenecks of slow, inconsistent, and generic feedback in existing solutions, CSPR leverages Large Language Models (LLMs) agents and tailored workflows to deliver realistic and actionable reviews within one minute. In merely four weeks, it served more than 7,000 unique users from 80 countries and processed over 15,000 reviews, highlighting a strong demand from the CS community. We present our architecture, design choices, benchmarks, user analytics and future road maps.
Keywords
AI-assisted peer reviewconference paper reviewlarge language modelsrubric-aligned evaluationautomated feedback generationhuman-AI collaborationresearch benchmarkingcomputer science conferences
Citation
@article{Cao2025CSPaper,
title={CSPaper Review: Fast, Rubric-Faithful Conference Feedback},
author={Lele Cao and Lei You and Kai Xie and Weiping Ding and Yong Du and Sven Salmonsson and Yumin Zhou and Vilhelm von Ehrenheim},
year={2025},
url={https://cspaper.org/openprint/20260212.0001v1},
journal={OpenPrint:20260212.0001v1}
}Version History
| Version | Submitted On |
|---|---|
| v1Current | October 1, 2025 |