Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions

TL;DR

This paper introduces a multimodal, community-aware peer review simulation system that leverages multimodal LLMs and retrieval-augmented generation to provide structured, actionable feedback for manuscript revisions, improving review quality and transparency.

Contribution

The work presents a novel interactive web-based system integrating multimodal LLMs, retrieval-augmented generation, and actionable to-do lists to enhance peer review and manuscript revision processes.

Findings

Generated reviews are more comprehensive and useful.

System surpasses baseline methods in review quality.

Enhances transparency and traceability in peer review.

Abstract

While large language models (LLMs) offer promising capabilities for automating academic workflows, existing systems for academic peer review remain constrained by text-only inputs, limited contextual grounding, and a lack of actionable feedback. In this work, we present an interactive web-based system for multimodal, community-aware peer review simulation to enable effective manuscript revisions before paper submission. Our framework integrates textual and visual information through multimodal LLMs, enhances review quality via retrieval-augmented generation (RAG) grounded in web-scale OpenReview data, and converts generated reviews into actionable to-do lists using the proposed Action:Objective[\#] format, providing structured and traceable guidance. The system integrates seamlessly into existing academic writing platforms, providing interactive interfaces for real-time feedback and revision tracking. Experimental results highlight the effectiveness of the proposed system in generating more comprehensive and useful reviews aligned with expert standards, surpassing ablated baselines and advancing transparent, human-centered scholarly assistance.