Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

TL;DR

This paper introduces RebuttalAgent, a multi-agent system that improves rebuttal generation for peer reviews by decomposing feedback, synthesizing evidence, and ensuring transparent, evidence-based responses, outperforming existing methods.

Contribution

The paper presents the first multi-agent framework for rebuttal generation that emphasizes evidence-centric planning and external knowledge integration, enhancing transparency and accuracy.

Findings

Outperforms baselines in coverage, faithfulness, and coherence

Decomposes feedback into atomic concerns for precise responses

Incorporates external search to resolve outside literature concerns

Abstract

Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text generation problem, suffering from hallucination, overlooked critiques, and a lack of verifiable grounding. To address these limitations, we introduce $\textbf{RebuttalAgent}$, the first multi-agents framework that reframes rebuttal generation as an evidence-centric planning task. Our system decomposes complex feedback into atomic concerns and dynamically constructs hybrid contexts by synthesizing compressed summaries with high-fidelity text while integrating an autonomous and on-demand external search module to resolve concerns requiring outside literature. By generating an inspectable response plan before drafting, $\textbf{RebuttalAgent}$ ensures that every argument is explicitly anchored in internal or external evidence. We validate our approach on the proposed $\textbf{RebuttalBench}$ and demonstrate that our pipeline outperforms strong baselines in coverage, faithfulness, and strategic coherence, offering a transparent and controllable assistant for the peer review process. Code will be released.