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

2026-01-20

AI Summary

This work addresses the limitations of existing rebuttal generation methods, which often suffer from hallucination, neglect of reviewer concerns, or insufficient verifiable grounding. To overcome these issues, the authors propose RebuttalAgent—the first multi-agent framework specifically designed for rebuttal generation—reformulating the task as an evidence-driven planning process. The approach decomposes reviewer comments into atomic claims, constructs a hybrid context by integrating compressed summaries with high-fidelity source text, and incorporates on-demand external literature retrieval. It first generates an auditable response plan before drafting the final reply. Evaluated on the newly introduced RebuttalBench benchmark, RebuttalAgent significantly outperforms strong baselines in coverage, faithfulness, and strategic coherence, offering a traceable, verifiable, and controllable assistant for author responses.

Technology Category

• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• rebuttal generation
• hallucination
• reviewer feedback
• evidence grounding
• peer review

Innovation

• multi-agent framework
• evidence-centric planning
• rebuttal generation
• external search module
• response plan