AI/ ai · peer-review · research · llm

RebuttalAgent Aims to Fix AI-Assisted Peer Review Responses

A multi-agent system called RebuttalAgent breaks reviewer feedback into discrete concerns and anchors every reply in traceable evidence before drafting.

An AI framework built for academic peer review wants to stop language models from making things up when authors write rebuttals.

The system, called RebuttalAgent, is the core contribution of a paper titled Paper2Rebuttal. Rather than feeding a reviewer's comments directly into a model and hoping for the best, RebuttalAgent decomposes complex feedback into individual concerns, then builds evidence before writing a single word. It pulls from compressed summaries and high-fidelity excerpts of the original manuscript, and can reach out to external literature when a reviewer's point requires outside support. A response plan is generated and inspected before any prose is drafted — meaning a human can see the reasoning chain, not just the output.

The distinction matters because hallucination is a known failure mode when LLMs handle dense, citation-heavy academic text. Existing tools tend to treat rebuttal writing as a text-completion task, which is exactly where models confidently fabricate supporting evidence. An evidence-first architecture at least makes the fabrication easier to catch.

The authors tested RebuttalAgent against a benchmark they also built — RebuttalBench — and report gains in coverage, faithfulness, and what they call strategic coherence. Self-reported benchmarks on self-built datasets are a peer-review tradition in their own right, so independent validation would be a more convincing next step.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →