ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
Summary
ActReview is a rebuttal-guided post-training framework that generates diagnostic claims and revision suggestions for peer reviews by leveraging author responses as supervision, along with a human-curated benchmark for evaluation.
View Cached Full Text
Cached at: 09/11/26, 06:19 PM
Paper page - ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
Source: https://huggingface.co/papers/2609.09076
Abstract
ActReview is a rebuttal-guided post-training framework that generates diagnostic claims and concrete revision suggestions for peer review by leveraging author responses as latent supervision.
As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revisions. We study this asActionable Peer-review Generationand decompose it into two subtasks:diagnostic claim generationandrevision suggestion generation. We introduceActReview, arebuttal-guided post-trainingframework that connects paper-specific diagnoses to concrete, grounded revision plans. Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback. From real review-rebuttal threads on OpenReview, we constructActReview-40Kby aligning reviewer weaknesses with author responses and grounding the resulting feedback in localized paper evidence. We post-train Qwen3-8B-Base withmulti-task supervised fine-tuningfollowed byGRPOusing candidate-aware, weakness-specific rubric rewards. We also introduceActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness. Experiments show thatActReviewoutperforms prior specialized review-generation models on actionability and grounding while remaining competitive with strong prompt-based LLMs. Human evaluation confirms improved revision usefulness while revealing a remaining gap in technical accuracy, and additional analyses support generalization to held-out papers and robustness across independent judges.
View arXiv pageView PDFGitHub0Add to collection
Get this paper in your agent:
hf papers read 2609\.09076
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.09076 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.09076 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.09076 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review
Introduces RubricReviewer, a rubric-driven framework for LLM-based peer review that explicitly generates paper-adaptive rubrics and combines a training-free evidence-gathering agent (Scout) with a trained human-aligned model (Aligner) to produce more comprehensive, discriminative, and robust reviews.
Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review
This paper introduces the Re3Align dataset, REspGen framework, and REspEval evaluation suite for author-in-the-loop response generation in peer review, integrating author expertise and intent signals. The work addresses gaps in NLP formulation of scientific rebuttal writing with comprehensive datasets, controllable generation frameworks, and multi-dimensional evaluation metrics.
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
Co-ReAct introduces a rubric-guided action-selection framework that uses rubrics as step-level guidance during inference for ReAct agents, improving trajectory quality and outperforming baselines on DeepResearchBench and SQA-CS-V2.
InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
This paper presents InternReviewer and InternAdvocate, a framework for developing AI agents in academic peer review and rebuttal using agentic reinforcement learning with objective rewards to improve reasoning depth, citation accuracy, and reduce hallucinations.
Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
This paper introduces Adversarial Review (AR), a minimal cooperative protocol for agentic code review that uses structured disagreement to improve performance on repository-level coding tasks, outperforming baselines with fewer agents on benchmarks like LiveCodeBench and SWE-bench.