# ReviewRL: Towards Automated Scientific Review with RL

arXiv: https://arxiv.org/abs/2508.10308 · HTML: https://mlsanity.com/paper/2508.10308/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://mlsanity.com/paper/1804.09635/) (2018)
- [JudgeLRM: Large Reasoning Models as a Judge](https://mlsanity.com/paper/2504.00050/) (2025)
- [NLPeer: A Unified Resource for the Computational Study of Peer Review](https://mlsanity.com/paper/2211.06651/) (2022)
- [Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation](https://mlsanity.com/paper/2407.08940/) (2024)
- [Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards](https://mlsanity.com/paper/2505.04966/) (2025)
- [ReviewEval: An Evaluation Framework for AI-Generated Reviews](https://mlsanity.com/paper/2502.11736/) (2025)
- [Agent models: Internalizing Chain-of-Action Generation into Reasoning models](https://mlsanity.com/paper/2503.06580/) (2025)
- [Reviewing Scientific Papers for Critical Problems With Reasoning LLMs: Baseline Approaches and Automatic Evaluation](https://mlsanity.com/paper/2505.23824/) (2025)

## Built on by (most cited first, 19 of 19)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists](https://mlsanity.com/paper/2511.16931/) (2025)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future](https://mlsanity.com/paper/2604.27924/) (2026)
- [ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review](https://mlsanity.com/paper/2601.22638/) (2026)
- [LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers](https://mlsanity.com/paper/2605.25415/) (2026)
- [Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism](https://mlsanity.com/paper/2510.15600/) (2025)
- [APRES: An Agentic Paper Revision and Evaluation System](https://mlsanity.com/paper/2603.03142/) (2026)
- [PaperGym: Rubric-Centered Evolution for Research-Plan Generation](https://mlsanity.com/paper/2608.31119/) (2026)
- [From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation](https://mlsanity.com/paper/2603.17588/) (2026)
- [No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions](https://mlsanity.com/paper/2606.13044/) (2026)
- [RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review](https://mlsanity.com/paper/2608.00005/) (2026)
- [MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment](https://mlsanity.com/paper/2603.20884/) (2026)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [Beyond Detection: Governing GenAI in Academic Peer Review as a Sociotechnical Challenge](https://mlsanity.com/paper/2603.20214/) (2026)
- [GraphReview: Scientific Paper Evaluation via LLM-based Graph Evidence Expansion](https://mlsanity.com/paper/2605.27204/) (2026)
- [From peer review nuances to best practices](https://mlsanity.com/paper/2607.22681/) (2026)
- [InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal](https://mlsanity.com/paper/2608.28612/) (2026)
- [IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation](https://mlsanity.com/paper/2610.04074/) (2026)

## Abstract (arXiv)

Peer review is essential for scientific progress but faces growing challenges due to increasing submission volumes and reviewer fatigue. Existing automated review approaches struggle with factual accuracy, rating consistency, and analytical depth, often generating superficial or generic feedback lacking the insights characteristic of high-quality human reviews. We introduce ReviewRL, a reinforcement learning framework for generating comprehensive and factually grounded scientific paper reviews. Our approach combines: (1) an ArXiv-MCP retrieval-augmented context generation pipeline that incorporates relevant scientific literature, (2) supervised fine-tuning that establishes foundational reviewing capabilities, and (3) a reinforcement learning procedure with a composite reward function that jointly enhances review quality and rating accuracy. Experiments on ICLR 2025 papers demonstrate that ReviewRL significantly outperforms existing methods across both rule-based metrics and model-based quality assessments. ReviewRL establishes a foundational framework for RL-driven automatic critique generation in scientific discovery, demonstrating promising potential for future development in this domain. The implementation of ReviewRL will be released at GitHub.