# From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

arXiv: https://arxiv.org/abs/2606.13349 · HTML: https://mlsanity.com/paper/2606.13349/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review](https://mlsanity.com/paper/2412.01708/) (2024)
- [GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study](https://mlsanity.com/paper/2307.05492/) (2023)
- [AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot](https://mlsanity.com/paper/2604.13940/) (2026)
- [ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review](https://mlsanity.com/paper/2510.08867/) (2025)
- [Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review](https://mlsanity.com/paper/2502.12510/) (2025)
- [Reviewer2: Optimizing Review Generation Through Prompt Generation](https://mlsanity.com/paper/2402.10886/) (2024)
- [DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review](https://mlsanity.com/paper/2604.09590/) (2026)
- [ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review](https://mlsanity.com/paper/2601.22638/) (2026)

## Built on by (most cited first, 4 of 4)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [More Criticism Does Not Make a Better Review: EquiReview-R](https://mlsanity.com/paper/2609.03943/) (2026)
- [A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review](https://mlsanity.com/paper/2609.39027/) (2026)

## Abstract (arXiv)

Effective peer review requires adaptive investigation that responds to evidence emerging from each paper. Existing LLM-based reviewers largely organize the review process around predefined workflows, leaving limited scope for emerging evidence to reshape investigation. We propose ProReviewer, an evidence-driven review agent that formulates reviewing as a Markov Decision Process, with a structured review log forming the core of its state. At each step, the agent uses accumulated findings to decide what to inspect next and when to conclude. As new evidence emerges, it updates the log by revising claim statuses, resolving open questions, and recording new findings. Each point in the final review cites supporting log entries, making its judgments traceable to the recorded evidence. On 1,000 held-out ICLR 2026 papers, the trained 8B ProReviewer achieves the highest average score among all compared methods, including those built on a 397B model; human evaluators prefer its reviews over all baselines on three of four review-quality dimensions.