DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weng, Yixuan, Zhu, Minjun, Xie, Qiujie, Ning, Zhiyuan, Li, Shichen, Lu, Panzhong, Lin, Zhen, Gu, Enhao, Sun, Qiyao, Zhang, Yue
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911583921242112
author Weng, Yixuan
Zhu, Minjun
Xie, Qiujie
Ning, Zhiyuan
Li, Shichen
Lu, Panzhong
Lin, Zhen
Gu, Enhao
Sun, Qiyao
Zhang, Yue
author_facet Weng, Yixuan
Zhu, Minjun
Xie, Qiujie
Ning, Zhiyuan
Li, Shichen
Lu, Panzhong
Lin, Zhen
Gu, Enhao
Sun, Qiyao
Zhang, Yue
contents Automated peer review is often framed as generating fluent critique, yet reviewers and area chairs need judgments they can \emph{audit}: where a concern applies, what evidence supports it, and what concrete follow-up is required. DeepReviewer~2.0 is a process-controlled agentic review system built around an output contract: it produces a \textbf{traceable review package} with anchored annotations, localized evidence, and executable follow-up actions, and it exports only after meeting minimum traceability and coverage budgets. Concretely, it first builds a manuscript-only claim--evidence--risk ledger and verification agenda, then performs agenda-driven retrieval and writes anchored critiques under an export gate. On 134 ICLR~2025 submissions under three fixed protocols, an \emph{un-finetuned 196B} model running DeepReviewer~2.0 outperforms Gemini-3.1-Pro-preview, improving strict major-issue coverage (37.26\% vs.\ 23.57\%) and winning 71.63\% of micro-averaged blind comparisons against a human review committee, while ranking first among automatic systems in our pool. We position DeepReviewer~2.0 as an assistive tool rather than a decision proxy, and note remaining gaps such as ethics-sensitive checks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09590
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review
Weng, Yixuan
Zhu, Minjun
Xie, Qiujie
Ning, Zhiyuan
Li, Shichen
Lu, Panzhong
Lin, Zhen
Gu, Enhao
Sun, Qiyao
Zhang, Yue
Artificial Intelligence
Computation and Language
Computers and Society
Automated peer review is often framed as generating fluent critique, yet reviewers and area chairs need judgments they can \emph{audit}: where a concern applies, what evidence supports it, and what concrete follow-up is required. DeepReviewer~2.0 is a process-controlled agentic review system built around an output contract: it produces a \textbf{traceable review package} with anchored annotations, localized evidence, and executable follow-up actions, and it exports only after meeting minimum traceability and coverage budgets. Concretely, it first builds a manuscript-only claim--evidence--risk ledger and verification agenda, then performs agenda-driven retrieval and writes anchored critiques under an export gate. On 134 ICLR~2025 submissions under three fixed protocols, an \emph{un-finetuned 196B} model running DeepReviewer~2.0 outperforms Gemini-3.1-Pro-preview, improving strict major-issue coverage (37.26\% vs.\ 23.57\%) and winning 71.63\% of micro-averaged blind comparisons against a human review committee, while ranking first among automatic systems in our pool. We position DeepReviewer~2.0 as an assistive tool rather than a decision proxy, and note remaining gaps such as ethics-sensitive checks.
title DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review
topic Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2604.09590