DeepReviewer 2.0：一个可追溯的代理系统用于可审计的科学同行评审
DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review
AI总结：
DeepReviewer 2.0通过可追溯的审查包和可执行的后续行动，提升同行评审的可审计性，其在134个提交中优于人类评审和现有自动系统。
摘要：
自动化同行评审常被描述为生成流畅的批评，但评审员和领域主席需要能够审计的判断：何处存在关切，有何证据支持，以及需要哪些具体后续行动。DeepReviewer 2.0是一种过程受控的代理评审系统，围绕输出合同构建：它生成一个可追溯的审查包，包含锚定注释、本地化证据和可执行的后续行动，并在满足最低可追溯性和覆盖预算后导出。具体而言，它首先构建仅包含手稿的主张-证据-风险账簿和验证议程，然后在议程驱动下进行检索，并在导出门下编写锚定批评。在134个ICLR 2025提交中，未经微调的196B模型运行DeepReviewer 2.0在严格的主要问题覆盖度（37.26% vs. 23.57%）和71.63%的微平均盲比较中胜过人类评审委员会，同时在我们的池中自动系统中排名第一。我们将DeepReviewer 2.0定位为辅助工具而非决策代理，并指出仍需解决的伦理敏感检查等不足。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
