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

arXiv: https://arxiv.org/abs/2604.09590 · HTML: https://mlsanity.com/paper/2604.09590/

## Key facts

- Cited by 7 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 22 of its 28 references that are in the map.
- First posted on arXiv 3 Mar 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, 22 of 22)

- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution](https://mlsanity.com/paper/2509.19349/) (2025)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs](https://mlsanity.com/paper/2411.14199/) (2024)
- [Can We Automate Scientific Reviewing?](https://mlsanity.com/paper/2102.00176/) (2021)
- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review](https://mlsanity.com/paper/2412.01708/) (2024)
- [ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews](https://mlsanity.com/paper/2503.08506/) (2025)
- [PRE: A Peer Review Based Large Language Model Evaluator](https://mlsanity.com/paper/2401.15641/) (2024)
- [ReviewEval: An Evaluation Framework for AI-Generated Reviews](https://mlsanity.com/paper/2502.11736/) (2025)
- [A review on the novelty measurements of academic papers](https://mlsanity.com/paper/2501.17456/) (2025)
- [Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers](https://mlsanity.com/paper/2509.19326/) (2025)
- [Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper](https://mlsanity.com/paper/2511.04583/) (2025)
- [UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation](https://mlsanity.com/paper/2503.14941/) (2025)
- [Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models](https://mlsanity.com/paper/2512.22145/) (2025)
- [ReAct: A Review Comment Dataset for Actionability (and more)](https://mlsanity.com/paper/2210.00443/) (2022)
- [SPHERE: Scaling Personalized Feedback in Programming Classrooms with Structured Review of LLM Outputs](https://mlsanity.com/paper/2410.16513/) (2024)
- [ILCiteR: Evidence-grounded Interpretable Local Citation Recommendation](https://mlsanity.com/paper/2403.08737/) (2024)
- [A Semi-automated Peer-review System](https://mlsanity.com/paper/1311.2504/) (2013)
- [Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles](https://mlsanity.com/paper/2410.04202/) (2024)

## Built on by (most cited first, 7 of 7)

- [From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent](https://mlsanity.com/paper/2606.13349/) (2026)
- [RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review](https://mlsanity.com/paper/2608.00005/) (2026)
- [EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation](https://mlsanity.com/paper/2606.06025/) (2026)
- [Uncertainty-Aware Generation and Decision-Making Under Ambiguity](https://mlsanity.com/paper/2606.30578/) (2026)
- [ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs](https://mlsanity.com/paper/2608.12788/) (2026)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [AppliedScientist: Automated Scientific Revision Through Iterative AI Reviewing](https://mlsanity.com/paper/2609.14738/) (2026)

## Abstract (arXiv)

Automated peer review is often framed as generating fluent critique, yet reviewers and area chairs need judgments they can 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 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 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.