# EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation

arXiv: https://arxiv.org/abs/2606.06025 · HTML: https://mlsanity.com/paper/2606.06025/

## Key facts

- Cited by 1 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 20 of its 32 references that are in the map.
- First posted on arXiv 4 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, 20 of 20)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [Large language models for automated scholarly paper review: A survey](https://mlsanity.com/paper/2501.10326/) (2025)
- [Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions](https://mlsanity.com/paper/2406.05688/) (2024)
- [MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models](https://mlsanity.com/paper/2402.01620/) (2024)
- [GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study](https://mlsanity.com/paper/2307.05492/) (2023)
- [Automated Focused Feedback Generation for Scientific Writing Assistance](https://mlsanity.com/paper/2405.20477/) (2024)
- [TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review](https://mlsanity.com/paper/2506.07642/) (2025)
- [Paper Matching with Local Fairness Constraints](https://mlsanity.com/paper/1905.11924/) (2019)
- [AAAR-1.0: Assessing AI's Potential to Assist Research](https://mlsanity.com/paper/2410.22394/) (2024)
- [Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach](https://mlsanity.com/paper/2211.06398/) (2022)
- [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://mlsanity.com/paper/2602.03955/) (2026)
- [DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review](https://mlsanity.com/paper/2604.09590/) (2026)
- [A FAIR and Free Prompt-based Research Assistant](https://mlsanity.com/paper/2405.14601/) (2024)
- [STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models](https://mlsanity.com/paper/2510.07923/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)

## Abstract (arXiv)

Scientific peer review generation has attracted increasing attention for reducing reviewing burdens and providing timely feedback. However, existing Large Language Model (LLM)-based methods often produce generic comments with insufficient evidence support and weak source traceability, while complex multi-agent systems incur high inference costs. To address these challenges, we propose EGTR-Review, an Evidence-Grounded and Traceable Review Generation framework via Multi-Agent Teacher Distillation. EGTR-Review first constructs a multi-agent teacher that performs structure-aware paper decomposition, key-element extraction, external scholarly evidence retrieval, evidence-state labeling, verification reasoning, and review synthesis. It then distills both intermediate reasoning trajectories and final review comments into a lightweight student model through task-prefix-driven multi-task learning. An evidence-weighted objective further reduces the influence of weak, missing, or non-verifiable supervision. Experiments on public peer-review datasets show that EGTR-Review (Student) outperforms strong prompt-based, fine-tuned, and structured/agentic baselines across automatic metrics, LLM-as-Judge evaluation, and human evaluation, while maintaining strong factual grounding and source traceability with substantially lower token consumption and inference time. Our code, prompts, configurations, and sample data are available on GitHub.