发表机构
The University of Hong Kong; Sun Yat-sen University（香港大学; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对单智能体LLM论文-代码差异检测召回率低的问题，提出首个双检测多智能体系统Dude，通过粒度对齐协商与两阶段显著性过滤机制，在真实数据集上使F1分数最高提升18.7%。
AI 中文摘要
由于研究投稿规模超出人工审核能力，大语言模型（LLM）赋能的论文-代码差异检测受到越来越多关注。然而，现有单智能体LLM范式存在上下文容量有限、差异检测片面的问题，导致差异检测的召回性能较差。本文提出Dude，首个用于论文-代码差异检测的双检测多智能体系统。研究发现，论文语言与代码语言的粒度不对称会在差异检测的多智能体系统设计中引入过度解读与过度报告挑战，导致误报增加。为解决该问题，Dude中提出了粒度对齐协商机制与两阶段显著性过滤机制，可有效防止智能体误报差异。在真实论文-代码差异数据集上的实验结果显示，与基线方法相比，Dude的召回率和精确率提升最高达22.8%，F1分数提升最高达18.7%。
英文摘要
LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-language and code-language introduces over-interpretation and over-reporting challenges in a multi-agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.
CommentsAccepted to EMNLP 2026 Main Conference. Dude is now open-source and available at https://github.com/VinnyLiu0817/Dude
