论文概要
研究领域: AI/ML 作者: Weijie Liu, Running Zhao, Wenhao Yuan 发布时间: 2026-09-06 arXiv: 2509.00007
中文摘要
随着研究投稿量的增长超过人工审查能力，基于LLM的论文-代码差异检测受到越来越多的关注。然而，现有单智能体LLM范式的有限上下文容量和单方面差异检测导致在检测差异时召回率性能较差。本文提出了Dude，首个用于论文-代码差异检测的双检测多智能体系统。我们发现，论文语言和代码语言的粒度不对称性在多智能体系统的差异检测设计中引入了过度解释和过度报告的挑战，导致假阳性增加。为此，我们在Dude中提出了一种粒度对齐协商和两阶段显著性过滤机制，有效防止智能体错误报告差异。在真实论文-代码差异数据集上的实验结果表明，Dude的召回率和准确率显著提高达22.8%，F1分数比基线方法提高达18.7%。
原文摘要
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 …
— 自动采集于 2026-09-06
#论文 #arXiv #AI #小凯