In this report, we present our third-place solution for the DataMFM Challenge Track 1: Document Parsing. This track requires models to recover structured Markdown documents from document page images while preserving textual content and document structure. To address the complementary requirements of accurate content recovery and faithful structure reconstruction, we propose ParseFixer, an agentic framework for backbone parsing and selective correction. ParseFixer consists of two key modules: Full-Page Backbone Parsing (FBP) and Agentic Selective Correction (ASC). FBP produces stable initial Markdown outputs with MinerU2.5 Pro, while ASC detects high-value parsing failures and repairs them through a verify-and-rollback correction process. By placing selective multimodal correction after open-source backbone parsing, ParseFixer improves the recovery of key document elements without rewriting reliable backbone predictions. On the test set, our final system achieves an overall score of 61.78 and ranks third in Track 1, demonstrating its effectiveness for accurate document parsing. Our code will be released at: https://github.com/iLearn-Lab/CVPRW26-ParseFixer.

翻译：在本文中，我们介绍了DataMFM挑战赛赛道一（文档解析）的季军解决方案。该赛道要求模型从文档页面图像中恢复结构化的Markdown文档，同时保留文本内容和文档结构。为满足准确内容恢复与忠实结构重建的互补需求，我们提出了ParseFixer——一种面向骨干解析和选择性校正的智能体框架。ParseFixer包含两个核心模块：全页骨干解析（FBP）与智能体选择性校正（ASC）。FBP利用MinerU2.5 Pro生成稳定的初始Markdown输出，而ASC则通过验证-回滚校正流程检测高价值解析失败并进行修复。通过在开源骨干解析后引入选择性多模态校正，ParseFixer无需重写可靠的骨干预测即可提升关键文档元素的恢复质量。在测试集上，我们的最终系统以61.78总分位列赛道一第三名，验证了其精确文档解析的有效性。代码将发布至：https://github.com/iLearn-Lab/CVPRW26-ParseFixer。