Declaration of Performance (DoP) documents, mandated by EU regulation, certify the performance of construction products. There are two challenges to make DoPs machine and human accessible through automated key-value pair extraction (KVP) and question answering (QA): (1) While some of their content is standardized, DoPs vary widely in layout, schema, and format; (2) Both users and documents are multilingual. Existing static or LLM-only Information Extraction (IE) pipelines fail to adapt to this structural document and user diversity. Our domain-specific, agentic system addresses these challenges through a planner-executor-responder architecture. The system infers user intent, detects document language and modality, and orchestrates tools dynamically for robust, traceable reasoning while avoiding tool misuse or execution loops. Our agent outperforms baselines (ROUGE: 0.783 vs. 0.703/0.608) with better cross-lingual stability (17-point vs. 21-26-point variation).

翻译：性能声明（DoP）文档是欧盟法规要求用于认证建筑产品性能的文件。要实现通过自动化键值对提取（KVP）和问答（QA）使DoP文档能被机器和人类访问，面临两大挑战：（1）虽然部分内容已标准化，但DoP文档在版面布局、数据模式和格式方面差异巨大；（2）用户和文档均具有多语言特性。现有的静态或纯大语言模型（LLM）信息提取（IE）流程难以适应这种结构性文档和用户多样性。我们提出的领域专用智能体系统通过规划器-执行器-响应器架构应对这些挑战。该系统能够推断用户意图，检测文档语言与模态，并动态协调工具以实现鲁棒、可追溯的推理，同时避免工具误用或执行循环。实验表明，我们的智能体在基准测试中表现优异（ROUGE得分：0.783 vs. 0.703/0.608），并展现出更好的跨语言稳定性（17分波动 vs. 21-26分波动）。