为乌克兰语设计可自主重试的检索增强生成系统
Toward Agentic RAG for Ukrainian
- 两阶段检索+轻量级智能体重写查询、重试答案
- 重试机制提升准确率，但文档定位仍是瓶颈
- 适合研究乌克兰语多领域理解与智能体系统
我们针对乌克兰语开展了一项关于自主式检索增强生成（Agentic RAG）的初步研究，参与了UNLP 2026共享任务中的多领域文档理解。系统采用BGE-M3结合BGE重排序的两阶段检索，并在Qwen2.5-3B-Instruct基础上添加轻量级智能体层，实现查询重写与答案重试循环。分析表明，检索质量是主要瓶颈：虽然智能体重试机制提升了回答准确率，但整体性能仍受限于文档与页面识别。我们讨论了离线智能体流程的实际局限性，并提出未来方向——将更强的检索能力与更先进的智能体推理相结合，以支持乌克兰语场景。
原文摘要 · Abstract (English)
We present an initial investigation into Agentic Retrieval-Augmented Generation (RAG) for Ukrainian, conducted within the UNLP 2026 Shared Task on Multi-Domain Document Understanding. Our system combines two-stage retrieval (BGE-M3 with BGE reranking) with a lightweight agentic layer performing query rephrasing and answer-retry loops on top of Qwen2.5-3B-Instruct. Our analysis reveals that retrieval quality is the primary bottleneck: agentic retry mechanisms improve answer accuracy but the overall score remains constrained by document and page identification. We discuss practical limitations of offline agentic pipelines and outline directions for combining stronger retrieval with more advanced agentic reasoning for Ukrainian.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。