Abstract
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.
Topics
Agentic RAGUkrainian LanguageMulti-Domain Document UnderstandingRetrieval QualityQuery Rephrasing
Relevance Scores
Long-Horizon Score65
Enterprise Score60
Completeness75
Paper Info
Year2026
Venue
Type
ChapterCh. 4
Authors2
Zone III Analysis
Frameworks
Related Papers
ReAct: Synergizing Reasoning and Acting in Language Mod…
2023 · Ch.1
Toolformer: Language Models Can Teach Themselves to Use…
2023 · Ch.1
HuggingGPT: Solving AI Tasks with ChatGPT and its Frien…
2023 · Ch.4
MemGPT: Towards LLMs as Operating Systems
2023 · Ch.2
View all Chapter 4 papers →