Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.14896 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911598255276032 |
|---|---|
| author | Sumyk, Marta Kosovan, Oleksandr |
| author_facet | Sumyk, Marta Kosovan, Oleksandr |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14896 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Agentic RAG for Ukrainian Sumyk, Marta Kosovan, Oleksandr Artificial Intelligence 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. |
| title | Toward Agentic RAG for Ukrainian |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.14896 |