| 2510.22344v1 | We introduce a novel agentic RAG architecture centered on an Iterative Refinement loop. | preliminary-linked | has evidence row | full-text | On HotpotQA, it achieves an F1-score of 0.453—an absolute improvement of 8.3 points over the strongest iterative baseline—establishing a new state-of-the-art for this class of methods on these benchmarks. | Abstract | in-scope: LLM extractor confirmed direction match | needs work; filled but source-depth unclear; report=audit_report.md |
| 2502.01113v3 | We introduce a graph foundation model for retrieval augmented generation (GFM-RAG), powered by a novel query-dependent GNN to enable efficient multi-hop retrieval within a single step. | supported | has evidence row | full-text | This supports the opinion that GPT-4o-mini generally outperforms GPT-3.5-turbo in constructing high quality KG-index, which is crucial for the graph-enhanced retrieval. | 1 | in-scope: LLM extractor confirmed direction match | needs work; full-text verified; report=audit_report.md |
| 2210.15133v1 | The proposed ROM enables term importance information to help language model pre-training thus achieving better performance on multiple passage retrieval benchmarks. | supported | has evidence row | full-text | How- ever, the language model trained by the random masking strategy is flawed. 3.3 Retrieval Oriented Masking As mentioned above, term importance is instruc- tive for passage retrieval. | 4.4 Evaluation Results | in-scope: LLM extractor confirmed direction match | needs work; full-text verified; report=audit_report.md |
| 2002.08909v1 | We demonstrate the effectiveness of Retrieval-Augmented Language Model pre-training (REALM) by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA). | preliminary-linked | has evidence row | full-text | we find that we outperform all previous methods by a significant margin (4-16% absolute accuracy) | Abstract | in-scope: LLM extractor confirmed direction match | needs work; filled but source-depth unclear; report=audit_report.md |
| 2505.18906v2 | This paper presents the first systematic mapping study of Federated RAG, covering literature published between 2020 and 2025. | supported | has evidence row | full-text | +12.7% QA accuracy (59.8 →72.5) using SGX | Extended Resources and Comparative Synthesis | in-scope: LLM extractor confirmed direction match | needs work; full-text verified; report=audit_report.md |