{"total":10,"items":[{"citing_arxiv_id":"2605.08333","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG","primary_cat":"cs.LG","submitted_at":"2026-05-08T17:58:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CDS4RAG cyclically optimizes full RAG hyperparameters by distinguishing and alternating between retriever and generator components, boosting performance up to 1.54x over prior methods on benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17458","ref_index":292,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","primary_cat":"cs.AI","submitted_at":"2026-04-19T14:18:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14222","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents","primary_cat":"cs.IR","submitted_at":"2026-04-14T10:48:13+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07752","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models","primary_cat":"cs.SE","submitted_at":"2026-04-09T03:16:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MIMIC-Py provides a modular Python framework that turns personality-driven LLM agents into an extensible system for automated game testing via configurable traits, decoupled components, and multiple interaction methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05467","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation","primary_cat":"cs.IR","submitted_at":"2026-04-07T06:05:08+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CUE-R uses REMOVE, REPLACE, and DUPLICATE interventions on individual evidence items to quantify their per-item utility in RAG along correctness, grounding faithfulness, and confidence axes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.20505","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA","primary_cat":"cs.CL","submitted_at":"2025-10-23T12:48:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.04338","ref_index":95,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","primary_cat":"cs.IR","submitted_at":"2025-03-06T11:34:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.09891","ref_index":68,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","primary_cat":"cs.IR","submitted_at":"2025-02-14T03:28:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2407.13193","ref_index":191,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","primary_cat":"cs.CL","submitted_at":"2024-07-18T06:06:53+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"by adding a new cross-attention module in each transformer block for introducing retrieval knowledge. The intuition of those works is that given the similar Prefixes and their next tokens (retrieving stage), the pre-trained model can calibrate the model's prediction using the cross-attention module to capture the pattern between the next token and prefix (model forwarding stage). Zhong et al. [191] propose to augment the language model with three types of re- trieval memories/databases (local memory, long-term memory, and external memory) and optimize the next-token probability distribu- tion with nearest neighbors retrieved from the memories/databases. Another branch of works [53, 68, 88, 133, 177] focuses on augment- ing the inputs or outputs of generators with retrievals."},{"citing_arxiv_id":"2404.10981","ref_index":161,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","primary_cat":"cs.IR","submitted_at":"2024-04-17T01:27:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"PRCA [151] 2023 BM25, DPR, Contriver, SimCSE [37], SBERT T5, Phoenix-7B [19], Vicuna-7B [22], ChatGLM [31], GPT-3.5 REPLUG [122] 2023 Contriever GPT-3 AAR [157] 2023 ANCE [146], Contriever Flan-T5, InstructGPT Query2doc [137] 2023 BM25, DPR GPT-3 (text-davinci-003) Step-Back [163] 2023 PaLM-2L [23] PaLM-2L, GPT-4 ITER-RETGEN [121] 2023 Contriever InstructGPT (text-davinci-003), LLaMA2 RECITE [125] 2023 PaLM, UL2 [127], OPT [161], Codex [16] PROMPTAGATOR [27] 2023 T5 FLAN UPRISE [20] 2023 GPT-Neo-2.7B [8] BLOOM-7.1B [142], OPT-66B, GPT-3-175B GENREAD [156] 2023 InstructGPT LAPDOG [52] 2023 Contriever T5 KnowledGPT [140] 2023 GPT-4 Selfmem [21] 2023 BM25 XGLM [90], XLM-Rbase [25] MEMWALKER [13] 2023 LLaMA2 LLaMA2 RECOMP [147] 2023 BM25 T5-Large Rewrite-Retrieve-Read [94]2023 Bing T5-Large, ChatGPT(gpt-3."}],"limit":50,"offset":0}