{"total":16,"items":[{"citing_arxiv_id":"2606.13669","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:58:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Agents-K1 is an end-to-end pipeline with a multimodal parser, 4B GRPO-trained extractor, and agent CLI that builds scientific knowledge graphs from full papers and was run on 2.46 million documents to produce Scholar-KG.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01240","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking","primary_cat":"cs.CL","submitted_at":"2026-05-31T13:42:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31135","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge","primary_cat":"cs.CR","submitted_at":"2026-05-29T10:46:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Replication finds Java security API misuse persists in current LLMs but is reduced by external knowledge in a model-dependent manner.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17965","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BLAgent: Agentic RAG for File-Level Bug Localization","primary_cat":"cs.SE","submitted_at":"2026-05-18T07:20:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BLAgent achieves over 78% Top-1 accuracy on SWE-bench Lite for file-level bug localization using agentic RAG, at 18x lower cost than baselines, and boosts end-to-end APR success by over 20%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15102","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Improving Multi-turn Dialogue Consistency with Self-Recall Thinking","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:20:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SRT framework improves multi-turn dialogue F1 by 4.7% and cuts end-to-end latency by 14.7% via dependency construction, capability initialization, and reasoning improvement with recall tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14192","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Why Retrieval-Augmented Generation Fails: A Graph Perspective","primary_cat":"cs.CL","submitted_at":"2026-05-13T23:18:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Attribution graphs reveal that RAG failures arise from shallow fragmented evidence flow in LLMs, enabling topology-based detection and targeted interventions that reinforce question-guided routing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01700","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation","primary_cat":"cs.CV","submitted_at":"2026-05-03T03:51:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TrajRAG uses a topological-polar trajectory representation and hierarchical retrieval to accumulate and reuse geometric-semantic navigation experiences, improving zero-shot ObjectNav on MP3D and HM3D benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22661","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines","primary_cat":"cs.IR","submitted_at":"2026-04-24T15:36:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"QPP methods can select query variants that boost end-to-end RAG quality over the original query, though retrieval-optimized variants often fail to produce the best generated answers, revealing a utility gap.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22843","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Structure Guided Retrieval-Augmented Generation for Factual Queries","primary_cat":"cs.IR","submitted_at":"2026-04-21T14:43:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SG-RAG frames retrieval as subgraph matching to ensure LLMs meet every condition in factual queries and reports large gains over baselines on a new 120k-pair ERQA dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.08819","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","primary_cat":"cs.IR","submitted_at":"2026-03-09T18:20:20+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.16326","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","primary_cat":"cs.IR","submitted_at":"2025-11-20T13:05:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ARK fine-tunes retrievers for answer alignment using KG-augmented curriculum contrastive learning on answer-sufficient positives and progressive hard negatives, reporting 14.5% gains on long-context benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.20505","ref_index":4,"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":"2503.19470","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","primary_cat":"cs.AI","submitted_at":"2025-03-25T09:00:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ReSearch trains LLMs via RL to integrate search operations into reasoning steps, achieving strong generalization across benchmarks and eliciting reflection and self-correction without supervised reasoning data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.05779","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","primary_cat":"cs.IR","submitted_at":"2024-10-08T08:00:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LightRAG builds graph structures into RAG indexing and retrieval with dual-level search and incremental updates to improve accuracy and speed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2404.10981","ref_index":12,"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":"6 Huang et al. RAG Pre-Retrieval Indexing REALM [42];kNN-LMs [72];RAG [83];Webgpt [100];RETRO [9];MEMWALKER [13];Atlas [94];Chameleon [63];AiSAQ [126];PipeRAG [64];LRUS-CoverTree [93] Query Ma-nipulation Webgpt [100];DSP [73];CoK [86];IRCOT [131];Query2doc [137];Step-Back [163];PROMPTAGATOR [27];KnowledGPT [140];Rewrite-Retrieve-Read [94];FLARE [65];RQ-RAG [12];RARG [159];DRAGIN [124] Data Modification RA-DIT [89];RECITE [125];UPRISE [20];GENREAD [156];KnowledGPT [140];Selfmem [21];RARG [159] Retrieval Search & Ranking REALM [42];kNN-LMs [72];RAG [83];FiD [58];Webgpt [100];RETRO [9];ITRG [34];RA-DIT [89];SURGE [70];PRCA [151];AAR [157];ITER-RETGEN [121];UPRISE [20];MEMWALKER [13];Atlas [94];FLARE [65];PlanRAG [81]"},{"citing_arxiv_id":"2402.19473","ref_index":128,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:01+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"generate a pseudo document, which is later used as the query for retrieval. The pseudo document contains richer relevant information, which helps to retrieve more accurate results. TOC [127] leverages retrieved contents to decompose the ambiguous query into multiple clear sub-queries, which are sent to the generator and aggregated to produce the final result. For complex or ambiguous queries, RQ-RAG [128] breaks them down into clear subqueries for fine-grained retrieval and synthesizes the responses to deliver a cohesive answer to the original query. Tayal et al. [129] refined the initial query using dynamic few-shot examples and context retrieval, enhancing the generator's grasp of user intent. Data Augmentation: Data augmentation improves data before"}],"limit":50,"offset":0}