{"total":11,"items":[{"citing_arxiv_id":"2604.26283","ref_index":53,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","primary_cat":"cs.CV","submitted_at":"2026-04-29T04:23:35+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Moreover, discrete symbols tend to encode generic linguistic priors rather than dynamic anatomical context, readily giving rise to \"pseudo-logical\" hallu- cinations that lack grounding in physical evidence. An intuitive remedy is to supplement models with external diagnostic knowl- edge. Retrieval-augmented generation (RAG) prepends retrieved text fragments or similar cases to the input context [1,53,61,63,66], while soft-prompt and prefix-tuning methods concatenate learnable vectors to the input sequence to in- ject domain-specific cues [14,22,47]. However, both strategies inject information that remainsstaticandcausally unverified: it has undergone neither validation of causal relevance to the current diagnostic decision nor evolution into an intrin-"},{"citing_arxiv_id":"2604.25646","ref_index":50,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SAMe: A Semantic Anatomy Mapping Engine for Robotic Ultrasound","primary_cat":"cs.CV","submitted_at":"2026-04-28T13:44:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SAMe grounds complaints to organs, builds a lightweight patient anatomy model from one body image, and outputs probe initialization poses, outperforming keypoint baselines in real-robot liver and kidney trials.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17114","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning","primary_cat":"cs.CL","submitted_at":"2026-04-18T19:10:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HEG-TKG grounds LLM clinical reasoning in hierarchical evidence-based temporal knowledge graphs from 4,512 PubMed records, delivering 100% citation verifiability and error detectability where standard RAG and unprompted LLMs produce none.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12185","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-14T01:31:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OKH-RAG represents knowledge as ordered hyperedges and retrieves coherent interaction sequences via a learned transition model, outperforming permutation-invariant RAG baselines on order-sensitive QA tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.01707","ref_index":104,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","primary_cat":"cs.CL","submitted_at":"2026-04-02T07:19:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"ence captured in a vast array of database forum discussions, recent studies [7, 16, 20, 35, 42, 45, 82, 85, 104, 105] have begun leveraging LLMs to enhance database performance. For instance, GPTuner [35] proposes to enhance database knob tuning using LLMs by leverag- ing domain knowledge to identify important knobs and coarsely initialize their values for subsequent refinement. Besides, D-Bot [104] proposes an LLM-based database diagnosis system, which can retrieve relevant knowledge chunks and tools, and use them to identify typical root causes accurately. The LLM-based data analysis systems and tools have also been studied [2, 10, 17, 25, 38, 39, 46- 50, 68, 95, 100]. To the best of our knowledge, our work is the first study that pro- vides a unified framework for all existing agent memory methods"},{"citing_arxiv_id":"2604.19776","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","primary_cat":"cs.CL","submitted_at":"2026-03-28T11:22:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A domain-specific LLM for TB care in South Africa, created by fine-tuning BioMistral-7B with QLoRA and GraphRAG on local guidelines, shows improved contextual alignment over the base model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.24649","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows","primary_cat":"cs.CV","submitted_at":"2026-03-25T17:33:58+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"MedFlowBench evaluates VLM agents on full radiology and pathology studies by requiring both task answers and verifiable evidence like key slices and regions of interest, revealing that answer-only scores overestimate performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.22609","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generation","primary_cat":"cs.AI","submitted_at":"2025-10-26T10:11:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"CLIN-LLM combines uncertainty-calibrated BioBERT classification with retrieval-augmented FLAN-T5 generation and safety post-processing to reach 98% accuracy on clinical cases while cutting unsafe antibiotic suggestions by 67%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.00017","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation","primary_cat":"cs.CL","submitted_at":"2025-04-24T01:05:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ReCellTy constructs a knowledge graph with 18850 nodes and 48944 edges, retrieves relevant entities for differential genes, and applies multi-task LLM reasoning to improve single-cell type annotation over standard LLMs by up to 0.21 in human scores and 6.1% in semantic similarity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.04338","ref_index":90,"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":62,"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}],"limit":50,"offset":0}