arXiv Computer Science @arxiv_cs@qoto.org

HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance https://arxiv.org/abs/2602.23367 #cs.AI #cs.IR

Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use https://arxiv.org/abs/2602.23368 #cs.IR #cs.AI

Reason to Contrast: A Cascaded Multimodal Retrieval Framework https://arxiv.org/abs/2602.23369 #cs.IR #cs.AI #cs.CL

Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents https://arxiv.org/abs/2602.23370 #cs.CL #cs.AI #cs.IR

Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India https://arxiv.org/abs/2602.23371 #cs.IR #cs.AI #cs.CL

Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA https://arxiv.org/abs/2602.23372 #cs.IR #cs.AI #cs.CL

An Agentic LLM Framework for Adverse Media Screening in AML Compliance https://arxiv.org/abs/2602.23373 #cs.AI #cs.CL #cs.IR

Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG https://arxiv.org/abs/2602.23374 #cs.IR #cs.AI #cs.CL

Enriching Taxonomies Using Large Language Models https://arxiv.org/abs/2602.22213 #cs.IR #cs.AI #cs.CL

Adaptive Prefiltering for High-Dimensional Similarity Search: A Frequency-Aware Approach https://arxiv.org/abs/2602.22214 #cs.IR #cs.CV

Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation https://arxiv.org/abs/2602.22215 #cs.AI #cs.CL #cs.IR

Retrieval-Augmented Generation Assistant for Anatomical Pathology Laboratories https://arxiv.org/abs/2602.22216 #cs.IR #cs.AI

RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal Retrieval-Augmented Generation on the Edge https://arxiv.org/abs/2602.22217 #cs.IR #cs.AI

Cybersecurity Data Extraction from Common Crawl https://arxiv.org/abs/2602.22218 #cs.CR #cs.IR

Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications https://arxiv.org/abs/2602.22219 #cs.IR #cs.AI #cs.CL

What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty https://arxiv.org/abs/2602.22220 #cs.IR #cs.AI #cs.CL

Misinformation Exposure in the Chinese Web: A Cross-System Evaluation of Search Engines, LLMs, and AI Overviews https://arxiv.org/abs/2602.22221 #cs.IR #cs.AI #cs.CL #cs.CY

TWICE: An LLM Agent Framework for Simulating Personalized User Tweeting Behavior with Long-term Temporal Features https://arxiv.org/abs/2602.22222 #cs.IR #cs.MA

Disaster Question Answering with LoRA Efficiency and Accurate End Position https://arxiv.org/abs/2602.21212 #cs.CL #cs.IR #cs.LG

Topological Relational Theory: A Simplicial-Complex View of Functional Dependencies, Lossless Decomposition, and Acyclicity https://arxiv.org/abs/2602.21213 #cs.DB