SOTAVerified

Retrieval-augmented Generation

Papers

Showing 150 of 2196 papers

TitleStatusHype
Mem0: Building Production-Ready AI Agents with Scalable Long-Term MemoryCode15
LightRAG: Simple and Fast Retrieval-Augmented GenerationCode14
Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria RerankingCode13
From Local to Global: A Graph RAG Approach to Query-Focused SummarizationCode13
Zep: A Temporal Knowledge Graph Architecture for Agent MemoryCode12
WebWalker: Benchmarking LLMs in Web TraversalCode11
UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented GenerationCode9
AutoAgent: A Fully-Automated and Zero-Code Framework for LLM AgentsCode9
Contextual Augmented Multi-Model Programming (CAMP): A Hybrid Local-Cloud Copilot FrameworkCode9
KAG: Boosting LLMs in Professional Domains via Knowledge Augmented GenerationCode9
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-HaystackCode9
HuixiangDou2: A Robustly Optimized GraphRAG ApproachCode7
From RAG to Memory: Non-Parametric Continual Learning for Large Language ModelsCode7
VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context VideosCode7
A Survey of Graph Retrieval-Augmented Generation for Customized Large Language ModelsCode7
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented GenerationCode7
AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation PipelineCode7
MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge DiscoveryCode7
PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning MethodsCode7
ColPali: Efficient Document Retrieval with Vision Language ModelsCode7
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsCode7
MiniCheck: Efficient Fact-Checking of LLMs on Grounding DocumentsCode7
SGLang: Efficient Execution of Structured Language Model ProgramsCode6
RAGAS: Automated Evaluation of Retrieval Augmented GenerationCode6
RAG-R1 : Incentivize the Search and Reasoning Capabilities of LLMs through Multi-query ParallelismCode5
TrustRAG: An Information Assistant with Retrieval Augmented GenerationCode5
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGCode5
MiniRAG: Towards Extremely Simple Retrieval-Augmented GenerationCode5
Search-o1: Agentic Search-Enhanced Large Reasoning ModelsCode5
Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge TasksCode5
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive AnnotationsCode5
KBLaM: Knowledge Base augmented Language ModelCode5
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented GenerationCode5
Retrieval-Augmented Generation for AI-Generated Content: A SurveyCode5
A Survey of LLM DATACode4
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory SynthesisCode4
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement LearningCode4
s3: You Don't Need That Much Data to Train a Search Agent via RLCode4
OnPrem.LLM: A Privacy-Conscious Document Intelligence ToolkitCode4
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world EnvironmentsCode4
Retrieval-Augmented Generation with Hierarchical KnowledgeCode4
ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning AgentsCode4
LettuceDetect: A Hallucination Detection Framework for RAG ApplicationsCode4
Training Sparse Mixture Of Experts Text Embedding ModelsCode4
Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented GenerationCode4
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process RewardingCode4
EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network OperationsCode4
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality DocumentsCode4
When Does Perceptual Alignment Benefit Vision Representations?Code4
Data-Prep-Kit: getting your data ready for LLM application developmentCode4
Show:102550
← PrevPage 1 of 44Next →

No leaderboard results yet.