Retrieval-Augmented Generation papers, 2023–2026

RAG and retrieval augmentation

Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 1,200 papers are tagged with this topic.

Key findings

Papers per year

Papers per venue

Counts by year and venue

Retrieval-Augmented Generation papers by year and venue
YearNeurIPSICLRICMLCVPRTotal
202319291737102
202450345049183
20251361115762366
2026186129126108549

Representative papers

Spread across years and venues so every edition shows up

All Retrieval-Augmented Generation papers

549 papers, page 10 of 11

  1. NeurIPS 2026KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
  2. NeurIPS 2026Latent Abstraction for Retrieval-Augmented Generation
  3. NeurIPS 2026LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
  4. NeurIPS 2026Learning Augmented Exact Exponential Algorithms
  5. NeurIPS 2026Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
  6. NeurIPS 2026Learning-Augmented Online Scheduling with Parsimonious Preemption
  7. NeurIPS 2026Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA
  8. NeurIPS 2026Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
  9. NeurIPS 2026LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data
  10. NeurIPS 2026LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
  11. NeurIPS 2026Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
  12. NeurIPS 2026LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
  13. NeurIPS 2026LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
  14. NeurIPS 2026Machine Learning-Driven RAG System Design
  15. NeurIPS 2026ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
  16. NeurIPS 2026Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
  17. NeurIPS 2026MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
  18. NeurIPS 2026MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
  19. NeurIPS 2026Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks
  20. NeurIPS 2026Memory Retrieval for Changing Preferences
  21. NeurIPS 2026MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
  22. NeurIPS 2026MiniPIC: Flexible Position-Independent Caching in <100LOC
  23. NeurIPS 2026Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval
  24. NeurIPS 2026MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
  25. NeurIPS 2026MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
  26. NeurIPS 2026MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
  27. NeurIPS 2026Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
  28. NeurIPS 2026OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
  29. NeurIPS 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
  30. NeurIPS 2026OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
  31. NeurIPS 2026On objective mismatch in molecular retrieval from tandem mass spectrometry
  32. NeurIPS 2026On the Price of Privacy for Language Identification and Generation
  33. NeurIPS 2026On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation
  34. NeurIPS 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
  35. NeurIPS 2026OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
  36. NeurIPS 2026Optimal Real-Data Allocation for Synthetic-Data-Augmented Inference
  37. NeurIPS 2026Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
  38. NeurIPS 2026PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
  39. NeurIPS 2026Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
  40. NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
  41. NeurIPS 2026PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
  42. NeurIPS 2026Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
  43. NeurIPS 2026Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
  44. NeurIPS 2026Prediction-Augmented Trees for Reliable Statistical Inference
  45. NeurIPS 2026Privacy-Preserving Retrieval-Augmented Generation with Plausible Deniability
  46. NeurIPS 2026Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models
  47. NeurIPS 2026ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science
  48. NeurIPS 2026RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
  49. NeurIPS 2026RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting
  50. NeurIPS 2026RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance

Ask about this trend from Claude or Cursor

Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.

Copy this prompt into your assistant

Use paperlist to show how Retrieval-Augmented Generation papers grew at NeurIPS from 2023 to 2026, and which year jumped the most.

Tool the assistant calls: get_topic_stats {"topic": "retrieval-augmented-generation"}

Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)

FAQ

How many Retrieval-Augmented Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?
1,200 in total: 102 in 2023, 183 in 2024, 366 in 2025, 549 in 2026.
How many Retrieval-Augmented Generation papers are at NeurIPS 2026?
NeurIPS 2026 has 186 Retrieval-Augmented Generation papers, versus 136 the year before.
How many Retrieval-Augmented Generation papers are at ICLR 2026?
ICLR 2026 has 129 Retrieval-Augmented Generation papers, versus 111 the year before.
How many Retrieval-Augmented Generation papers are at ICML 2026?
ICML 2026 has 126 Retrieval-Augmented Generation papers, versus 57 the year before.
How many Retrieval-Augmented Generation papers are at CVPR 2026?
CVPR 2026 has 108 Retrieval-Augmented Generation papers, versus 62 the year before.
Which conference publishes the most Retrieval-Augmented Generation papers?
NeurIPS, with 391 papers from 2023 to 2026.

More in Natural Language