Retrieval Memory papers, 2023–2026

Key findings

• Retrieval Memory went from 23 papers in 2023 to 151 in 2026, roughly 6.6x in three years.
• NeurIPS publishes the most Retrieval Memory work: 120 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 25 in 2026.
• Among the 5 topics under Long Context and Memory, it ranks #3 by 2026 paper count; the fastest grower in the group, Long Context, is up 5.2x versus 6.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
• ICML 2026Attention with Routed-Memory for Learnable Sparse Control
• ICLR 2026AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
• CVPR 2026DREAM Document Recognition with Explicit Adaptive Memory
• NeurIPS 2025EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
• ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
• ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
• CVPR 2025MAD: Memory-Augmented Detection of 3D Objects
• NeurIPS 2024A Gradient Accumulation Method for Dense Retriever under Memory Constraint
• ICML 2024Think Before You Act: Decision Transformers with Working Memory
• ICLR 2024STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
• CVPR 2024Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
• NeurIPS 2023Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection
• ICML 2023Memory-Based Meta-Learning on Non-Stationary Distributions
• ICLR 2023Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
• CVPR 2023Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis
• NeurIPS 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
• ICML 2026Dense associative memory for Gaussian distributions
• ICLR 2026FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
• CVPR 2026Interactive Tracking A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation

All Retrieval Memory papers

64 papers, page 1 of 2

1. ICLR 2026Adaptive Hopfield Network: Rethinking Similarities in Associative Memory
2. ICLR 2026AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
3. ICLR 2026Attributing Response to Context: A Jensen–Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
4. ICLR 2026Automated Formalization via Conceptual Retrieval-Augmented LLMs
5. ICLR 2026Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
6. ICLR 2026Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding
7. ICLR 2026BrowseNet: Knowledge Graph-Based Associative Memory for Contextual Information Retrieval
8. ICLR 2026Counterfactual Reasoning for Retrieval-Augmented Generation
9. ICLR 2026Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
10. ICLR 2026Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
11. ICLR 2026FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
12. ICLR 2026gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
13. ICLR 2026GRO-RAG: Gradient-aware Re-rank Optimization for Multi-source Retrieval-Augmented Generation
14. ICLR 2026Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction
15. ICLR 2026LightMem: Lightweight and Efficient Memory-Augmented Generation
16. ICLR 2026LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
17. ICLR 2026MLP Memory: A Retriever-Pretrained Memory for Large Language Models
18. ICLR 2026MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval
19. ICLR 2026Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
20. ICLR 2026Pisces: Cryptography-based Private Retrieval-Augmented Generation with Dual-Path Retrieval
21. ICLR 2026RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference
22. ICLR 2026Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
23. ICLR 2026Rescue: Retrieval Augmented Secure Code Generation
24. ICLR 2026Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
25. ICLR 2026Scaling up Memory for Robotic Control via Experience Retrieval
26. ICLR 2026Short Window Attention Enables Long-Term Memorization
27. ICLR 2026SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
28. ICLR 2026The Pensieve Paradigm: Stateful Language Models with Learned Memory Management
29. ICLR 2026TokMem: Tokenized Procedural Memory for Large Language Models
30. ICLR 2026Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
31. ICLR 2026Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
32. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
33. ICLR 2025An Evolved Universal Transformer Memory
34. ICLR 2025BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
35. ICLR 2025DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints
36. ICLR 2025ESE: Espresso Sentence Embeddings
37. ICLR 2025Human-inspired Episodic Memory for Infinite Context LLMs
38. ICLR 2025InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
39. ICLR 2025LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
40. ICLR 2025MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory
41. ICLR 2025RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models
42. ICLR 2025RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
43. ICLR 2025RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression
44. ICLR 2025RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
45. ICLR 2025RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
46. ICLR 2025SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
47. ICLR 2025Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
48. ICLR 2025Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
49. ICLR 2025STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
50. ICLR 2025Sufficient Context: A New Lens on Retrieval Augmented Generation Systems

FAQ

How many Retrieval Memory papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

290 in total: 23 in 2023, 44 in 2024, 72 in 2025, 151 in 2026.

How many Retrieval Memory papers are at NeurIPS 2026?

NeurIPS 2026 has 64 Retrieval Memory papers, versus 34 the year before.

How many Retrieval Memory papers are at ICLR 2026?

ICLR 2026 has 31 Retrieval Memory papers, versus 19 the year before.

How many Retrieval Memory papers are at ICML 2026?

ICML 2026 has 38 Retrieval Memory papers, versus 14 the year before.

How many Retrieval Memory papers are at CVPR 2026?

CVPR 2026 has 18 Retrieval Memory papers, versus 5 the year before.

Which conference publishes the most Retrieval Memory papers?

NeurIPS, with 120 papers from 2023 to 2026.