检索记忆论文趋势 2023–2026

主要结论

• 检索记忆论文从 2023 年的 23 篇增长到 2026 年的 151 篇，三年间扩大到约 6.6 倍。
• NeurIPS 是发检索记忆论文最多的会议，2023–2026 年共 120 篇，占四个会议总量的 41%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 25 篇。
• 在「长上下文与记忆」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的长上下文是 5.2 倍，检索记忆是 6.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部检索记忆论文

共 64 篇，第 1 / 2 页

1. NeurIPS 2026ADMIT: Support-Gated Memory-Write Admission for Document QA Agents
2. NeurIPS 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
3. NeurIPS 2026Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
4. NeurIPS 2026Augmented Lagrangian Predictive Coding
5. NeurIPS 2026Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
6. NeurIPS 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
7. NeurIPS 2026AUTOMEM: Automated Learning of Memory as a Cognitive Skill
8. NeurIPS 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
9. NeurIPS 2026Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation
10. NeurIPS 2026BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node Perturbation
11. NeurIPS 2026Block Sparse Flash Attention
12. NeurIPS 2026Block Sphere Vector Quantization
13. NeurIPS 2026Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation
14. NeurIPS 2026Contrastive Retrieval Heads for Improved Attention-Based Reranking
15. NeurIPS 2026Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
16. NeurIPS 2026Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
17. NeurIPS 2026Do LLMs Bind Episodes? Probing Cross-Episode Parametric Retrieval Through Shared Cues
18. NeurIPS 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
19. NeurIPS 2026EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory
20. NeurIPS 2026FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
21. NeurIPS 2026Gradient Boosted Trees for Retrieval-Augmented Generation
22. NeurIPS 2026GraphMemRL: Action-Native Reinforcement Learning for Persistent Graph Memory Construction
23. NeurIPS 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
24. NeurIPS 2026How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?
25. NeurIPS 2026In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
26. NeurIPS 2026Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory
27. NeurIPS 2026Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
28. NeurIPS 2026LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
29. NeurIPS 2026ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
30. NeurIPS 2026MEMAUDIT: An Exact Package-Oracle Evaluation Protocol for Budgeted Long-Term LLM Memory Writing
31. NeurIPS 2026MemDLM: Memory-Enhanced DLM Training
32. NeurIPS 2026Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks
33. NeurIPS 2026Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
34. NeurIPS 2026Memory Retrieval for Changing Preferences
35. NeurIPS 2026Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
36. NeurIPS 2026Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
37. NeurIPS 2026MemPilot: Learning Transferable Latent Memory Mechanisms for LLM Reasoning
38. NeurIPS 2026MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
39. NeurIPS 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
40. NeurIPS 2026OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
41. NeurIPS 2026Phase Kernel Lifts Capacity of Dense Associative Memory
42. NeurIPS 2026Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph Memory
43. NeurIPS 2026Privacy-Preserving Retrieval-Augmented Generation with Plausible Deniability
44. NeurIPS 2026RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting
45. NeurIPS 2026ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts
46. NeurIPS 2026Remembering What Matters: From Markovian to Subtask-Causal Memory in VLA Policies
47. NeurIPS 2026Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
48. NeurIPS 2026RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory
49. NeurIPS 2026RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking
50. NeurIPS 2026SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented Generation

常见问题

2023–2026 年四大会议一共有多少篇检索记忆论文？

共 290 篇，按年份分别是 2023 年 23 篇、2024 年 44 篇、2025 年 72 篇、2026 年 151 篇。

NeurIPS 2026 有多少篇检索记忆论文？

NeurIPS 2026 有 64 篇检索记忆论文，上一届是 34 篇。

ICLR 2026 有多少篇检索记忆论文？

ICLR 2026 有 31 篇检索记忆论文，上一届是 19 篇。

ICML 2026 有多少篇检索记忆论文？

ICML 2026 有 38 篇检索记忆论文，上一届是 14 篇。

CVPR 2026 有多少篇检索记忆论文？

CVPR 2026 有 18 篇检索记忆论文，上一届是 5 篇。

哪个会议的检索记忆论文最多？

NeurIPS，2023–2026 年共 120 篇。