对话系统论文趋势 2023–2026

主要结论

• 对话系统论文从 2023 年的 49 篇增长到 2026 年的 171 篇，三年间扩大到约 3.5 倍。
• NeurIPS 是发对话系统论文最多的会议，2023–2026 年共 189 篇，占四个会议总量的 45%。
• 交叉方向里涨得最快的是多智能体 RL：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 17 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的检索增强生成是 5.4 倍，对话系统是 3.5 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 2026A Quantitative Visual Taxonomy of Worldwide Writing Systems
• ICML 2026An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
• ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
• CVPR 2026Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
• NeurIPS 2025FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
• ICML 2025Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
• ICLR 2025ContextGNN: Beyond Two-Tower Recommendation Systems
• CVPR 2025Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses
• NeurIPS 2024Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
• ICML 2024Amortized Equation Discovery in Hybrid Dynamical Systems
• ICLR 2024Safe Collaborative Filtering
• NeurIPS 2023Moral Responsibility for AI Systems
• ICML 2023Graph Switching Dynamical Systems
• ICLR 2023An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
• CVPR 2023expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization
• NeurIPS 2026Adaptive auditing of AI systems with anytime-valid guarantees
• ICML 2026Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
• ICLR 2026ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation Pipeline
• CVPR 2026Task-Driven Implicit Representations for Automated Design of LiDAR Systems
• NeurIPS 2025In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation

全部对话系统论文

共 419 篇，第 1 / 9 页

1. CVPR 2026AMB3R Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
2. CVPR 2026Lens Component Deletion based on Differentiable Ray Tracing
3. CVPR 2026Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation
4. CVPR 2026Task-Driven Implicit Representations for Automated Design of LiDAR Systems
5. CVPR 2026Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
6. ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
7. ICLR 2026Action Chunking and Data Augmentation Yield Exponential Improvements in Behavior Cloning for Continuous Spaces
8. ICLR 2026AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
9. ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
10. ICLR 2026AutoDA-Timeseries: Automated Data Augmentation for Time Series
11. ICLR 2026Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent Systems
12. ICLR 2026Causal Score Conditioning for Multi-Resolution Latent Systems
13. ICLR 2026ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation Pipeline
14. ICLR 2026CoDA: Agentic Systems for Collaborative Data Visualization
15. ICLR 2026ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
16. ICLR 2026DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
17. ICLR 2026Denoising Neural Reranker for Recommender Systems
18. ICLR 2026Detecting Invariant Manifolds in ReLU-Based RNNs
19. ICLR 2026Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective
20. ICLR 2026EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
21. ICLR 2026Flipping the Dialogue: Training and Evaluating User Language Models
22. ICLR 2026Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility
23. ICLR 2026Frequency-Domain Better than Time-Domain for Causal Structure Recovery in Dynamical Systems on Networks
24. ICLR 2026Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
25. ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
26. ICLR 2026Learning Explicit Single-Cell Dynamics Using ODE Representations
27. ICLR 2026Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor–EM Method
28. ICLR 2026Measuring Bias Amplification in Multi-Agent Systems with Large Language Models
29. ICLR 2026NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
30. ICLR 2026On learning linear dynamical systems in context with attention layers
31. ICLR 2026Operator Theory-Driven Autoformulation of MDPs for Control of Queueing Systems
32. ICLR 2026Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
33. ICLR 2026Paper Copilot: Tracking the Evolution of Peer Review in AI Conferences
34. ICLR 2026Random Controlled Differential Equations
35. ICLR 2026Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
36. ICLR 2026Stochastic Self-Organization in Multi-Agent Systems
37. ICLR 2026Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
38. ICLR 2026SysMoBench: Evaluating AI on Formally Specifying Complex Real-World Systems
39. ICLR 2026Textual Equilibrium Propagation for Deep Compound AI Systems
40. ICLR 2026The Curious Case of In-Training Compression of State Space Models
41. ICLR 2026Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
42. ICML 2026A Regime-Aware Trajectory Prediction Framework for 1000+ Systems Biology Models
43. ICML 2026An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
44. ICML 2026AutoRAS: Learning Robust Agentic Systems with Primitive Representations
45. ICML 2026Beyond Hamming: Query-Aware Decoding of Binary Cosine Sketches
46. ICML 2026Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors
47. ICML 2026Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
48. ICML 2026Clustering in Deep Stochastic Transformers
49. ICML 2026Condition-Aware Graph Flow Matching for Modeling the Distributions of Complex Fluid Systems
50. ICML 2026Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems

常见问题

2023–2026 年四大会议一共有多少篇对话系统论文？

共 419 篇，按年份分别是 2023 年 49 篇、2024 年 92 篇、2025 年 107 篇、2026 年 171 篇。

NeurIPS 2026 有多少篇对话系统论文？

NeurIPS 2026 有 76 篇对话系统论文，上一届是 46 篇。

ICLR 2026 有多少篇对话系统论文？

ICLR 2026 有 36 篇对话系统论文，上一届是 34 篇。

ICML 2026 有多少篇对话系统论文？

ICML 2026 有 54 篇对话系统论文，上一届是 20 篇。

CVPR 2026 有多少篇对话系统论文？

CVPR 2026 有 5 篇对话系统论文，上一届是 7 篇。

哪个会议的对话系统论文最多？

NeurIPS，2023–2026 年共 189 篇。