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 54 篇，第 1 / 2 页

1. ICML 2026A Regime-Aware Trajectory Prediction Framework for 1000+ Systems Biology Models
2. ICML 2026An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
3. ICML 2026AutoRAS: Learning Robust Agentic Systems with Primitive Representations
4. ICML 2026Beyond Hamming: Query-Aware Decoding of Binary Cosine Sketches
5. ICML 2026Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors
6. ICML 2026Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
7. ICML 2026Clustering in Deep Stochastic Transformers
8. ICML 2026Condition-Aware Graph Flow Matching for Modeling the Distributions of Complex Fluid Systems
9. ICML 2026Constrained hybrid modelling to predict microbial dynamics and organic matter turnover in soil systems
10. ICML 2026Continual Learning through Control Minimization
11. ICML 2026Continuous-Time Piecewise-Linear Recurrent Neural Networks
12. ICML 2026Convex Low-resource Accent-Robust Language Detection in Speech Recognition
13. ICML 2026CORAL: Uncertainty-Aware Regulation of Exposure Concentration in Recommender Systems
14. ICML 2026DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
15. ICML 2026Embedding Hybrid Systems into Continuous Latent Vector Fields
16. ICML 2026Equilibrium Propagation for Non-Conservative Systems
17. ICML 2026Faster Activation Functions at the Edge for Post-Training Speedups
18. ICML 2026From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraints
19. ICML 2026G-RANS: Generalizable Residual-Aware Neural Solvers for Sparse Systems
20. ICML 2026Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality
21. ICML 2026Interpretable Functional Koopman Learning with Non-Markovian Closure for Spatiotemporal Systems
22. ICML 2026Investigating Component Contributions in Multi-Agent ML Systems
23. ICML 2026LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
24. ICML 2026Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
25. ICML 2026LieStoNet: Learning Lie Symmetries from Spatiotemporal Data for Stochastic Dynamical Systems
26. ICML 2026Measuring Agents in Production
27. ICML 2026MemEvolve: Meta-Evolution of Agent Memory Systems
28. ICML 2026MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
29. ICML 2026Meta-learning Structure-Preserving Dynamics
30. ICML 2026Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?
31. ICML 2026Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems
32. ICML 2026Neural Vector Lyapunov–Razumikhin Certificates for Delayed Interconnected Systems
33. ICML 2026Obliviate: Efficient Unlearning in Recommender Systems
34. ICML 2026On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
35. ICML 2026Online Bayesian Experimental Design for Partially Observed Dynamical Systems
36. ICML 2026Perceptrons and Localization of Attention’s Mean-Field Landscape
37. ICML 2026Persistent Semantic Entities in Tool-Augmented LLM Systems
38. ICML 2026PRISM: Parallel Residual Iterative Sequence Model
39. ICML 2026QPKO: Differentiable QP-Embedded Deep Koopman Framework for Modeling Nonlinear Systems
40. ICML 2026Recursive Binding on a Budget: Subspace Carving in Order-$p$ Tensor Memories
41. ICML 2026Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue
42. ICML 2026Rethinking Contrastive Learning for Graph Collaborative Filtering: Limitations and a Simple Remedy
43. ICML 2026Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation
44. ICML 2026SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
45. ICML 2026SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs
46. ICML 2026Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems
47. ICML 2026Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
48. ICML 2026TAMPO: Task- and Model-Aware Automatic Prompt Optimization for Auto-Routing in LLM-based Systems
49. ICML 2026TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
50. ICML 2026The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

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。