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 171 篇，第 2 / 4 页

51. ICML 2026Continual Learning through Control Minimization
52. ICML 2026Continuous-Time Piecewise-Linear Recurrent Neural Networks
53. ICML 2026Convex Low-resource Accent-Robust Language Detection in Speech Recognition
54. ICML 2026CORAL: Uncertainty-Aware Regulation of Exposure Concentration in Recommender Systems
55. ICML 2026DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
56. ICML 2026Embedding Hybrid Systems into Continuous Latent Vector Fields
57. ICML 2026Equilibrium Propagation for Non-Conservative Systems
58. ICML 2026Faster Activation Functions at the Edge for Post-Training Speedups
59. ICML 2026From geometry to dynamics: Learning overdamped Langevin dynamics from sparse observations with geometric constraints
60. ICML 2026G-RANS: Generalizable Residual-Aware Neural Solvers for Sparse Systems
61. ICML 2026Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality
62. ICML 2026Interpretable Functional Koopman Learning with Non-Markovian Closure for Spatiotemporal Systems
63. ICML 2026Investigating Component Contributions in Multi-Agent ML Systems
64. ICML 2026LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
65. ICML 2026Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
66. ICML 2026LieStoNet: Learning Lie Symmetries from Spatiotemporal Data for Stochastic Dynamical Systems
67. ICML 2026Measuring Agents in Production
68. ICML 2026MemEvolve: Meta-Evolution of Agent Memory Systems
69. ICML 2026MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
70. ICML 2026Meta-learning Structure-Preserving Dynamics
71. ICML 2026Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?
72. ICML 2026Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems
73. ICML 2026Neural Vector Lyapunov–Razumikhin Certificates for Delayed Interconnected Systems
74. ICML 2026Obliviate: Efficient Unlearning in Recommender Systems
75. ICML 2026On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
76. ICML 2026Online Bayesian Experimental Design for Partially Observed Dynamical Systems
77. ICML 2026Perceptrons and Localization of Attention’s Mean-Field Landscape
78. ICML 2026Persistent Semantic Entities in Tool-Augmented LLM Systems
79. ICML 2026PRISM: Parallel Residual Iterative Sequence Model
80. ICML 2026QPKO: Differentiable QP-Embedded Deep Koopman Framework for Modeling Nonlinear Systems
81. ICML 2026Recursive Binding on a Budget: Subspace Carving in Order-$p$ Tensor Memories
82. ICML 2026Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue
83. ICML 2026Rethinking Contrastive Learning for Graph Collaborative Filtering: Limitations and a Simple Remedy
84. ICML 2026Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation
85. ICML 2026SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
86. ICML 2026SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs
87. ICML 2026Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems
88. ICML 2026Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
89. ICML 2026TAMPO: Task- and Model-Aware Automatic Prompt Optimization for Auto-Routing in LLM-based Systems
90. ICML 2026TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning
91. ICML 2026The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
92. ICML 2026Universal Learning of Nonlinear Dynamics
93. ICML 2026User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
94. ICML 2026VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
95. ICML 2026Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
96. NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
97. NeurIPS 2026A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems
98. NeurIPS 2026A Quantitative Visual Taxonomy of Worldwide Writing Systems
99. NeurIPS 2026Adaptive auditing of AI systems with anytime-valid guarantees
100. NeurIPS 2026AgenTracer-v2: Agentic Failure Tracer for LLM Agentic 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。