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 3 / 9 页

101. NeurIPS 2026Attention-Based Soft Answer Sets
102. NeurIPS 2026Auditing Evidence Framing at NeurIPS: A Decade-Scale Study of Accepted Papers
103. NeurIPS 2026BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
104. NeurIPS 2026Beyond DSA: Conjugacy-based Comparison of Dynamical Systems
105. NeurIPS 2026Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged Propensities
106. NeurIPS 2026C3H: Compression-to-Consensus Criteria Hijacking in Multimodal LLM Recommender Systems
107. NeurIPS 2026Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems
108. NeurIPS 2026CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition
109. NeurIPS 2026DDBench: A Benchmark for Agentic Debugging on Distributed Systems
110. NeurIPS 2026DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
111. NeurIPS 2026Discovering Phase Space Structure in Learned Hamiltonian Systems
112. NeurIPS 2026DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
113. NeurIPS 2026Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
114. NeurIPS 2026Efficient evaluation and error pattern discovery for blackbox AI systems
115. NeurIPS 2026Embedding Security Properties into AI-Enabled Cyber-Physical Systems
116. NeurIPS 2026EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue
117. NeurIPS 2026End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
118. NeurIPS 2026Fingerprinting Inference Systems of Large Language Models
119. NeurIPS 2026Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems
120. NeurIPS 2026GT-Free OCR Metrics: A Reference-Free Evaluation Framework for Document OCR Systems
121. NeurIPS 2026Hidden Tails: Certifying Tail-Risk Claims under Selective Labels
122. NeurIPS 2026In-context learning to predict critical transitions in dynamical systems
123. NeurIPS 2026Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
124. NeurIPS 2026Information bottleneck dynamics during learning across artificial and biological neural systems
125. NeurIPS 2026Inter-Agent Influence: Evaluating Persuasion, Deception and Coercion in Multi-Agent Systems
126. NeurIPS 2026Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
127. NeurIPS 2026Know Where You Stand: Memory-Source Choice in Long-Context Dialogue Agents
128. NeurIPS 2026Knowing When Multivariate Forecasts Are Wrong
129. NeurIPS 2026Learned Lagrangian Models of PDEs via Euler–Lagrange Residual Minimization
130. NeurIPS 2026Learning Digital Twins under Drift: Optimal Tracking Rates for Non-Stationary Dynamical Systems
131. NeurIPS 2026Learning Provable Neural Network Observer for Uncertain Dynamical Systems
132. NeurIPS 2026LLM-ACES: Closed-Loop Discovery of Dynamic Systems with LLM-Guided Adaptive Search
133. NeurIPS 2026LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
134. NeurIPS 2026Markov Metrical Task Systems
135. NeurIPS 2026Mental Health AI Must Move Beyond Diagnostic Prediction and Chat-Based Support: Toward Perspective-Aware, Multisensory Co-Experience
136. NeurIPS 2026Mental-Models for Multi-Agent Systems
137. NeurIPS 2026MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
138. NeurIPS 2026Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
139. NeurIPS 2026Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
140. NeurIPS 2026Online Causal Configuration for Networked Systems via Doubly Robust Steady-State Learning
141. NeurIPS 2026Overcoming Attention Distraction: Training-Free Latent Communication for Multi-Agent Systems
142. NeurIPS 2026PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
143. NeurIPS 2026PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
144. NeurIPS 2026PRIME: Poincaré return induced measure for learning partially observed dynamical systems
145. NeurIPS 2026ProbMedTOD: A Bayesian Network Guided Task-Oriented Dialogue System for Patient History Taking
146. NeurIPS 2026Prompt–Activation Duality: Improving Activation Steering via Attention-Level Interventions
147. NeurIPS 2026Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime
148. NeurIPS 2026RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
149. NeurIPS 2026Recursive Multi-Agent Systems
150. NeurIPS 2026Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic

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。