Dialogue Systems papers, 2023–2026

Key findings

• Dialogue Systems went from 49 papers in 2023 to 171 in 2026, roughly 3.5x in three years.
• NeurIPS publishes the most Dialogue Systems work: 189 papers from 2023 to 2026, 45% of the four-venue total.
• The fastest-growing overlap is with Multi-Agent RL: papers tagged with both rose from 0 in 2023 to 17 in 2026.
• Among the 5 topics under Natural Language, it ranks #4 by 2026 paper count; the fastest grower in the group, Retrieval-Augmented Generation, is up 5.4x versus 3.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Dialogue Systems papers

100 papers, page 1 of 2

1. ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
2. ICLR 2026Action Chunking and Data Augmentation Yield Exponential Improvements in Behavior Cloning for Continuous Spaces
3. ICLR 2026AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
4. ICLR 2026ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
5. ICLR 2026AutoDA-Timeseries: Automated Data Augmentation for Time Series
6. ICLR 2026Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent Systems
7. ICLR 2026Causal Score Conditioning for Multi-Resolution Latent Systems
8. ICLR 2026ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation Pipeline
9. ICLR 2026CoDA: Agentic Systems for Collaborative Data Visualization
10. ICLR 2026ConvRec-R1: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
11. ICLR 2026DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
12. ICLR 2026Denoising Neural Reranker for Recommender Systems
13. ICLR 2026Detecting Invariant Manifolds in ReLU-Based RNNs
14. ICLR 2026Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective
15. ICLR 2026EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
16. ICLR 2026Flipping the Dialogue: Training and Evaluating User Language Models
17. ICLR 2026Formalising Human-in-the-Loop: Computational Reductions, Failure Modes, and Legal-Moral Responsibility
18. ICLR 2026Frequency-Domain Better than Time-Domain for Causal Structure Recovery in Dynamical Systems on Networks
19. ICLR 2026Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
20. ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
21. ICLR 2026Learning Explicit Single-Cell Dynamics Using ODE Representations
22. ICLR 2026Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor–EM Method
23. ICLR 2026Measuring Bias Amplification in Multi-Agent Systems with Large Language Models
24. ICLR 2026NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
25. ICLR 2026On learning linear dynamical systems in context with attention layers
26. ICLR 2026Operator Theory-Driven Autoformulation of MDPs for Control of Queueing Systems
27. ICLR 2026Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
28. ICLR 2026Paper Copilot: Tracking the Evolution of Peer Review in AI Conferences
29. ICLR 2026Random Controlled Differential Equations
30. ICLR 2026Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
31. ICLR 2026Stochastic Self-Organization in Multi-Agent Systems
32. ICLR 2026Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
33. ICLR 2026SysMoBench: Evaluating AI on Formally Specifying Complex Real-World Systems
34. ICLR 2026Textual Equilibrium Propagation for Deep Compound AI Systems
35. ICLR 2026The Curious Case of In-Training Compression of State Space Models
36. ICLR 2026Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
37. ICLR 2025Accelerating Neural ODEs: A Variational Formulation-based Approach
38. ICLR 2025Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems
39. ICLR 2025CAX: Cellular Automata Accelerated in JAX
40. ICLR 2025ContextGNN: Beyond Two-Tower Recommendation Systems
41. ICLR 2025Disentangling 3D Animal Pose Dynamics with Scrubbed Conditional Latent Variables
42. ICLR 2025DS-LLM: Leveraging Dynamical Systems to Enhance Both Training and Inference of Large Language Models
43. ICLR 2025Efficiently Parameterized Neural Metriplectic Systems
44. ICLR 2025FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
45. ICLR 2025Feedback Favors the Generalization of Neural ODEs
46. ICLR 2025Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional, Black-box Systems
47. ICLR 2025Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems
48. ICLR 2025How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions
49. ICLR 2025Identifying latent state transitions in non-linear dynamical systems
50. ICLR 2025Improving Data Efficiency via Curating LLM-Driven Rating Systems

FAQ

How many Dialogue Systems papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

419 in total: 49 in 2023, 92 in 2024, 107 in 2025, 171 in 2026.

How many Dialogue Systems papers are at NeurIPS 2026?

NeurIPS 2026 has 76 Dialogue Systems papers, versus 46 the year before.

How many Dialogue Systems papers are at ICLR 2026?

ICLR 2026 has 36 Dialogue Systems papers, versus 34 the year before.

How many Dialogue Systems papers are at ICML 2026?

ICML 2026 has 54 Dialogue Systems papers, versus 20 the year before.

How many Dialogue Systems papers are at CVPR 2026?

CVPR 2026 has 5 Dialogue Systems papers, versus 7 the year before.

Which conference publishes the most Dialogue Systems papers?

NeurIPS, with 189 papers from 2023 to 2026.