代码生成论文趋势 2023–2026

主要结论

• 代码生成论文从 2023 年的 210 篇增长到 2026 年的 860 篇，三年间扩大到约 4.1 倍。
• NeurIPS 是发代码生成论文最多的会议，2023–2026 年共 630 篇，占四个会议总量的 29%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 93 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的检索增强生成是 5.4 倍，代码生成是 4.1 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 Theoretical Analysis of Test-Driven Code Generation
• ICML 2026$A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program Trees
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026ACPV-Net All-Class Polygonal Vectorization for Seamless Vector Map Generation from
• NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
• ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
• ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
• CVPR 2025ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
• NeurIPS 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
• ICML 2024ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
• ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
• CVPR 2024Desigen: A Pipeline for Controllable Design Template Generation
• NeurIPS 2023ANPL: Towards Natural Programming with Interactive Decomposition
• ICML 2023Can Large Language Models Reason about Program Invariants?
• ICLR 2023Binding Language Models in Symbolic Languages
• CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
• ICLR 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
• CVPR 2026Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

全部代码生成论文

共 236 篇，第 2 / 5 页

51. NeurIPS 2026Debiased Counterfactual Generation via Flow Matching from Observations
52. NeurIPS 2026DeepfakeGenome: Toward Next-Generation Deepfake Attribution
53. NeurIPS 2026Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
54. NeurIPS 2026DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
55. NeurIPS 2026Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
56. NeurIPS 2026Diffusion Language Models Can Approximate Optimal Infilling Lengths Implicitly
57. NeurIPS 2026DiPhon: Diffusion on Graphons for Scalable Graph Generation
58. NeurIPS 2026DiReCL: Learning Differentiable Reward Code with Inverse Reinforcement Learning
59. NeurIPS 2026DIS-Bench: Evaluating LLMs on System Testing via Directed Input Synthesis
60. NeurIPS 2026Discrete Stochastic Localization for Non-autoregressive Generation
61. NeurIPS 2026Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
62. NeurIPS 2026Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?
63. NeurIPS 2026Doomed to Re-Annotate, Forever: The ImageNet Story
64. NeurIPS 2026dRAE: Representation Autoencoder with Hyper-Spherical Codes
65. NeurIPS 2026DriftWeight: Repulsive Drift in Mean-Flow Space for Neural Network Weight Generation
66. NeurIPS 2026DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
67. NeurIPS 2026Duality Models: An Embarrassingly Simple One-step Generation Paradigm
68. NeurIPS 2026Dynamic Video Generation: Shaping Video Generation Across Time and Space
69. NeurIPS 2026EditFlowSR: Revisable Expression Generation for Symbolic Regression
70. NeurIPS 2026ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
71. NeurIPS 2026Empirical regularities in subjective decision-making by LLMs
72. NeurIPS 2026Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution
73. NeurIPS 2026Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
74. NeurIPS 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?
75. NeurIPS 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
76. NeurIPS 2026Exact Regular-Constrained Sampling for Variable-Order Markov Generation
77. NeurIPS 2026Exploring Advertising Manipulation in Diffusion Image Generation
78. NeurIPS 2026Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
79. NeurIPS 2026Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
80. NeurIPS 2026Feeling of Knowing in Large Language Models
81. NeurIPS 2026FlexCover: Flexible Cover Song Generation via Symbolic Lead Sheet Control
82. NeurIPS 2026FloatDoor: Platform triggered Backdoors in LLMs
83. NeurIPS 2026Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
84. NeurIPS 2026FracTS: Hierarchical and Autoregressive Time Series Generation
85. NeurIPS 2026Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation
86. NeurIPS 2026From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts
87. NeurIPS 2026From Generation to Restoration: Residual Diffusion for Neural Channel Decoding
88. NeurIPS 2026From I/O to Code with Discovery Agent
89. NeurIPS 2026From Ideas to Code: Tree-structured Policy Optimization for Automated Algorithm Design with LLMs
90. NeurIPS 2026FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
91. NeurIPS 2026G-Zero: Self-Play for Open-Ended Generation from Zero Data
92. NeurIPS 2026Generation-Drift-Guided Block Pruning for Large Language Models
93. NeurIPS 2026GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond Caching
94. NeurIPS 2026GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
95. NeurIPS 2026GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
96. NeurIPS 2026Guarding the Life Code: Preserving Membership Privacy in Genomic Foundation Models
97. NeurIPS 2026Guided Data Generation for Understanding Model Behavior
98. NeurIPS 2026Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
99. NeurIPS 2026Hidden Positives: Why Code Retrieval Benchmarks Underestimate Model Quality
100. NeurIPS 2026HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation

常见问题

2023–2026 年四大会议一共有多少篇代码生成论文？

共 2,161 篇，按年份分别是 2023 年 210 篇、2024 年 446 篇、2025 年 645 篇、2026 年 860 篇。

NeurIPS 2026 有多少篇代码生成论文？

NeurIPS 2026 有 236 篇代码生成论文，上一届是 230 篇。

ICLR 2026 有多少篇代码生成论文？

ICLR 2026 有 241 篇代码生成论文，上一届是 164 篇。

ICML 2026 有多少篇代码生成论文？

ICML 2026 有 174 篇代码生成论文，上一届是 79 篇。

CVPR 2026 有多少篇代码生成论文？

CVPR 2026 有 209 篇代码生成论文，上一届是 172 篇。

哪个会议的代码生成论文最多？

NeurIPS，2023–2026 年共 630 篇。