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 230 篇，第 1 / 5 页

1. NeurIPS 2025$\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization
2. NeurIPS 2025AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
3. NeurIPS 2025Activation-Informed Merging of Large Language Models
4. NeurIPS 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
5. NeurIPS 2025Adaptive Discretization for Consistency Models
6. NeurIPS 2025Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
7. NeurIPS 2025AdvPrefix: An Objective for Nuanced LLM Jailbreaks
8. NeurIPS 2025Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
9. NeurIPS 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
10. NeurIPS 2025AlignedGen: Aligning Style Across Generated Images
11. NeurIPS 2025AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
12. NeurIPS 2025ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
13. NeurIPS 2025AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation
14. NeurIPS 2025APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
15. NeurIPS 2025Approximately Aligned Decoding
16. NeurIPS 2025AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy
17. NeurIPS 2025ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data
18. NeurIPS 2025AutoPartGen: Autoregressive 3D Part Generation and Discovery
19. NeurIPS 2025BADiff: Bandwidth Adaptive Diffusion Model
20. NeurIPS 2025Benchmarking Large Language Models with Integer Sequence Generation Tasks
21. NeurIPS 2025Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
22. NeurIPS 2025Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation
23. NeurIPS 2025Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
24. NeurIPS 2025Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing
25. NeurIPS 2025BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks
26. NeurIPS 2025Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
27. NeurIPS 2025BoltzNCE: Learning likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
28. NeurIPS 2025Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
29. NeurIPS 2025Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
30. NeurIPS 2025Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
31. NeurIPS 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
32. NeurIPS 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code
33. NeurIPS 2025CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
34. NeurIPS 2025CLEVER: A Curated Benchmark for Formally Verified Code Generation
35. NeurIPS 2025CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
36. NeurIPS 2025CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
37. NeurIPS 2025Color Conditional Generation with Sliced Wasserstein Guidance
38. NeurIPS 2025COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
39. NeurIPS 2025Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
40. NeurIPS 2025Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
41. NeurIPS 2025Constrained Discrete Diffusion
42. NeurIPS 2025Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
43. NeurIPS 2025Contextual Thompson Sampling via Generation of Missing Data
44. NeurIPS 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
45. NeurIPS 2025CoRe: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks
46. NeurIPS 2025CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
47. NeurIPS 2025CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
48. NeurIPS 2025CSGO: Content-Style Composition in Text-to-Image Generation
49. NeurIPS 2025Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
50. NeurIPS 2025CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning

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。