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 1 / 5 页

1. NeurIPS 2026$\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics
2. NeurIPS 2026$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation
3. NeurIPS 20263DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
4. NeurIPS 2026A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models
5. NeurIPS 2026A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
6. NeurIPS 2026A Theoretical Analysis of Test-Driven Code Generation
7. NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
8. NeurIPS 2026AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation
9. NeurIPS 2026AccelEval: A Whole-Program Benchmark for LLM-Generated CPU-to-GPU Code Acceleration
10. NeurIPS 2026AdaPCLA: Curriculum Prior Internalization For Long-Tailed Longitudinal EHR Generation
11. NeurIPS 2026AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
12. NeurIPS 2026Anchoring LLM-based Chest X-ray Report Generation via Diffusion Language Planning
13. NeurIPS 2026Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
14. NeurIPS 2026Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive
15. NeurIPS 2026Antibody Generation via Redistributed Latent Diffusion
16. NeurIPS 2026APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
17. NeurIPS 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
18. NeurIPS 2026Ask-E: An Environment for Calibrated Question Generation
19. NeurIPS 2026Assessing Sample Quality in Conditional Generation under Compositional Shift
20. NeurIPS 2026Benchmarking and Optimizing Multimodal Structured Generation: The OracleGraph Dataset and PRISM Framework
21. NeurIPS 2026Benchmarking Risk Attitudes of LLMs
22. NeurIPS 2026Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
23. NeurIPS 2026Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation
24. NeurIPS 2026Beyond Generation: Unlocking Discriminative Representations from Diffusion Models
25. NeurIPS 2026Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Image Generation
26. NeurIPS 2026Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning
27. NeurIPS 2026BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization
28. NeurIPS 2026Bridging Diffusion and Autoregression for Flexible Time Series Synthesis
29. NeurIPS 2026Can Bits Seal Language?
30. NeurIPS 2026Can LLMs Take Retrieved Information with a Grain of Salt?
31. NeurIPS 2026CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
32. NeurIPS 2026ChronosAlign: A Large-Scale, Updatable Benchmark for Decomposing Temporal Alignment in LLMs
33. NeurIPS 2026CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
34. NeurIPS 2026CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
35. NeurIPS 2026CogBench: Evaluating Cognitive-Level Control in LLM Question Generation
36. NeurIPS 2026CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation
37. NeurIPS 2026Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation
38. NeurIPS 2026ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs
39. NeurIPS 2026Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning
40. NeurIPS 2026Continuous Latent Diffusion Language Model
41. NeurIPS 2026Contrastive Identification and Generation in the Limit
42. NeurIPS 2026Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
43. NeurIPS 2026Coreset-Induced Conditional Velocity Flow Matching
44. NeurIPS 2026Corrective Diffusion Language Models
45. NeurIPS 2026Correpondence Alignment For Improved Virtual Try-On
46. NeurIPS 2026Coupling Models for One-Step Discrete Generation
47. NeurIPS 2026CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
48. NeurIPS 2026CryptanalysisBench: Can LLMs do cryptanalysis?
49. NeurIPS 2026Curriculum proof repair with learned counterexamples
50. NeurIPS 2026CyCLeGen: Cycle-Consistent Layout Prediction and Image 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。