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 79 篇，第 1 / 2 页

1. ICML 2025AAAR-1.0: Assessing AI’s Potential to Assist Research
2. ICML 2025Agent-as-a-Judge: Evaluate Agents with Agents
3. ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
4. ICML 2025An Online Learning Approach to Prompt-based Selection of Generative Models and LLMs
5. ICML 2025AuPair: Golden Example Pairs for Code Repair
6. ICML 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
7. ICML 2025Automated Benchmark Generation for Repository-Level Coding Tasks
8. ICML 2025BaxBench: Can LLMs Generate Correct and Secure Backends?
9. ICML 2025Black-Box Adversarial Attacks on LLM-Based Code Completion
10. ICML 2025BoA: Attention-aware Post-training Quantization without Backpropagation
11. ICML 2025Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
12. ICML 2025Can Large Language Models Understand Intermediate Representations in Compilers?
13. ICML 2025CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction
14. ICML 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
15. ICML 2025CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
16. ICML 2025Continuous Visual Autoregressive Generation via Score Maximization
17. ICML 2025Controllable Data Generation with Hierarchical Neural Representations
18. ICML 2025Copilot Arena: A Platform for Code LLM Evaluation in the Wild
19. ICML 2025CRANE: Reasoning with constrained LLM generation
20. ICML 2025CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
21. ICML 2025CursorCore: Assist Programming through Aligning Anything
22. ICML 2025Deep Reinforcement Learning from Hierarchical Preference Design
23. ICML 2025DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
24. ICML 2025Diffusion on Language Model Encodings for Protein Sequence Generation
25. ICML 2025DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
26. ICML 2025DLP: Dynamic Layerwise Pruning in Large Language Models
27. ICML 2025DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
28. ICML 2025Earley-Driven Dynamic Pruning for Efficient Structured Decoding
29. ICML 2025EditLord: Learning Code Transformation Rules for Code Editing
30. ICML 2025EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
31. ICML 2025EpiCoder: Encompassing Diversity and Complexity in Code Generation
32. ICML 2025Fast Inference with Kronecker-Sparse Matrices
33. ICML 2025FreeMesh: Boosting Mesh Generation with Coordinates Merging
34. ICML 2025From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
35. ICML 2025Function-to-Style Guidance of LLMs for Code Translation
36. ICML 2025Generation from Noisy Examples
37. ICML 2025Geometry Informed Tokenization of Molecules for Language Model Generation
38. ICML 2025GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code
39. ICML 2025Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
40. ICML 2025KernelBench: Can LLMs Write Efficient GPU Kernels?
41. ICML 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
42. ICML 2025Language Models over Canonical Byte-Pair Encodings
43. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
44. ICML 2025Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
45. ICML 2025Logits are All We Need to Adapt Closed Models
46. ICML 2025Long-Form Speech Generation with Spoken Language Models
47. ICML 2025LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
48. ICML 2025Matryoshka Quantization
49. ICML 2025Multi-Turn Code Generation Through Single-Step Rewards
50. ICML 2025Multimodal Medical Code Tokenizer

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。