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 164 篇，第 1 / 4 页

1. ICLR 20253DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation
2. ICLR 2025A Simple Approach to Unifying Diffusion-based Conditional Generation
3. ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
4. ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
5. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
6. ICLR 2025Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
7. ICLR 2025Adding Conditional Control to Diffusion Models with Reinforcement Learning
8. ICLR 2025Advancing Graph Generation through Beta Diffusion
9. ICLR 2025AFlow: Automating Agentic Workflow Generation
10. ICLR 2025Aligning Human Motion Generation with Human Perceptions
11. ICLR 2025An Engorgio Prompt Makes Large Language Model Babble on
12. ICLR 2025APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
13. ICLR 2025API Pack: A Massive Multi-Programming Language Dataset for API Call Generation
14. ICLR 2025Automated Proof Generation for Rust Code via Self-Evolution
15. ICLR 2025Backtracking Improves Generation Safety
16. ICLR 2025Benchmarking Agentic Workflow Generation
17. ICLR 2025Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
18. ICLR 2025BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
19. ICLR 2025BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks
20. ICLR 2025BOND: Aligning LLMs with Best-of-N Distillation
21. ICLR 2025Calibrating LLMs with Information-Theoretic Evidential Deep Learning
22. ICLR 2025Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
23. ICLR 2025ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
24. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
25. ICLR 2025ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
26. ICLR 2025CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning
27. ICLR 2025Commit0: Library Generation from Scratch
28. ICLR 2025Context Steering: Controllable Personalization at Inference Time
29. ICLR 2025ControlAR: Controllable Image Generation with Autoregressive Models
30. ICLR 2025Controllable Generation via Locally Constrained Resampling
31. ICLR 2025ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments
32. ICLR 2025Copyright-Protected Language Generation via Adaptive Model Fusion
33. ICLR 2025CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
34. ICLR 2025Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
35. ICLR 2025CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair
36. ICLR 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
37. ICLR 2025DataGen: Unified Synthetic Dataset Generation via Large Language Models
38. ICLR 2025DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation
39. ICLR 2025DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
40. ICLR 2025Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
41. ICLR 2025Diffusion On Syntax Trees For Program Synthesis
42. ICLR 2025Diffusion-based Neural Network Weights Generation
43. ICLR 2025DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
44. ICLR 2025Discrete Distribution Networks
45. ICLR 2025Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
46. ICLR 2025DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
47. ICLR 2025ECHOPulse: ECG Controlled Echocardio-gram Video Generation
48. ICLR 2025Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
49. ICLR 2025ESE: Espresso Sentence Embeddings
50. ICLR 2025Execution-guided within-prompt search for programming-by-example

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。