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 66 篇，第 1 / 2 页

1. ICLR 2024$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
2. ICLR 2024A Branching Decoder for Set Generation
3. ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
4. ICLR 2024A Simple and Scalable Representation for Graph Generation
5. ICLR 2024Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
6. ICLR 2024An interpretable error correction method for enhancing code-to-code translation
7. ICLR 2024Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
8. ICLR 2024At Which Training Stage Does Code Data Help LLMs Reasoning?
9. ICLR 2024AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
10. ICLR 2024Batched Low-Rank Adaptation of Foundation Models
11. ICLR 2024Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
12. ICLR 2024Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
13. ICLR 2024CODE REPRESENTATION LEARNING AT SCALE
14. ICLR 2024CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
15. ICLR 2024Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
16. ICLR 2024Controlled Text Generation via Language Model Arithmetic
17. ICLR 2024DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
18. ICLR 2024DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
19. ICLR 2024Don't Play Favorites: Minority Guidance for Diffusion Models
20. ICLR 2024DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
21. ICLR 2024Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
22. ICLR 2024Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
23. ICLR 2024ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
24. ICLR 2024Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
25. ICLR 2024Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
26. ICLR 2024GenSim: Generating Robotic Simulation Tasks via Large Language Models
27. ICLR 2024Graph Generation with $K^2$-trees
28. ICLR 2024Guess & Sketch: Language Model Guided Transpilation
29. ICLR 2024Is Self-Repair a Silver Bullet for Code Generation?
30. ICLR 2024L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
31. ICLR 2024LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
32. ICLR 2024Learning Performance-Improving Code Edits
33. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
34. ICLR 2024LILO: Learning Interpretable Libraries by Compressing and Documenting Code
35. ICLR 2024LLM Augmented LLMs: Expanding Capabilities through Composition
36. ICLR 2024LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
37. ICLR 2024LLM-Assisted Code Cleaning For Training Accurate Code Generators
38. ICLR 2024MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
39. ICLR 2024MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
40. ICLR 2024Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
41. ICLR 2024MixSATGEN: Learning Graph Mixing for SAT Instance Generation
42. ICLR 2024Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
43. ICLR 2024MVDream: Multi-view Diffusion for 3D Generation
44. ICLR 2024NOLA: Compressing LoRA using Linear Combination of Random Basis
45. ICLR 2024OctoPack: Instruction Tuning Code Large Language Models
46. ICLR 2024PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
47. ICLR 2024Personalize Segment Anything Model with One Shot
48. ICLR 2024PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
49. ICLR 2024Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
50. ICLR 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis

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。