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 174 篇，第 1 / 4 页

1. ICML 2026$A_2$DEPT: Large Language Model–Driven Automated Algorithm Design via Evolutionary Program Trees
2. ICML 2026A Flat Vocabulary or a Rich Hierarchy? Re-introducing Intrinsic Structure Transforms the Autoregressive Image Generation
3. ICML 2026ABSINT-AI: Agentic Heap Abstractions for Abstract Interpretation
4. ICML 2026Adaptive Code Watermarking Through Reinforcement Learning
5. ICML 2026Adaptive Generation of Bias-Eliciting Questions for LLMs
6. ICML 2026AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
7. ICML 2026Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
8. ICML 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
9. ICML 2026AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms
10. ICML 2026Anchoring Self-Play for Code Repair
11. ICML 2026Antidistillation Fingerprinting
12. ICML 2026Attention Projection Mixing with Exogenous Anchors
13. ICML 2026AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking
14. ICML 2026AutoBaxBuilder: Bootstrapping Code Security Benchmarking
15. ICML 2026Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
16. ICML 2026Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective
17. ICML 2026Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
18. ICML 2026BEST: Benchmarking Efficiency in Space and Time for LLM-Generated Code
19. ICML 2026Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming
20. ICML 2026Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?
21. ICML 2026BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
22. ICML 2026BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AI
23. ICML 2026BOOSTAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
24. ICML 2026Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
25. ICML 2026Bridging Tokens and Geometry: Token-wise 3D Supervision for CAD Generation
26. ICML 2026Bringing Code ALIVE: Optimizing Interactive Frontend Mini-Games via Automated Play and Reinforcement Learning at Scale
27. ICML 2026CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
28. ICML 2026Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
29. ICML 2026Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
30. ICML 2026CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments
31. ICML 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
32. ICML 2026Characterizing the Effect of Noise in Language Generation in the Limit
33. ICML 2026CIRBench: Evaluating Large Language Models as LLVM IR Optimizers
34. ICML 2026Closing the Loop: Universal Repository Representation with RPG-Encoder
35. ICML 2026CoDA-Bench: Can Code Agents Handle Data-Intensive Tasks?
36. ICML 2026CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer
37. ICML 2026CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
38. ICML 2026CoFrGeNet: Continued Fraction Architectures for Language Generation
39. ICML 2026Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective
40. ICML 2026ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation
41. ICML 2026CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
42. ICML 2026Depth-Progressive Monotonic Learning without Global Backpropagation
43. ICML 2026Deterministic Component Mining for Multi-Framework UI2Code Generation
44. ICML 2026DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
45. ICML 2026Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations
46. ICML 2026Dreaming in Code for Curriculum Learning in Open-Ended Worlds
47. ICML 2026DRIVE: Best Data Scheduling Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation
48. ICML 2026DRPBench: Evaluating LLMs in Concurrent Code Comprehension via Fine-Grained Data Race Prediction
49. ICML 2026ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
50. ICML 2026Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models

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。