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 135 篇，第 3 / 3 页

101. NeurIPS 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
102. NeurIPS 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
103. NeurIPS 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agents
104. NeurIPS 2024Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
105. NeurIPS 2024RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
106. NeurIPS 2024Reproducibility Study of "ITI-GEN: Inclusive Text-to-Image Generation"
107. NeurIPS 2024Reranking Laws for Language Generation: A Communication-Theoretic Perspective
108. NeurIPS 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policy
109. NeurIPS 2024SciCode: A Research Coding Benchmark Curated by Scientists
110. NeurIPS 2024Score Distillation via Reparametrized DDIM
111. NeurIPS 2024Score-based 3D molecule generation with neural fields
112. NeurIPS 2024Selective Generation for Controllable Language Models
113. NeurIPS 2024SelfCodeAlign: Self-Alignment for Code Generation
114. NeurIPS 2024SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
115. NeurIPS 2024SnapKV: LLM Knows What You are Looking for Before Generation
116. NeurIPS 2024Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
117. NeurIPS 2024SparseLLM: Towards Global Pruning of Pre-trained Language Models
118. NeurIPS 2024Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
119. NeurIPS 2024Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
120. NeurIPS 2024Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
121. NeurIPS 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
122. NeurIPS 2024Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
123. NeurIPS 2024Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages
124. NeurIPS 2024The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
125. NeurIPS 2024Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
126. NeurIPS 2024Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
127. NeurIPS 2024Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
128. NeurIPS 2024U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
129. NeurIPS 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-World Document Analysis
130. NeurIPS 2024UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
131. NeurIPS 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
132. NeurIPS 2024Verified Code Transpilation with LLMs
133. NeurIPS 2024Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
134. NeurIPS 2024Where does In-context Learning Happen in Large Language Models?
135. NeurIPS 2024ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

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。