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 3 / 4 页

101. ICLR 2025One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
102. ICLR 2025OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
103. ICLR 2025OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
104. ICLR 2025PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation
105. ICLR 2025Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
106. ICLR 2025PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
107. ICLR 2025PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance
108. ICLR 2025Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming
109. ICLR 2025Planning in Natural Language Improves LLM Search for Code Generation
110. ICLR 2025Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
111. ICLR 2025Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
112. ICLR 2025Procedural Synthesis of Synthesizable Molecules
113. ICLR 2025RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
114. ICLR 2025Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
115. ICLR 2025Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation
116. ICLR 2025Real2Code: Reconstruct Articulated Objects via Code Generation
117. ICLR 2025Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
118. ICLR 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code
119. ICLR 2025Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
120. ICLR 2025RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
121. ICLR 2025Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks
122. ICLR 2025Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions
123. ICLR 2025RuAG: Learned-rule-augmented Generation for Large Language Models
124. ICLR 2025SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
125. ICLR 2025SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
126. ICLR 2025Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data Generation
127. ICLR 2025ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
128. ICLR 2025ScImage: How good are multimodal large language models at scientific text-to-image generation?
129. ICLR 2025SFS: Smarter Code Space Search improves LLM Inference Scaling
130. ICLR 2025Shh, don't say that! Domain Certification in LLMs
131. ICLR 2025Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
132. ICLR 2025SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects
133. ICLR 2025Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes
134. ICLR 2025Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
135. ICLR 2025Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
136. ICLR 2025STAR: Synthesis of Tailored Architectures
137. ICLR 2025STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
138. ICLR 2025Steering Large Language Models between Code Execution and Textual Reasoning
139. ICLR 2025Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
140. ICLR 2025SysBench: Can LLMs Follow System Message?
141. ICLR 2025Taming Overconfidence in LLMs: Reward Calibration in RLHF
142. ICLR 2025TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice
143. ICLR 2025Teaching LLMs How to Learn with Contextual Fine-Tuning
144. ICLR 2025Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency
145. ICLR 2025TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark
146. ICLR 2025The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
147. ICLR 2025The KoLMogorov Test: Compression by Code Generation
148. ICLR 2025The Ramanujan Library - Automated Discovery on the Hypergraph of Integer Relations
149. ICLR 2025The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
150. ICLR 2025ThinK: Thinner Key Cache by Query-Driven Pruning

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。