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 230 篇，第 3 / 5 页

101. NeurIPS 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
102. NeurIPS 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generation
103. NeurIPS 2025InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
104. NeurIPS 2025InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning
105. NeurIPS 2025IntrinsiX: High-Quality PBR Generation using Image Priors
106. NeurIPS 2025Joint Relational Database Generation via Graph-Conditional Diffusion Models
107. NeurIPS 2025Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning
108. NeurIPS 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
109. NeurIPS 2025KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
110. NeurIPS 2025Large Language Diffusion Models
111. NeurIPS 2025Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
112. NeurIPS 2025Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
113. NeurIPS 2025LeVo: High-Quality Song Generation with Multi-Preference Alignment
114. NeurIPS 2025Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
115. NeurIPS 2025LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation
116. NeurIPS 2025LMFusion: Adapting Pretrained Language Models for Multimodal Generation
117. NeurIPS 2025Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
118. NeurIPS 2025Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
119. NeurIPS 2025MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
120. NeurIPS 2025Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
121. NeurIPS 2025Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
122. NeurIPS 2025MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation
123. NeurIPS 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
124. NeurIPS 2025MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation
125. NeurIPS 2025Metis: A Foundation Speech Generation Model with Masked Generative Pre-training
126. NeurIPS 2025MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
127. NeurIPS 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
128. NeurIPS 2025MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction
129. NeurIPS 2025Mixture of Inputs: Text Generation Beyond Discrete Token Sampling
130. NeurIPS 2025More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
131. NeurIPS 2025More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation
132. NeurIPS 2025Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
133. NeurIPS 2025Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
134. NeurIPS 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
135. NeurIPS 2025NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
136. NeurIPS 2025NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
137. NeurIPS 2025OmniGen-AR: AutoRegressive Any-to-Image Generation
138. NeurIPS 2025OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
139. NeurIPS 2025OmniSVG: A Unified Scalable Vector Graphics Generation Model
140. NeurIPS 2025OmniTry: Virtual Try-On Anything without Masks
141. NeurIPS 2025On the Entropy Calibration of Language Models
142. NeurIPS 2025On Union-Closedness of Language Generation
143. NeurIPS 2025OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
144. NeurIPS 2025ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
145. NeurIPS 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
146. NeurIPS 2025PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
147. NeurIPS 2025Personalized Visual Content Generation in Conversational Systems
148. NeurIPS 2025PF∆: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations
149. NeurIPS 2025PhysX-3D: Physical-Grounded 3D Asset Generation
150. NeurIPS 2025PoE-World: Compositional World Modeling with Products of Programmatic Experts

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。