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 241 篇，第 3 / 5 页

101. ICLR 2026How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective
102. ICLR 2026Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
103. ICLR 2026Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
104. ICLR 2026Improving Code Localization with Repository Memory
105. ICLR 2026InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement
106. ICLR 2026InfGen: Scenario Generation as Next Token Group Prediction
107. ICLR 2026Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing
108. ICLR 2026JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
109. ICLR 2026JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
110. ICLR 2026jqBench: a benchmark for reading and editing JSON from natural language and/or examples
111. ICLR 2026KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
112. ICLR 2026Kevin: Multi-Turn RL for Generating CUDA Kernels
113. ICLR 2026Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
114. ICLR 2026Learning to Generate Unit Test via Adversarial Reinforcement Learning
115. ICLR 2026Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration
116. ICLR 2026Leveraging Pretrained Knowledge at Inference Time: LoRA-Gated Contrastive Decoding for Multilingual Factual Language Generation in Adapted LLMs
117. ICLR 2026LightMem: Lightweight and Efficient Memory-Augmented Generation
118. ICLR 2026LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
119. ICLR 2026LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
120. ICLR 2026LLM-Guided Evolutionary Program Synthesis for Quasi-Monte Carlo Design
121. ICLR 2026Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
122. ICLR 2026LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
123. ICLR 2026LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
124. ICLR 2026M4PQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
125. ICLR 2026MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
126. ICLR 2026Making, Not Taking, the Best of N
127. ICLR 2026MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
128. ICLR 2026MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization
129. ICLR 2026Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
130. ICLR 2026Massive Editing for Large Language Models Based on Dynamic Weight Generation
131. ICLR 2026Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement Learning
132. ICLR 2026mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules
133. ICLR 2026Measuring LLM Novelty As The Frontier Of Original And High-Quality Output
134. ICLR 2026MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
135. ICLR 2026Metis: Training LLMs with FP4 Quantization
136. ICLR 2026Modeling Others' Minds as Code
137. ICLR 2026MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
138. ICLR 2026Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages
139. ICLR 2026MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
140. ICLR 2026Next Visual Granularity Generation
141. ICLR 2026NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
142. ICLR 2026Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images
143. ICLR 2026On Code-Induced Reasoning in LLMs
144. ICLR 2026On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation
145. ICLR 2026Once-More: Continuous Self-Correction for Large Language Models via Perplexity-Guided Intervention
146. ICLR 2026OptimSyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation
147. ICLR 2026ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation
148. ICLR 2026Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
149. ICLR 2026Parallel Token Generation for Language Models
150. ICLR 2026Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in 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。