代码生成论文趋势 2023–2026
程序合成与代码 LLM
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,161 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 29 | 55 | 31 | 95 | 210 |
| 2024 | 135 | 66 | 111 | 134 | 446 |
| 2025 | 230 | 164 | 79 | 172 | 645 |
| 2026 | 236 | 241 | 174 | 209 | 860 |
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 2,161 篇，第 5 / 44 页
- CVPR 2026VecGlypher Unified Vector Glyph Generation with Language Models
- CVPR 2026ViLearn Accelerating Training Convergence of Image-to-3D Generation via Visibility Learning
- CVPR 2026VisiLock Authorizing Instruction-based Image editing with Dual Score Distillation
- CVPR 2026VVS Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial
- CVPR 2026Widget2Code From Visual Widgets to UI Code via Multimodal LLMs
- CVPR 2026WonderZoom Multi-Scale 3D World Generation
- CVPR 2026You Only Erase Once Erasing Anything without Bringing Unexpected Content
- CVPR 2026Your Classifier Can Do More Towards Balancing the Gaps in
- CVPR 2026Zero-Shot Image Denoising via Hybrid Prior-Guided Pseudo Sample Generation
- ICLR 2026$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
- ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
- ICLR 2026A Noise is Worth Diffusion Guidance
- ICLR 2026A Problem-Oriented Perspective and Anchor Verification for Code Optimization
- ICLR 2026Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter
- ICLR 2026Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
- ICLR 2026AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions
- ICLR 2026AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
- ICLR 2026Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment
- ICLR 2026AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
- ICLR 2026Algorithm Generation via Creative Ideation
- ICLR 2026Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
- ICLR 2026All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
- ICLR 2026An Agentic Framework with LLMs for Solving Complex Vehicle Routing Problems
- ICLR 2026Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
- ICLR 2026Any-Order Any-Subset AutoRegressive Model
- ICLR 2026Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation
- ICLR 2026APT: Towards Universal Scene Graph Generation via Plug-in Adaptive Prompt Tuning
- ICLR 2026Aria: an Agent for Retrieval and Iterative Auto-Formalization via Dependency Graph
- ICLR 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
- ICLR 2026ATGen: Adversarial Reinforcement Learning for Test Case Generation
- ICLR 2026Attention Is All You Need for KV Cache in Diffusion LLMs
- ICLR 2026Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
- ICLR 2026AutoCode: LLMs as Problem Setters for Competitive Programming
- ICLR 2026AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators
- ICLR 2026Automated Formalization via Conceptual Retrieval-Augmented LLMs
- ICLR 2026Autoregressive Image Generation with Randomized Parallel Decoding
- ICLR 2026BAR: Refactor the Basis of Autoregressive Visual Generation
- ICLR 2026Benchmarking Overton Pluralism in LLMs
- ICLR 2026Best-of-Infinity: Asymptotic Performance of Test-Time Compute
- ICLR 2026Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning
- ICLR 2026BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
- ICLR 2026BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions
- ICLR 2026Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
- ICLR 2026Bures-Wasserstein Flow Matching for Graph Generation
- ICLR 2026Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
- ICLR 2026Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
- ICLR 2026Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
- ICLR 2026Cautious Optimizers: Improving Training with One Line of Code
- ICLR 2026ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
- ICLR 2026CLARC: C/C++ Benchmark for Robust Code Search
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查代码生成在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "code-generation"}
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。