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 13 / 44 页
- ICML 2026Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
- ICML 2026STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics–Physics Dual System
- ICML 2026SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
- ICML 2026SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
- ICML 2026Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
- ICML 2026Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
- ICML 2026TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation
- ICML 2026The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
- ICML 2026The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation
- ICML 2026The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
- ICML 2026Threat2Traffic: Multi-Agent Environment Synthesis for Malware Traffic Generation from Threat Intelligence
- ICML 2026Towards Functional Correctness of Large Code Models with Selective Generation
- ICML 2026Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding
- ICML 2026TritonGym: A Benchmark for Agentic LLM Workflows in Triton GPU Code Generation
- ICML 2026TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
- ICML 2026UniCode: Augmenting Evaluation for Code Reasoning
- ICML 2026UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
- ICML 2026Variational Bayesian Flow Network for Graph Generation
- ICML 2026VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
- ICML 2026VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification
- ICML 2026WeightCLIP: Aligning Datasets and Models for Weight Space Learning
- ICML 2026Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer
- ICML 2026Winformer: Transcending Pairwise Similarity for Time-series Generation
- ICML 2026With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots
- NeurIPS 2026$\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics
- NeurIPS 2026$SE(2)$-Aware Conditional Distribution Transport for Vehicle Trajectory Generation
- NeurIPS 20263DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
- NeurIPS 2026A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models
- NeurIPS 2026A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
- NeurIPS 2026A Theoretical Analysis of Test-Driven Code Generation
- NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
- NeurIPS 2026AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody Generation
- NeurIPS 2026AccelEval: A Whole-Program Benchmark for LLM-Generated CPU-to-GPU Code Acceleration
- NeurIPS 2026AdaPCLA: Curriculum Prior Internalization For Long-Tailed Longitudinal EHR Generation
- NeurIPS 2026AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
- NeurIPS 2026Anchoring LLM-based Chest X-ray Report Generation via Diffusion Language Planning
- NeurIPS 2026Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
- NeurIPS 2026Answering At Any Cost: Frontier LLMs Are Consequence-Insensitive
- NeurIPS 2026Antibody Generation via Redistributed Latent Diffusion
- NeurIPS 2026APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
- NeurIPS 2026Articraft: An Agentic System for Scalable Articulated 3D Asset Generation
- NeurIPS 2026Ask-E: An Environment for Calibrated Question Generation
- NeurIPS 2026Assessing Sample Quality in Conditional Generation under Compositional Shift
- NeurIPS 2026Benchmarking and Optimizing Multimodal Structured Generation: The OracleGraph Dataset and PRISM Framework
- NeurIPS 2026Benchmarking Risk Attitudes of LLMs
- NeurIPS 2026Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
- NeurIPS 2026Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation
- NeurIPS 2026Beyond Generation: Unlocking Discriminative Representations from Diffusion Models
- NeurIPS 2026Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Image Generation
- NeurIPS 2026Breaking the Quality–Privacy Tradeoff in Tabular Data Generation via In-Context Learning
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。