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 630 篇，第 9 / 13 页

401. NeurIPS 2025Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
402. NeurIPS 2025Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
403. NeurIPS 2025Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
404. NeurIPS 2025RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation
405. NeurIPS 2025Repo2Run: Automated Building Executable Environment for Code Repository at Scale
406. NeurIPS 2025Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
407. NeurIPS 2025ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
408. NeurIPS 2025Rethinking Verification for LLM Code Generation: From Generation to Testing
409. NeurIPS 2025Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
410. NeurIPS 2025RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net
411. NeurIPS 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
412. NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
413. NeurIPS 2025Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures
414. NeurIPS 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
415. NeurIPS 2025Scaling Diffusion Transformers Efficiently via $\mu$P
416. NeurIPS 2025Scaling Up Parameter Generation: A Recurrent Diffusion Approach
417. NeurIPS 2025SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
418. NeurIPS 2025SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAI
419. NeurIPS 2025SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
420. NeurIPS 2025Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs
421. NeurIPS 2025SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
422. NeurIPS 2025ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation
423. NeurIPS 2025SimpleStrat: Diversifying Language Model Generation with Stratification
424. NeurIPS 2025SnapMoGen: Human Motion Generation from Expressive Texts
425. NeurIPS 2025Sparse Image Synthesis via Joint Latent and RoI Flow
426. NeurIPS 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
427. NeurIPS 2025SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
428. NeurIPS 2025Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
429. NeurIPS 2025Steering When Necessary: Flexible Steering Large Language Models with Backtracking
430. NeurIPS 2025Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
431. NeurIPS 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
432. NeurIPS 2025SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
433. NeurIPS 2025Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency
434. NeurIPS 2025Synthetic Series-Symbol Data Generation for Time Series Foundation Models
435. NeurIPS 2025Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
436. NeurIPS 2025TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles
437. NeurIPS 2025Text-to-Code Generation for Modular Building Layouts in Building Information Modeling
438. NeurIPS 2025The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
439. NeurIPS 2025The Curse of Depth in Large Language Models
440. NeurIPS 2025Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
441. NeurIPS 2025Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
442. NeurIPS 2025Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
443. NeurIPS 2025Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
444. NeurIPS 2025Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
445. NeurIPS 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
446. NeurIPS 2025Training Language Models to Generate Quality Code with Program Analysis Feedback
447. NeurIPS 2025Training-Free Constrained Generation With Stable Diffusion Models
448. NeurIPS 2025Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection
449. NeurIPS 2025TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
450. NeurIPS 2025Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

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。