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 395 篇，第 3 / 8 页

101. ICML 2026LitReview Arena: Evaluating Literature Review Agents with Battle-style Peer Review Platform
102. ICML 2026LLM-Guided Loop Bound Generation for Program Termination Verification
103. ICML 2026LLMs Lean on Priors, Not Programming Language Semantics
104. ICML 2026Locally Coherent Parallel Decoding in Diffusion Language Models
105. ICML 2026MALICE: Memory-aware Loop Invariants Generation on Symbolic Execution Traces
106. ICML 2026MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
107. ICML 2026MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
108. ICML 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
109. ICML 2026Mosaic: Unlocking Over 30$\times$ Context Length for Diffusion LLMs Inference via Global Memory Planning and Dynamic Peak Taming
110. ICML 2026Motion-Aware Caching for Efficient Autoregressive Video Generation
111. ICML 2026MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation
112. ICML 2026NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
113. ICML 2026One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
114. ICML 2026OpenSage: Self-programming Agent Generation Engine
115. ICML 2026PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic Alignment
116. ICML 2026Pair2Scene: Learning Local Object Relations for Procedural Scene Generation
117. ICML 2026ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
118. ICML 2026Periodic Bayesian Flow Networks with Additive Accuracy
119. ICML 2026PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
120. ICML 2026PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation
121. ICML 2026Planar Symmetric Pattern Generation
122. ICML 2026PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization
123. ICML 2026Poison with Style: A Practical Poisoning Attack on Code Large Language Models
124. ICML 2026PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
125. ICML 2026ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling
126. ICML 2026Propose, Solve, Verify: Self-Play Through Formal Verification
127. ICML 2026Q-Delta: Beyond Key–Value Associative State Evolution
128. ICML 2026Q-Tab: Quantized Tabular Data Generator
129. ICML 2026QiMeng-LibBench: Benchmarking LLM Agents for Library-Scale Cross-Architecture Migration
130. ICML 2026Random Selection Reveals Implicit Knowledge Consensus in Code Generation
131. ICML 2026Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
132. ICML 2026Regression Language Models for Code
133. ICML 2026Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation
134. ICML 2026Rethinking Code Complexity Through the Lens of Large Language Models
135. ICML 2026Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
136. ICML 2026Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation
137. ICML 2026Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
138. ICML 2026Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
139. ICML 2026S-Quant: Rethinking Weight Quantization with Seed-Based Generation
140. ICML 2026Scaling Agentic Verifier for Competitive Coding
141. ICML 2026Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
142. ICML 2026ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
143. ICML 2026Score Based Error Correcting Code Decoder
144. ICML 2026SecCodePRM: A Process Reward Model for Code Security
145. ICML 2026Self-Supervised Learning as Discrete Communication
146. ICML 2026SemRep : Generative Code Representation Learning with Code Transformations
147. ICML 2026Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control
148. ICML 2026SimGFM: Simplifying Discrete Flow Matching for Graph Generation
149. ICML 2026Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
150. ICML 2026SPADA: A Verifiable Test-Driven Agent for Controllable Parametric CAD Assembly 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。