Code Generation papers, 2023–2026

Key findings

• Code Generation went from 210 papers in 2023 to 860 in 2026, roughly 4.1x in three years.
• NeurIPS publishes the most Code Generation work: 630 papers from 2023 to 2026, 29% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 93 in 2026.
• Among the 5 topics under Natural Language, it ranks #1 by 2026 paper count; the fastest grower in the group, Retrieval-Augmented Generation, is up 5.4x versus 4.1x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Code Generation papers

395 papers, page 2 of 8

51. ICML 2026Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
52. ICML 2026Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads
53. ICML 2026Efficient Skill Grounding via Code Refactoring with Small Language Models
54. ICML 2026Efficient Synthetic Network Generation via Latent Embedding Reconstruction
55. ICML 2026EGG: An Expert-Guided Agent Framework for Kernel Generation
56. ICML 2026Escaping Whack-a-Mole: Optimizing Documentation as Repo-Specific Playbooks for Coding Agents
57. ICML 2026Expert-level Leaf Cell Layout Generation via Preference-Optimized LLM
58. ICML 2026ExVerus: Verus Proof Repair via Counterexample Reasoning
59. ICML 2026FairGB: A Fair Granular-Ball Generation Method for Data Classification
60. ICML 2026Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation
61. ICML 2026FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
62. ICML 2026FormAct: Agentic Source Editing for Rich-Format Document Generation
63. ICML 2026FormulaCode: Evaluating Agentic Optimization on Large Codebases
64. ICML 2026From Diagrams to Code: Multilingual Programming with Visual Design
65. ICML 2026From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion
66. ICML 2026From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
67. ICML 2026Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents
68. ICML 2026FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds
69. ICML 2026GAUSS: Graph-Assisted Uncertainty Quantification using Structure and Semantics for Long-Form Generation in LLMs
70. ICML 2026GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design
71. ICML 2026Generative Visual Code Mobile World Models
72. ICML 2026GOCM: Single-Step Graph Outlier Synthesis via Origin Consistency Model
73. ICML 2026Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation
74. ICML 2026Gradient-Aware Scheduling: Coupling Curriculum and Staleness for Async Reinforcement Learning
75. ICML 2026Gram2Token: Enabling Run-time GPU-Native Grammar-Constrained Decoding for LLMs
76. ICML 2026GXPO: Group Cross-Lingual Relative Policy Optimization for Code Generation
77. ICML 2026How Do Language Models Speak Languages? A Case Study on Unintended Code-Switching
78. ICML 2026How much can language models memorize?
79. ICML 2026How2Everything: Mining the Web for How-to Procedures to Evaluate and Improve LLMs
80. ICML 2026Hybrid Policy Distillation for LLMs
81. ICML 2026HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds
82. ICML 2026IDLM: Inverse-distilled Diffusion Language Models
83. ICML 2026In-Context Generation with Regional Constraints for Instructional Video Editing
84. ICML 2026InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames
85. ICML 2026InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
86. ICML 2026Innovation: An Almost Characterization of Hallucination
87. ICML 2026Insertion Based Sequence Generation with Learnable Order Dynamics
88. ICML 2026InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
89. ICML 2026InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation
90. ICML 2026Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
91. ICML 2026Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
92. ICML 2026KernelFoundry: Hardware-Aware Evolutionary GPU Kernel Optimization
93. ICML 2026Language Generation with Feedback: Queries and Mistakes
94. ICML 2026Language Generation with Replay: A Learning-Theoretic View of Model Collapse
95. ICML 2026Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
96. ICML 2026Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
97. ICML 2026Learning Gaussian Mixture-distributed Prototypes for 3D Scene Graph Generation from RGB-D Sequences
98. ICML 2026Learning Unmasking Policies for Diffusion Language Models
99. ICML 2026LECTOR: Joint Learning of Scientific Reasoning Graphs and Introduction Generation
100. ICML 2026LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

FAQ

How many Code Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,161 in total: 210 in 2023, 446 in 2024, 645 in 2025, 860 in 2026.

How many Code Generation papers are at NeurIPS 2026?

NeurIPS 2026 has 236 Code Generation papers, versus 230 the year before.

How many Code Generation papers are at ICLR 2026?

ICLR 2026 has 241 Code Generation papers, versus 164 the year before.

How many Code Generation papers are at ICML 2026?

ICML 2026 has 174 Code Generation papers, versus 79 the year before.

How many Code Generation papers are at CVPR 2026?

CVPR 2026 has 209 Code Generation papers, versus 172 the year before.

Which conference publishes the most Code Generation papers?

NeurIPS, with 630 papers from 2023 to 2026.