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

164 papers, page 2 of 4

51. ICLR 2025Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning
52. ICLR 2025FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
53. ICLR 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
54. ICLR 2025FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
55. ICLR 2025Forking Paths in Neural Text Generation
56. ICLR 2025FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
57. ICLR 2025FreeVS: Generative View Synthesis on Free Driving Trajectory
58. ICLR 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
59. ICLR 2025GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation
60. ICLR 2025Generating CAD Code with Vision-Language Models for 3D Designs
61. ICLR 2025GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
62. ICLR 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
63. ICLR 2025Guaranteed Generation from Large Language Models
64. ICLR 2025Gumbel Counterfactual Generation From Language Models
65. ICLR 2025How efficient is LLM-generated code? A rigorous & high-standard benchmark
66. ICLR 2025HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction
67. ICLR 2025HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation
68. ICLR 2025Improving Uncertainty Estimation through Semantically Diverse Language Generation
69. ICLR 2025InCoDe: Interpretable Compressed Descriptions For Image Generation
70. ICLR 2025Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
71. ICLR 2025InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
72. ICLR 2025InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
73. ICLR 2025IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities
74. ICLR 2025Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
75. ICLR 2025It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
76. ICLR 2025IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
77. ICLR 2025Large Language Models are Interpretable Learners
78. ICLR 2025LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
79. ICLR 2025Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
80. ICLR 2025Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
81. ICLR 2025Let the Code LLM Edit Itself When You Edit the Code
82. ICLR 2025LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
83. ICLR 2025Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
84. ICLR 2025LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
85. ICLR 2025LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
86. ICLR 2025MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
87. ICLR 2025MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
88. ICLR 2025MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
89. ICLR 2025MagicPIG: LSH Sampling for Efficient LLM Generation
90. ICLR 2025MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds
91. ICLR 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
92. ICLR 2025McEval: Massively Multilingual Code Evaluation
93. ICLR 2025Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
94. ICLR 2025Measuring memorization in RLHF for code completion
95. ICLR 2025MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
96. ICLR 2025Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
97. ICLR 2025NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
98. ICLR 2025ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
99. ICLR 2025OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
100. ICLR 2025OmniKV: Dynamic Context Selection for Efficient Long-Context 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.