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

526 papers, page 4 of 11

151. ICLR 2026PCB-Bench: Benchmarking LLMs for Printed Circuit Board Placement and Routing
152. ICLR 2026pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
153. ICLR 2026PLAGUE: Plug-and-play Framework for Lifelong Adaptive Generation of Multi-turn Exploits
154. ICLR 2026Plan then Act: Bi-level CAD Command Sequence Generation
155. ICLR 2026Planned Diffusion
156. ICLR 2026Planner Aware Path Learning in Diffusion Language Models Training
157. ICLR 2026POEMetric: The Last Stanza of Humanity
158. ICLR 2026PolyGraph Discrepancy: a classifier-based metric for graph generation
159. ICLR 2026Positional Encoding Field
160. ICLR 2026Precise and Interpretable Editing of Code Knowledge in Large Language Models
161. ICLR 2026PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
162. ICLR 2026Programming with Pixels: Can Computer-Use Agents do Software Engineering?
163. ICLR 2026Prompt-MII: Meta-Learning Instruction Induction for LLMs
164. ICLR 2026ProReGen: Progressive Residual Generation under Attribute Correlations
165. ICLR 2026QuRL: Rubrics As Judge For Open-Ended Question Answering
166. ICLR 2026R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
167. ICLR 2026Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
168. ICLR 2026RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
169. ICLR 2026Reassessing Layer Pruning in LLMs: New Insights and Methods
170. ICLR 2026RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data
171. ICLR 2026RECODE: A Benchmark for Research Code DEvelopment with Interactive Human Feedback
172. ICLR 2026RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
173. ICLR 2026RefineStat: Efficient Exploration for Probabilistic Program Synthesis
174. ICLR 2026ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
175. ICLR 2026Reinforcement Learning from Dynamic Critic Feedback for Free-Form Generations
176. ICLR 2026Rescue: Retrieval Augmented Secure Code Generation
177. ICLR 2026Rethinking Code Similarity for Automated Algorithm Design with LLMs
178. ICLR 2026Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
179. ICLR 2026Retrospective Sparse Attention for Efficient Long-Context Generation
180. ICLR 2026ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
181. ICLR 2026Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
182. ICLR 2026ROSETTA: Constructing Code-Based Reward from Unconstrained Language Preference
183. ICLR 2026RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
184. ICLR 2026SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
185. ICLR 2026SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
186. ICLR 2026Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
187. ICLR 2026SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
188. ICLR 2026SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention
189. ICLR 2026Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
190. ICLR 2026Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization
191. ICLR 2026Scaling Behavior of Discrete Diffusion Language Models
192. ICLR 2026Sci2Pol: Evaluating and Fine-tuning LLMs on Scientific-to-Policy Brief Generation
193. ICLR 2026SciTS: Scientific Time Series Understanding and Generation with LLMs
194. ICLR 2026SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
195. ICLR 2026ShapeGen4D: Towards High Quality 4D Shape Generation from Videos
196. ICLR 2026ShieldedCode: Learning Robust Representations for Virtual Machine Protected Code
197. ICLR 2026ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
198. ICLR 2026Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People
199. ICLR 2026SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
200. ICLR 2026SketchEvo: Leveraging Drawing Dynamics for Enhanced Image Synthesis

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.