Code Generation

Follow this topic Ask about this topic

Code generation asks how models can turn requests, examples, images, or formal specifications into programs that work in real settings, from short functions to whole repositories and domain-specific software. Common approaches include prompting and fine-tuning, retrieval of relevant code or documentation, constrained decoding, and agents that iteratively run, test, and repair their outputs. Multimodal systems also use rendered interfaces, charts, and diagrams as input or feedback, while reinforcement learning can use execution tests, compilers, or formal verifiers as training signals. Benchmarks such as HumanEval, MBPP, LiveCodeBench, and repository-level tasks show progress, but passing tests or compiling does not guarantee that code meets its intended behavior, visual requirements, security needs, or deployment constraints.

Latest papers

313 papers42 papers in the last four weeks, up 68% on the four weeks before. 0.2% of all new papers.

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
May 22, 2026Zhangyi Hu, Chenhui Liu, Tian Huang +6LLM Self-Refinement Execution-Guided Code Generation
1The Hong Kong University of Science and Technology (Guangzhou) · Institute of Deep Perception Technology, JITRI, Wuxi, China
VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation
May 21, 2026Yifan Bai, Xiaoyang Liu, Zihao Mou +7Code Generation Synthetic Benchmark Generation
School of Mathematical Sciences, Shanghai Jiao Tong University · School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen · School of Mathematics, Jilin University +5
Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents
May 20, 2026Zijian Du, Nathaniel PinckneyElectronic Design Automation Code Generation
NVIDIA · Santa Clara, CA, USA
Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries
May 20, 2026Peng Ding, Rick StevensCode Generation LLM-Based Program Synthesis
University of Chicago · Argonne National Laboratory
Code Generation by Differential Test Time Scaling
May 19, 2026Yifeng He, Ethan Wang, Jicheng Wang +2Differential Testing Execution-Guided Code Generation
University of California, Davis · Wuhan University · University of Hong Kong
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
May 18, 2026Shangzhan Li, Xinyu Yin, Xuanyu Jin +8Large Language Model-Guided Optimization Code Generation
Harbin Institute of Technology, Harbin, China · Xiamen University, Xiamen, China · Tsinghua University, Beijing, China
Constrained Code Generation with Discrete Diffusion
May 16, 2026Lize Shao, Michael Cardei, Zichen Xie +2Constrained Generative Modeling Constrained Decoding
University of Virginia
VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
May 15, 2026Xiaoyan Su, Peijie Dong, Zhenheng Tang +8VLM Evaluation Code Generation
The Hong Kong University of Science and Technology (GuangZhou) · The Hong Kong University of Science and Technology · Huawei Technologies Co., Ltd +2
See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation
May 15, 2026Yuejia Li, Ke He, Junheng Li +5Execution-Guided Code Generation Code Generation
Wuhan University · University of Chinese Academy of Sciences
RTL-BenchMT: Dynamic Maintenance of RTL Generation Benchmark Through Agent-Assisted Analysis and Revision
May 15, 2026Jing Wang, Shang Liu, Hangan Zhou +1LLM Evaluation Electronic Design Automation
Hong Kong University of Science and Technology · Clear Water Bay, Hong Kong
Viverra: Text-to-Code with Guarantees
May 14, 2026Haoze Wu, Rocky Klopfenstein, Keith Farkas +1Code Generation LLM-Based Program Synthesis
Amherst College · Broadcom
Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support
May 14, 2026Alexander Du, Jianjun Ou, Danyang Zhuo +1Automated Program Repair Code Generation
Duke University Durham, NC, USA
Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR
May 14, 2026Plawan Kumar RathConstrained Decoding Code Generation
Meta
HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning
May 13, 2026Qingyun Zou, Feng Yu, Hongshi Tan +3RL for Code Generation Reward Modeling
National University of Singapore
ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation
May 13, 2026Zhongkai Yu, Yichen Lin, Chenyang Zhou +12RL for Code Generation Code Generation
UCSD · Columbia University
Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generation
May 11, 2026Ajay Vikram Periasami, Junlin Wang, Bhuwan DhingraVLM Evaluation Image-to-Code Generation
Duke University
SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications
May 10, 2026Abhinav Goel, Agostino Capponi, Alfio Gliozzo +1Code Generation Code Generation Evaluation
Columbia University New York, NY, USA · IBM T.J. Watson Research Center Yorktown Heights, NY, USA
Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
May 9, 2026Shan Jiang, Zijian Yi, Chenguang ZhuLLM Inference Efficiency Test-Time Optimization
The University of Texas at Austin
VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
May 8, 2026Zichen Xie, Mrigank Pawagi, Yuxin Liu +5Code Generation Formal Verification
University of Virginia · 2Indian Institute of Science · 3Rice University +1
CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
May 8, 2026Shiyang Li, Zijian Zhang, Guangyan Sun +5LLM Evaluation GPU Kernel Optimization
University of Minnesota · Northeastern University
Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate
May 8, 2026Hugh Xuechen Liu, Kıvanç TatarCode Generation Code Generation Evaluation
Chalmers University of Technology and University of Gothenburg
Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks
May 7, 2026Mahdi Erfanian, Nelson Daniel Troncoso, Aashna Garg +4Language Model Error Detection Language Model Generation Evaluation
University of Illinois Chicago · Microsoft
Constraint Decay: The Fragility of LLM Agents in Backend Code Generation
May 7, 2026Francesco Dente, Dario Satriani, Paolo PapottiAI Coding Agents Code Generation
EURECOM, France · University of Basilicata, Italy
The Single-File Test: A Longitudinal Public-Interface Evaluation of First-Output LLM Web Generation with Social Reach Tracking
May 6, 2026Diego Cabezas PalaciosCode Generation Code Generation Evaluation
Architectural Constraints Alignment in AI-assisted, Platform-based Service Development
May 6, 2026Julius Irion, Moritz Leugers, Paul Hartwig +5Software Engineering Code Generation
1Technische Universität Berlin, Germany · 2Information Systems Engineering, Technische Universität Berlin, Germany
LLM-Assisted Repository-Level Generation with Structured Spec-Driven Engineering
May 4, 2026Shuzhao Feng, Boqi Chen, Brett H Meyer +1Code Generation Repository-Level Code Generation
McGill University · Montreal, Quebec, Canada · University of Ottawa +1
GA-VisAgent: A Multi-Agent application for code generation and visualization in interactive learning
May 2, 2026Wang Jian, Zhou Jianbo, Xiong Yuhao +4Code Generation LLM-Based Program Synthesis
School of Geography, Nanjing Normal University, Nanjing 210023, Jiangsu, China · School of Environment, Nanjing Normal University, Nanjing 210023, Jiangsu, China · Key Laboratory of Virtual Geographic Environment, Ministry of Education,2026 Nanjing Normal University, Nanjing 210023, Jiangsu, China +2
BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis
May 1, 2026Massimo Rondelli, Francesco Pivi, Maurizio GabbrielliRetrieval-Augmented Generation 3D Asset Generation
University of Bologna, Bologna, Italy · Ferrari S.p.A., Maranello, Italy
From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation
Apr 30, 2026Guang Yang, Xing Hu, Xiang Chen +1Multimodal Grounding Code Generation
State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China · School of Artificial Intelligence and Computer Science, Nantong University, Nantong, China
TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models
Apr 30, 2026Amirreza Esmaeili, Fatemeh FardLLM Interpretability Code Generation
University of British Columbia Kelowna, British Columbia, Canada

May 22, 2026J/K move · Enter open · S save

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test

Zhangyi Hu, Chenhui Liu, Tian Huang, Jindong Li+5

1The Hong Kong University of Science and Technology (Guangzhou) · Institute of Deep Perception Technology, JITRI, Wuxi, China

LLM Self-Refinement Execution-Guided Code Generation Code Generation Test-Time Scaling Automated Test Generation LLM Code Generation

Open paper AskPDF arXiv

Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.