LLM Code Generation

LLM: Large Language Model

This field studies how large language models generate, edit, translate, and test programs from natural-language instructions, examples, or existing code. Common approaches include prompting and retrieval, fine-tuning and reinforcement learning, constrained decoding, and agentic loops that use execution, tests, or static analysis to refine outputs. Evaluations range from HumanEval, MBPP, and LiveCodeBench to repository-level and domain-specific tasks, increasingly measuring security, efficiency, and adherence to requirements alongside whether code runs. Models have improved on standard benchmarks, but reliability on unfamiliar APIs, complex projects, specialized languages, and implicit requirements remains a challenge, as do trade-offs among correctness, safety, cost, and maintainability.

Latest papers

314 papers23 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters
Apr 1, 2026Zhensu Sun, Zhihao Lin, Zhi Chen +4LLM Inference Acceleration Pipeline Parallelism
Singapore Management University · Beihang University
Unified Architecture Metamodel of Information Systems Developed by Generative AI
Mar 31, 2026Oleg Grynets, Vasyl LyashkevychModel-Driven Engineering Software Engineering
EPAM Systems, McLean, Virginia, USA · EPAM Systems, Lviv, Ukraine
Think Anywhere in Code Generation
Mar 31, 2026Xue Jiang, Tianyu Zhang, Ge Li +8LLM Code Generation Efficient Language Model Reasoning
School of Computer Science, Peking University · Tongyi Lab, Alibaba Group
Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus
Mar 31, 2026Huan Zhang, Wei Cheng, Wei HuLanguage Model Self-Improvement LLM Code Generation
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · State Key Laboratory for Novel Software Technology, National Institute of Healthcare Data Science, Nanjing University, Nanjing, China
BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations
Mar 30, 2026Kaushitha Silva, Srinath PereraLLM Code Generation LLM-Based Program Synthesis
WSO2 Santa Clara, CA, USA
Q-Bridge: Code Translation for Quantum Machine Learning via LLMs
Mar 29, 2026Runjia Zeng, Priyabrata Senapati, Ruixiang Tang +2Quantum Machine Learning LLM Code Generation
Rochester Institute of Technology, USA · Kent State University, USA · Rutgers University, USA
AstraAI: LLMs, Retrieval, and AST-Guided Assistance for HPC Codebases
Mar 28, 2026Mahesh Natarajan, Xiaoye Li, Weiqun ZhangRetrieval-Augmented Code Generation Code Generation
Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
IncreRTL: Traceability-Guided Incremental RTL Generation under Requirement Evolution
Mar 26, 2026Luanrong Chen, Renzhi Chen, Xinyu Li +3RTL Code Generation Code Generation
National University of Defense Technology, Changsha, China · Defense Innovation Institute, Academy of Military Sciences, Beijing, China · Qiyuan Lab, Beijing, China
LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops
Mar 24, 2026Ravin Ravi, Dylan Bradshaw, Stefano Ruberto +2LLM Code Generation LLM Self-Refinement
University of Auckland, Auckland, New Zealand · JRC European Commission, Ispra, Italy · King’s College London, London, United Kingdom
Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?
Mar 23, 2026Oscar Novo, Oscar Bastidas-Jossa, Alberto Calvo +2LLM Code Generation Knowledge Augmentation for Language Models
Quantum Computing Research, QCentroid, 48001, Bilbao, Spain
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation
Mar 18, 2026Jiawei Zhou, Chi Zhang, Xiang Feng +6Image-to-Code Generation Code Generation
School of Computer Science, Wuhan University, Wuhan, China · Independent Researcher, China · Xidian University, Xi’an, China +1
InCoder-32B: Code Foundation Model for Industrial Scenarios
Mar 17, 2026Jian Yang, Wei Zhang, Jiajun Wu +25Compiler Optimization Code Language Models
Beihang University · IQuest Research · Shanghai Jiao Tong University +6
IQuest-Coder-V1 Technical Report
Mar 17, 2026Jian Yang, Wei Zhang, Shawn Guo +35Recurrent Language Models Code Language Models
Exploring different approaches to customize language models for domain-specific text-to-code generation
Mar 17, 2026Luís Freire, Fernanda A. Andaló, Nicki Skafte DetlefsenCode Generation LLM Code Generation
Technical University of Denmark · The LEGO Group
From Natural Language to Executable Option Strategies via Large Language Models
Mar 17, 2026Haochen Luo, Zhengzhao Lai, Junjie Xu +4Algorithmic Trading Semantic Parsing
City University of Hong Kong · The Chinese University of Hong Kong (Shenzhen) · University of Science and Technology of China +1
GASP: Guided Asymmetric Self-Play For Coding LLMs
Mar 16, 2026Swadesh Jana, Cansu Sancaktar, Tomáš Daniš +3Language Model Self-Improvement LLM Code Generation
University of Tübingen · Max Planck Institute for Intelligent Systems · ELLIS Institute Tübingen +1
Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
Mar 16, 2026Vatsal Gupta, Darshan SreenivasamurthyAccess Control LLM-Based Program Synthesis
Apple Cupertino, California, USA
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
Mar 16, 2026Aozhe Wang, Yuchen Yan, Nan Zhou +5LLM Code Generation RL for Code Generation
Zhejiang University
SEMAG: Self-Evolutionary Multi-Agent Code Generation
Mar 16, 2026Yulin Peng, Haowen Hou, Xinxin Zhu +2Agentic Code Generation LLM Code Generation
College of Computer Science and Software Engineering, Shenzhen University, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), China · School of Information Technology, Carleton University, Canada
To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
Mar 16, 2026Yitong Zhang, Chengze Li, Ruize Chen +4LLM Code Generation Synthetic Data Generation for Language Models
College of AI, Tsinghua University, Beijing, China · Fitten Tech Co., Ltd., Beijing, China · School of Computer Science, Nanjing University, Nanjing, China +3
CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
Mar 15, 2026Junhang Cheng, Fang Liu, Jia Li +3Code Generation LLM Code Generation
Beihang University, Beijing, China · Wuhan University, Wuhan, China
QiMeng-CodeV-SVA: Training Specialized LLMs for Hardware Assertion Generation via RTL-Grounded Bidirectional Data Synthesis
Mar 15, 2026Yutong Wu, Chenrui Cao, Pengwei Jin +6SystemVerilog Assertion Generation Formal Hardware Verification
SKL of Processors, Institute of Computing Technology, CAS Beijing, China · University of Chinese Academy of Sciences Beijing, China · University of Science and Technology of China Hefei, Anhui, China +1
AeroGen: Structured Prompting for Low-Code Drone-as-a-Service Mission Composition
Mar 15, 2026Kautuk Astu, Yogesh SimmhanLLM-Based Program Synthesis LLM Code Generation
Indian Institute of Science, Bangalore 560012 India
Design-Specification Tiling for ICL-based CAD Code Generation
Mar 13, 2026Yali Du, San-Zhuo Xi, Hui Sun +1In-Context Learning Text-to-CAD Generation
National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China
MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?
Mar 12, 2026Xingze Zou, Jing Wang, Yuhua Zheng +8LLM Code Generation Efficient Neural Network Inference
Zhejiang University · Westlake University · HKUST +2
Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
Mar 11, 2026Maximilian Wendlinger, Daniel Kowatsch, Konstantin Böttinger +1Secure Code Generation Code Language Models
Cognitive Security Technologies Fraunhofer Institute for Applied and Integrated Security Garching near Munich, Germany
H2LooP Spark Preview: Continual Pretraining of Large Language Models for Low-Level Embedded Systems Code
Mar 11, 2026Amit Singh, Vedant Nipane, Pulkit Agrawal +2Code Language Models LLM Code Generation
Utility Function is All You Need: LLM-based Congestion Control
Mar 11, 2026Neta Rozen-Schiff, Liron Schiff, Stefan SchmidLarge Language Model-Guided Optimization LLM Code Generation
TU Berlin · Akamai Technologies · TU Berlin, Weizenbaum Institute & Fraunhofer SIT
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages
Mar 10, 2026Aman Sharma, Paras ChopraLLM Evaluation LLM Code Generation
Lossfunk
Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models
Mar 8, 2026Zongqian Li, Shaohan Huang, Zewen Chi +5RL for Code Generation LLM Code Generation
Microsoft Research · University of Cambridge · Princeton University

Apr 1, 2026J/K move · Enter open · S save

Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters

Zhensu Sun, Zhihao Lin, Zhi Chen, Chengran Yang+3

Singapore Management University · Beihang University

LLM Inference Acceleration Pipeline Parallelism LLM Code Generation

Open paper AskPDF arXiv

Current LLM systems are increasingly equipped with a code interpreter that executes generated code to obtain results. This works serially: the model first generates the complete code, then an interpreter executes it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. Our key observation is that an LLM, unlike a human developer, emits code tokens left to right and does not backtrack over what it has already written. This makes it possible to start executing a piece of code while later tokens are still being generated. We formalize this parallel execution paradigm, modeling it as a three-stage pipeline of generation, detection, and execution, and derive closed-form latency bounds that characterize its speedup potential and operating regimes. We then present EAGER, a concrete implementation featuring AST-based chunking, dynamic batching with gated execution, and early error interruption. We evaluate EAGER across four benchmarks, seven LLMs, and three execution environments. The overlap mechanism hides almost all execution behind generation, reducing the non-overlapped portion of execution time by up to 99.8% and cutting end-to-end latency by up to 37.3% on error-free runs.