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.

SAGE: Multi-Agent Self-Evolution for LLM Reasoning
Mar 16, 2026Yulin Peng, Xinxin Zhu, Chenxing Wei +4LLM Reasoning Self-Training for Language Models
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
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
Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging
Mar 14, 2026Zhilin Liu, Ye Huang, Ting Xie +3Code Generation Code Generation Benchmarks
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China
Visual-ERM: Reward Modeling for Visual Equivalence
Mar 13, 2026Ziyu Liu, Shengyuan Ding, Xinyu Fang +7Reward Modeling RL for VLMs
Shanghai Jiao Tong University · Shanghai AI Laboratory · Fudan University +1
QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions
Mar 12, 2026Jiayin Lei, Ming Ma, Yunxi Duan +2Instruction-Tuning Data Selection Code Generation
Beijing University of Technology, Beijing, 100124, China · Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China · University of Chinese Academy of Sciences, Beijing, 100049, China +1
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges
Mar 12, 2026Zi-Han Wang, Lam Nguyen, Zhengyang Zhao +4Computational Creativity Creativity Assessment
Southern University of Science and Technology · Tsinghua University · Xi’an Jiaotong University +3
DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation
Mar 12, 2026Xinhao Huang, Jinke Yu, Wenhao Xu +5Code Generation Vision-Language Models
HKUST (Guangzhou), Guangzhou, China · Alibaba Group, Hangzhou, China · HKUST, Hong Kong, China +2
CodePercept: Code-Grounded Visual STEM Perception for MLLMs
Mar 11, 2026Tongkun Guan, Zhibo Yang, Jianqiang Wan +10Image-to-Code Generation Visually Grounded Reasoning
MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University · Qwen Team · Beijing Institute of Technology +2
EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages
Mar 10, 2026Aman Sharma, Paras ChopraLLM Evaluation LLM Code Generation
Lossfunk
Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis
Mar 9, 2026Ethan Young, Zichun Wang, Aiden Taylor +6Code Generation VLM Evaluation
Marshall University · West Virginia State University
A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling
Mar 8, 2026Ziheng Geng, Jiachen Liu, Ran Cao +3Structural Engineering Multi-Agent LLM Systems
Department of Civil and Architectural Engineering, University of Miami, Coral Gables, FL 33146, USA · HBC Engineering Company, Miami, FL 33178, USA · College of Civil Engineering, Hunan University, Changsha, 410082, China +3
KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation
Mar 8, 2026Jiazhen Kang, Yuchen Lu, Chen Jiang +6Code Generation Graph Retrieval-Augmented Generation
Southeast University, Nanjing, China · ByteDance Ltd., China · Monash University, Melbourne, Australia
SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms
Mar 5, 2026Longkun Xu, Xiaochun Zhang, Qiantu Tuo +1Time Series Forecasting Code Generation
Ecoflow Inc.
Python Bindings for a Large C++ Robotics Library: The Case of OMPL
Mar 4, 2026Weihang Guo, Theodoros Tyrovouzis, Lydia E. KavrakiCode Generation LLM Code Generation
Department of Computer Science, Rice University, Houston TX, USA · Ken Kennedy Institute at Rice University
CONCUR: Benchmarking LLMs for Concurrent Code Generation
Mar 4, 2026Jue Huang, Tarek Mahmud, Corina Pasareanu +1Code Generation Evaluation Code Generation Benchmarks
The University of Queensland · Texas A&M University - Kingsville · Carnegie Mellon University
Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation
Mar 3, 2026Vaishak KumarCode Generation for Robotics Robot Policy Learning
General Bionix, Inc.
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Mar 3, 2026Guoxin Chen, Fanzhe Meng, Jiale Zhao +12Retrieval-Augmented Code Generation Software Engineering Benchmarks
An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
Mar 3, 2026Sophie Weidmann, Fernando CastorCode Generation LLM Code Generation
University of Twente, Enschede, The Netherlands
ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
Mar 3, 2026Liu Yang, Zeyu Nie, Andrew Liu +4High-Performance Computing Code Generation
Department of Computer Science, Yale University, New Haven, CT, USA · Google DeepMind, Mountain View, CA, USA
Test-Driven Agentic Framework for Reliable Robot Controller
Feb 28, 2026Shivanshu Tripathi, Reza Akbarian Bafghi, Maziar RaissiRobotic Control Code Generation
Department of Electrical and Computer Engineering, University of California, Riverside · Department of Computer Science, University of Colorado, Boulder · Department of Mathematics, University of California, Riverside
Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution
Feb 27, 2026Tinglin Huang, Bo Chen, Xiao Zhang +2Synthetic Data Generation for Language Models Code Generation
Yale University · ByteDance Seed
ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation
Feb 24, 2026Nabin OliCitation Hallucination Code Generation
Sunway College Kathmandu, Birmingham City University
From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation
Feb 24, 2026Linus Bantel, Moritz Strack, Alexander Strack +1Code Generation LLM Code Generation
Institute for Parallel and Distributed Systems, University of Stuttgart, Stuttgart, Germany
CodeGENCAT: Generative Computerized Adaptive Testing for Open-ended Coding Problems
Feb 23, 2026Wanyong Feng, Alexander Scarlatos, Ruochen Sun +1Computerized Adaptive Testing Educational Assessment
University of Massachusetts Amherst · Independent Researcher
VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
Feb 22, 2026Joan Rodriguez, Haotian Zhang, Abhay Puri +14VLM Evaluation Code Generation
Mila, Quebec AI Institute · ÉTS Montréal · QuiverAI +11
GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning
Feb 20, 2026Fali Wang, Chenglin Weng, Xianren Zhang +3LLM Reasoning with Graphs Graph Reasoning
The Pennsylvania State University, University Park, Pennsylvania, USA · Michigan State University, East Lansing, Michigan, USA
1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World
Feb 20, 2026Qiao Xu, Yipeng Yu, Chengxiao Feng +1Benchmark Design Execution-Guided Code Generation
Taobao & Tmall Group of Alibaba
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Feb 17, 2026Chansung Park, Juyong Jiang, Fan Wang +4LLM Code Generation RL for Code Generation
Electronics and Telecommunications Research Institute · The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology +2
An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
Feb 13, 2026Giang Son Nguyen, Zi Pong Lim, Sarthak Ketanbhai Modi +2VLM Evaluation Code Generation
Nanyang Technological University · VinUniversity · AUMOVIO Singapore
A Theoretical Analysis of Test-Driven Code Generation
Feb 5, 2026Nicolas Menet, Michael Hersche, Andreas Krause +1Execution-Guided Code Generation Code Generation

Mar 16, 2026J/K move · Enter open · S save

SAGE: Multi-Agent Self-Evolution for LLM Reasoning

Yulin Peng, Xinxin Zhu, Chenxing Wei, Nianbo Zeng+3

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

LLM Reasoning Self-Training for Language Models RL for Language Model Reasoning Multi-Agent LLMs Code Generation

Open paper AskPDF arXiv

Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and strong quality control, limiting stability in long-horizon multi-step reasoning. We present SAGE (Self-evolving Agents for Generalized reasoning Evolution), a closed-loop framework where four agents: Challenger, Planner, Solver, and Critic, co-evolve from a shared LLM backbone using only a small seed set. The Challenger continuously generates increasingly difficult tasks; the Planner converts each task into a structured multi-step plan; and the Solver follows the plan to produce an answer, whose correctness is determined by external verifiers. The Critic scores and filters both generated questions and plans to prevent curriculum drift and maintain training signal quality, enabling stable self-training. Across mathematics and code-generation benchmarks, SAGE delivers consistent gains across model scales, improving the Qwen-2.5-7B model by 8.9% on LiveCodeBench and 10.7% on OlympiadBench.