Overview

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

CardsList

335 papers34 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

  1. The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages

    Jul 24, 2026Zixuan Wu, Carolyn Jane Anderson, Arjun GuhaAI Coding AgentsCode Generation

  2. MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation

    Jul 24, 2026Zhen Zhao, Qihang Yang, Feifei Dai +2Execution-Guided Code GenerationCode Generation

  3. Benchmarking LLMs for Verilog Design Flows

    Jul 23, 2026Angshuman Chakravertty, Rahul Koshti, Buddhi Prakash Sharma +1Code GenerationCode Generation Evaluation

  4. Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy

    Jul 23, 2026Elisa Chiarotto, Jingbo Li, P. Chris Broekema +1Large Language Model-Guided OptimizationCode Generation

  5. MV-Bench: Benchmarking Multimodal Large Language Models for Coordinated Multi-View Interface Construction

    Jul 22, 2026Yue Zhao, Hongxu Liu, Feiyu Wang +5Data VisualizationCode Generation

  6. Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code

    Jul 21, 2026Vidyut Sriram, Saatvik Pradhan, Suman SahaAutomated Program RepairCode Generation

  7. Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments

    Jul 20, 2026Shuoming Zhang, Ruiyuan Xu, Haofeng Li +7Code GenerationLLM Code Generation

  8. Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement

    Jul 18, 2026Mingqiao Mo, Yangchen Zeng, Zikai Xiao +7Code Generation

  9. DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

    Jul 18, 2026Runming He, Zhen Hao Wong, Hao Liang +4LLM GroundingCode Generation

  10. Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

    Jul 16, 2026Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez +5Multilingual Language Model EvaluationCode Generation

  11. Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code

    Jul 15, 2026Niels Mündler-Sasahara, Hristo Venev, Dawn Song +2Code GenerationStatic Code Analysis

  12. Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications

    Jul 12, 2026Nasser Giacaman, Valerio Terragni, Paul Denny +1Computer Science EducationCode Generation

  13. ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

    Jul 9, 2026QiHong Chen, Aaron Imani, Iftekhar AhmedCode GenerationAgentic RAG

  14. Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection

    Jul 9, 2026Teng-Ruei ChenCode GenerationLLM Reliability

  15. Functional and Secure Code Generation with Task Vectors

    Jul 8, 2026Felix Wang, Anudeep Das, Mei Nagappan +1Code GenerationLLM Safety Alignment

  16. PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language

    Jul 8, 2026Xianglin Ji, Svetlana V. BoriskinaKnowledge Augmentation for Language ModelsCode Generation

  17. Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding

    Jul 7, 2026Daniel Maninger, Leon Chemnitz, Jannis Brugger +3Retrieval-Augmented GenerationConstrained Decoding

  18. What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation

    Jul 6, 2026Tianhao Niu, Qingfu Zhu, Wanxiang CheData VisualizationChart-to-Code Generation

  19. Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs

    Jul 6, 2026Gabriel Poesia, Simon Henniger, Tzu-Han Hsu +2Code GenerationLLM-Based Program Synthesis

  20. GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments

    Jul 3, 2026Brian La, Sejoon Chang, Ben Kim +5Coding AgentsSoftware Engineering Benchmarks

  21. DecompRL: Solving Harder Problems by Learning Modular Code Generation

    Jul 2, 2026Juliette Decugis, Fabian Gloeckle, Francis Bach +2RL for Code GenerationCode Generation

  22. Understanding Agent-Based Patching of Compiler Missed Optimizations

    Jul 2, 2026Batu Guan, Zirui Wang, Shaohua LiCode GenerationAI Coding Agents