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. Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics

    Nov 7, 2026Peiming Guo, Jinpeng Huang, Yangbin Sun +7Chart-to-Code GenerationCode Generation

  2. Crustify: Repository-Level Generation of Safe Rust Bindings with LLM Agents and Coverage-Guided Testing

    Nov 7, 2026Marius Momeu, Marius Arvinte, Cory Cornelius +1Code GenerationAgentic Code Generation

  3. Done Is Not Correct: Measuring Silent Failures and Self-Verification Calibration When LLM Agents Take CAD Actions

    Nov 6, 2026Carson Rodrigues, Clive Rodrigues, Aravind Reddy GText-to-CAD GenerationLLM Agent Reliability

  4. Test-Time Self-Play: Scaling without a Verifier

    Nov 5, 2026Akira Yoshiyama, Akmal Ashirmatov, Jonas Hübotter +2Self-Play for Language ModelsTest-Time Scaling

  5. Planning-Coding Separation in LLM-Based Code Generation: An Empirical Study

    Nov 3, 2026Wentao Wang, Zeyu Sun, Ruwei Pan +3Code GenerationLLM Code Generation

  6. Rethinking Neural Decompilation: Candidate Selection as the Hidden Bottleneck

    Nov 2, 2026Felix Mächtle, Gautham Sriram, Manjil Neupane +2Software Reverse EngineeringMalware Analysis

  7. Toward Executable Multi-framework Front-end Code Generation with Self-Correction

    Nov 1, 2026Linxiao Li, Haoran Ma, Chenyue Wang +3Code GenerationImage-to-Code Generation

  8. When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

    Oct 29, 2026Yishuo Cai, Minzheng Wang, Liang Zhao +5Code GenerationLong-Horizon Agent Tasks

  9. Cinematize from Unreal: Agentic Choreography for Controllable World Simulation

    Oct 28, 2026Zifan Song, Caihua Shan, Kaitao Song +3Functional 3D Scene GenerationCode Generation

  10. 3DCodeEdit: Benchmarking Instruction-Guided 3D Program Editing

    Oct 28, 2026Binjie Wang, Xinran Zhao, Shoubin Yu +83D Asset Editing3D Scene Editing

  11. Skeleton Coding: Program Structure as a Specification for Agents

    Oct 28, 2026Aditya Golatkar, Alessandro Achille, Renos Zabounidis +9Code GenerationAgentic Code Generation

  12. Search-Guided Reasoning Trace Curation for Verilog Generation

    Oct 26, 2026Matthew DeLorenzo, Kevin Tieu, Prithwish Jana +4Code GenerationStructured Reasoning in Language Models

  13. Benchmarking Coding Agents under Evolving Requirements

    Oct 26, 2026Jia Feng, Alyssa Wu, Cuiyun Gao +3Coding Agent BenchmarksCode Generation

  14. MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation

    Oct 25, 2026Jie Wu, Haoran Ma, Shisong Tang +3Code GenerationImage-to-Code Generation

  15. ComBeautify: Leveraging Code Change Summaries for Conventional Commit Generation

    Oct 25, 2026Rishi Raj, Aashray Tandon, Nikolay Matyunin +1Code GenerationLarge Language Model-Based Text Classification

  16. Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations

    Oct 23, 2026Sadra Emami, Benjamin Weigell, Mohammad Reza Mousavi +3Large Language Model-Guided OptimizationCode Generation

  17. RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding

    Oct 22, 2026Jingxuan Xu, Zihang Xu, Yuechen Luo +9Code GenerationRL for LLM Agents

  18. ProductWebBench: Evaluating Website Continuity Beyond Task Completion

    Oct 22, 2026Jiajun Wu, Jian Yang, Yaxin Du +9Software Engineering BenchmarksCode Generation Evaluation

  19. Did the Problem Actually Get Harder? Testing LLMs on Paired P and NP-Complete Problems Hardened by Adversarial Multi-Agent Rewriting

    Oct 21, 2026Nurul Labib Sayeedi, Md. Faiyaz Abdullah Sayeedi, Zabir Al Nazi +2Language Model Reasoning EvaluationAgent Benchmarks

  20. From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming

    Oct 20, 2026Joschka Kersting, Gesa BenndorfCoding AgentsCode Generation

  21. Self-Decomposing Diffusion for Code Generation

    Oct 20, 2026Lize Shao, Zichen Xie, Zhizhen Chen +2Code GenerationLLM Code Generation

  22. Revision-Based Learning from Interactive Experience and Feedback

    Oct 19, 2026Jiawen Li, Chenming Ge, Alice Gao +3Code GenerationWeb Application Generation

  23. VHDLBench: Benchmarking and Fine-Tuning Large Language Models for VHDL-Based Chip Design

    Oct 19, 2026Patrik Drazic, Benaoumeur Senouci, Boualem BenatallahElectronic Design AutomationCode Generation

  24. Learn the Interface, Not the Implementation: Output Representation Dominates Training Regime in LLM-Based RTL Generation

    Oct 19, 2026Siddharth Patel, Vikram Singh, Siddharth Savyasachi Malu +1RTL Code GenerationCode Generation

  25. Backend-Frontend Converter: Component-Based Conversion of .NET Computational Models to TypeScript

    Oct 17, 2026Petr Ivankov, Max ShestovCode TranslationCode Generation

  26. PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis

    Oct 14, 2026Qiushi Sun, Jingyang Gong, Yang Liu +14Multimodal Large Language ModelsCode Generation