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. ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks

    Sep 24, 2026Zeyu Michael Li, William Xingxu Chen, Bingshuo Qian +2Code GenerationDiffusion Language Models

  2. Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

    Sep 22, 2026Yuanteng Chen, Zhilei Liu, Peisong Wang +7Low-Bit QuantizationLLM Quantization

  3. Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation

    Sep 21, 2026Jean-Baptiste Espinasse, Djamel Eddine Khelladi, Mathieu AcherCode GenerationAgentic Code Generation

  4. ChartJudgeBench: Evaluating LMM Judges for Chart-to-Code Generation

    Sep 21, 2026Lijian Wu, Henry Hengyuan Zhao, Zijian Zhang +3VLM EvaluationLLM Evaluation

  5. LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning

    Sep 20, 2026Bakar ChargeishviliCode GenerationLLM Code Generation

  6. Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation

    Sep 18, 2026Ana Nunez, Peyman NajafiradRL for Code GenerationCode Generation

  7. Learning and Transferring Closed-Loop Robot Software

    Sep 17, 2026So Kuroki, Kento Kawaharazuka, Yujin TangRobot Policy LearningRobot Policy Adaptation

  8. Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage

    Sep 16, 2026Eric Fithian, Kirill Skobelev, X. Y. HanSupervised Fine-TuningDiverse Text Generation

  9. ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

    Sep 16, 2026Jeonghye Kim, Minseon Kim, Young Jin Kim +5Coding AgentsSoftware Engineering Benchmarks

  10. An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks

    Sep 16, 2026Chandimal Adikari, Nandika HerathCode GenerationLLM Reliability

  11. Generation of Custom Solvers in Rust for Convex Optimization

    Sep 12, 2026Hao Zhu, Joschka BoedeckerCode GenerationConstrained Optimization

  12. Retrofitting Code Using LLMs to Support Exceptional Behavior

    Sep 9, 2026Linghan Zhong, Jiyang Zhang, Jayanth Srinivasa +2Code GenerationCode Generation Benchmarks

  13. VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics

    Sep 9, 2026Jiahao Tang, Yiren Song, Alex Jinpeng WangImage-to-Code GenerationCode Generation

  14. Talking to Itself While Coding: What Makes Comments Help Code Generation?

    Sep 8, 2026Dangfeng Pan, Zhensu Sun, Cenyuan Zhang +2LLM PromptingCode Generation

  15. ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language

    Sep 6, 2026Hang Zhang, Chaokun Wang, Yuzhi Pan +12Code GenerationLLM Code Generation

  16. Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool

    Sep 4, 2026Samuel Kushnir, Kimia Noorbakhsh, Kavya Sreedhar +6Code Generation

  17. Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics

    Sep 3, 2026Gnaneswar Villuri, Hashmath Shaik, Alex DoboliLLM-Based Program SynthesisExecution-Guided Code Generation

  18. CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation

    Sep 2, 2026Varun Gadey, Ziad Marey, Alexandra DmitrienkoRetrieval-Augmented Code GenerationData Poisoning Attacks

  19. PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides

    Aug 31, 2026Xiaoqiu Wang, Yizhe Chi, Wenyi Li +7Coding AgentsAI Agent Benchmarks

  20. WebWorld: The Browser as a World Model for Self-Improving Web Code

    Aug 31, 2026Jiajun Wu, Jian Yang, Yaxin Du +7Self-Training for Language ModelsCode Generation

  21. Evaluating Tiny Recursive Models Across Training for Code Generation

    Aug 29, 2026Anjani Sirivella, Aanisha Newaz, Glaucia MeloRecursive Language ModelsCode Generation Evaluation

  22. FigMirror: Ground It, Code It, Plot It

    Aug 28, 2026Xiaohan Zhao, Jiacheng Liu, Yaxin Luo +1Image Style TransferScientific Visualization

  23. Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning

    Aug 28, 2026Rui Jin, Jikai Chen, Chengyue Yu +7RL for Code GenerationCode Generation

  24. MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

    Aug 26, 2026Miseon Yu, Jaehoon Choi, Younghan Lee +1Code GenerationSecure Code Generation

  25. ReproAgent: Contract-Guided Paper-to-Code Reproduction

    Aug 25, 2026Xue Hu, Zewei Pan, Zhongyuan Wang +3Scientific Code GenerationAgentic Code Generation

  26. Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation

    Aug 25, 2026Tianyi Xiong, Zhengyuan Yang, Xiaofei Wang +10Code GenerationLLM Self-Refinement