代码生成论文趋势 2023–2026

程序合成与代码 LLM

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,161 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

代码生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202329553195210
202413566111134446
202523016479172645
2026236241174209860

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部代码生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 395 篇，第 4 / 8 页

  1. ICML 2026Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
  2. ICML 2026STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics–Physics Dual System
  3. ICML 2026SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
  4. ICML 2026SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
  5. ICML 2026Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
  6. ICML 2026Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
  7. ICML 2026TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation
  8. ICML 2026The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
  9. ICML 2026The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation
  10. ICML 2026The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
  11. ICML 2026Threat2Traffic: Multi-Agent Environment Synthesis for Malware Traffic Generation from Threat Intelligence
  12. ICML 2026Towards Functional Correctness of Large Code Models with Selective Generation
  13. ICML 2026Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding
  14. ICML 2026TritonGym: A Benchmark for Agentic LLM Workflows in Triton GPU Code Generation
  15. ICML 2026TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
  16. ICML 2026UniCode: Augmenting Evaluation for Code Reasoning
  17. ICML 2026UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
  18. ICML 2026Variational Bayesian Flow Network for Graph Generation
  19. ICML 2026VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
  20. ICML 2026VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification
  21. ICML 2026WeightCLIP: Aligning Datasets and Models for Weight Space Learning
  22. ICML 2026Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer
  23. ICML 2026Winformer: Transcending Pairwise Similarity for Time-series Generation
  24. ICML 2026With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots
  25. ICML 2025AAAR-1.0: Assessing AI’s Potential to Assist Research
  26. ICML 2025Agent-as-a-Judge: Evaluate Agents with Agents
  27. ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
  28. ICML 2025An Online Learning Approach to Prompt-based Selection of Generative Models and LLMs
  29. ICML 2025AuPair: Golden Example Pairs for Code Repair
  30. ICML 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
  31. ICML 2025Automated Benchmark Generation for Repository-Level Coding Tasks
  32. ICML 2025BaxBench: Can LLMs Generate Correct and Secure Backends?
  33. ICML 2025Black-Box Adversarial Attacks on LLM-Based Code Completion
  34. ICML 2025BoA: Attention-aware Post-training Quantization without Backpropagation
  35. ICML 2025Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
  36. ICML 2025Can Large Language Models Understand Intermediate Representations in Compilers?
  37. ICML 2025CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction
  38. ICML 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
  39. ICML 2025CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
  40. ICML 2025Continuous Visual Autoregressive Generation via Score Maximization
  41. ICML 2025Controllable Data Generation with Hierarchical Neural Representations
  42. ICML 2025Copilot Arena: A Platform for Code LLM Evaluation in the Wild
  43. ICML 2025CRANE: Reasoning with constrained LLM generation
  44. ICML 2025CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
  45. ICML 2025CursorCore: Assist Programming through Aligning Anything
  46. ICML 2025Deep Reinforcement Learning from Hierarchical Preference Design
  47. ICML 2025DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
  48. ICML 2025Diffusion on Language Model Encodings for Protein Sequence Generation
  49. ICML 2025DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
  50. ICML 2025DLP: Dynamic Layerwise Pruning in Large Language Models

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查代码生成在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "code-generation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇代码生成论文？
共 2,161 篇，按年份分别是 2023 年 210 篇、2024 年 446 篇、2025 年 645 篇、2026 年 860 篇。
NeurIPS 2026 有多少篇代码生成论文？
NeurIPS 2026 有 236 篇代码生成论文，上一届是 230 篇。
ICLR 2026 有多少篇代码生成论文？
ICLR 2026 有 241 篇代码生成论文，上一届是 164 篇。
ICML 2026 有多少篇代码生成论文？
ICML 2026 有 174 篇代码生成论文，上一届是 79 篇。
CVPR 2026 有多少篇代码生成论文？
CVPR 2026 有 209 篇代码生成论文，上一届是 172 篇。
哪个会议的代码生成论文最多？
NeurIPS，2023–2026 年共 630 篇。

「自然语言」下的其他主题