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 2,161 篇，第 12 / 44 页

  1. ICML 2026LitReview Arena: Evaluating Literature Review Agents with Battle-style Peer Review Platform
  2. ICML 2026LLM-Guided Loop Bound Generation for Program Termination Verification
  3. ICML 2026LLMs Lean on Priors, Not Programming Language Semantics
  4. ICML 2026Locally Coherent Parallel Decoding in Diffusion Language Models
  5. ICML 2026MALICE: Memory-aware Loop Invariants Generation on Symbolic Execution Traces
  6. ICML 2026MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
  7. ICML 2026MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
  8. ICML 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
  9. ICML 2026Mosaic: Unlocking Over 30$\times$ Context Length for Diffusion LLMs Inference via Global Memory Planning and Dynamic Peak Taming
  10. ICML 2026Motion-Aware Caching for Efficient Autoregressive Video Generation
  11. ICML 2026MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation
  12. ICML 2026NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
  13. ICML 2026One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
  14. ICML 2026OpenSage: Self-programming Agent Generation Engine
  15. ICML 2026PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic Alignment
  16. ICML 2026Pair2Scene: Learning Local Object Relations for Procedural Scene Generation
  17. ICML 2026ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution
  18. ICML 2026Periodic Bayesian Flow Networks with Additive Accuracy
  19. ICML 2026PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
  20. ICML 2026PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation
  21. ICML 2026Planar Symmetric Pattern Generation
  22. ICML 2026PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization
  23. ICML 2026Poison with Style: A Practical Poisoning Attack on Code Large Language Models
  24. ICML 2026PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
  25. ICML 2026ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modeling
  26. ICML 2026Propose, Solve, Verify: Self-Play Through Formal Verification
  27. ICML 2026Q-Delta: Beyond Key–Value Associative State Evolution
  28. ICML 2026Q-Tab: Quantized Tabular Data Generator
  29. ICML 2026QiMeng-LibBench: Benchmarking LLM Agents for Library-Scale Cross-Architecture Migration
  30. ICML 2026Random Selection Reveals Implicit Knowledge Consensus in Code Generation
  31. ICML 2026Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
  32. ICML 2026Regression Language Models for Code
  33. ICML 2026Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation
  34. ICML 2026Rethinking Code Complexity Through the Lens of Large Language Models
  35. ICML 2026Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
  36. ICML 2026Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation
  37. ICML 2026Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
  38. ICML 2026Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
  39. ICML 2026S-Quant: Rethinking Weight Quantization with Seed-Based Generation
  40. ICML 2026Scaling Agentic Verifier for Competitive Coding
  41. ICML 2026Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
  42. ICML 2026ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
  43. ICML 2026Score Based Error Correcting Code Decoder
  44. ICML 2026SecCodePRM: A Process Reward Model for Code Security
  45. ICML 2026Self-Supervised Learning as Discrete Communication
  46. ICML 2026SemRep : Generative Code Representation Learning with Code Transformations
  47. ICML 2026Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control
  48. ICML 2026SimGFM: Simplifying Discrete Flow Matching for Graph Generation
  49. ICML 2026Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
  50. ICML 2026SPADA: A Verifiable Test-Driven Agent for Controllable Parametric CAD Assembly Generation

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