mlsanityData to 7 Oct 2026

Self-planning Code Generation with Large Language Models

arXiv 2303.06689 ↗First posted 12 Mar 2023cs.SEcited by 121

Not on the map. Why?

Cited by 32 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Although large language models (LLMs) have demonstrated impressive ability in code generation, they are still struggling to address the complicated intent provided by humans. It is widely acknowledged that humans typically employ planning to decompose complex problems and schedule solution steps prior to implementation. To this end, we introduce planning into code generation to help the model understand complex intent and reduce the difficulty of problem-solving. This paper proposes a self-planning code generation approach with large language models, which consists of two phases, namely planning phase and implementation phase. Specifically, in the planning phase, LLM outlines concise and formatted planning steps from the intent. Subsequently, in the implementation phase, the model generates code step by step, guided by the preceding planning steps. We conduct extensive experiments on various code-generation benchmarks across multiple programming languages. Experimental results show that self-planning code generation achieves a relative improvement of up to 25.4% in Pass@1 compared to direct code generation, and up to 11.9% compared to Chain-of-Thought code generation. Moreover, our self-planning approach also enhances the quality of the generated code with respect to correctness, readability, and robustness, as assessed by humans.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Mar 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 17; 2024: 26; 2025: 48; 2026: 30.

121 papers.

Sort:

By area:

  1. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  2. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  3. 2025VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Modelscited by 102
  4. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  5. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  6. 2023Large Language Models for Supply Chain Optimizationcited by 61
  7. 2024Agents in Software Engineering: Survey, Landscape, and Visioncited by 60
  8. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  9. 2024Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategiescited by 44
  10. 2023Large Language Model-Aware In-Context Learning for Code Generationcited by 42
  11. 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimizationcited by 39
  12. 2024Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLMcited by 38
38 more
  1. 2024Benchmarking Language Model Creativity: A Case Study on Code Generationcited by 38
  2. 2025A Survey of Direct Preference Optimizationcited by 35
  3. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generationcited by 33
  4. 2025CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Taskscited by 32
  5. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisationcited by 31
  6. 2024Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Modelscited by 31
  7. 2023CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generationcited by 29
  8. 2023LLM-Assisted Code Cleaning For Training Accurate Code Generatorscited by 27
  9. 2025FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoningcited by 25
  10. 2024Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Designcited by 24
  11. 2025CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignmentcited by 22
  12. 2023PACE: Improving Prompt with Actor-Critic Editing for Large Language Modelcited by 20
  13. 2025Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Taskscited by 20
  14. 2024Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generationcited by 19
  15. 2023Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoningcited by 17
  16. 2024Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMscited by 17
  17. 2024Selective Prompt Anchoring for Code Generationcited by 16
  18. 2025Could Thinking Multilingually Empower LLM Reasoning?cited by 16
  19. 2026Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verificationcited by 16
  20. 2023ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generationcited by 13
  21. 2024AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Accelerationcited by 13
  22. 2024The Impact of Prompt Programming on Function-Level Code Generationcited by 13
  23. 2025Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Modelcited by 13
  24. 2024RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidancecited by 12
  25. 2023Natural Language Decomposition and Interpretation of Complex Utterancescited by 10
  26. 2024RepoMasterEval: Evaluating Code Completion via Real-World Repositoriescited by 10
  27. 2024Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairmentscited by 10
  28. 2024Scattered Forest Search: Smarter Code Space Exploration with LLMscited by 10
  29. 2025Rethinking the Evaluation of Secure Code Generationcited by 10
  30. 2025Execution Guided Line-by-Line Code Generationcited by 10
  31. 2025Risk Assessment Framework for Code LLMs via Leveraging Internal Statescited by 8
  32. 2024An Empirical Study on Capability of Large Language Models in Understanding Code Semanticscited by 7
  33. 2024Planning-Driven Programming: A Large Language Model Programming Workflowcited by 7
  34. 2025Beyond the Prompt: An Empirical Study of Cursor Rulescited by 7
  35. 2023Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generationcited by 6
  36. 2024Collaborative Evolving Strategy for Automatic Data-Centric Developmentcited by 6
  37. 2025CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generationcited by 6
  38. 2026TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Codecited by 6

50 most cited of 121 All 121 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Advancing Code Generation with Large Language Models: A Research Roadmap
  2. 2024HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation
  3. 2025Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency
  4. 2024Assessing Code Generation with Intermediate Languages
  5. 2023Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation
  6. 2025Holistic Evaluation of State-of-the-Art LLMs for Code Generation
  7. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
  8. 2025An Empirical Study of Reasoning Steps in Thinking Code LLMs