← Back to Research Radar
Academic Publication Academic Publication

Self-Planning Code Generation with Large Language Models

98
Citations
September 30, 2024
Published Date

Research Abstract & Technology Focus

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 plans out concise solution steps from the intent combined with few-shot prompting. Subsequently, in the implementation phase, the model generates code step by step, guided by the preceding solution 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 of 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.
self-planning generation large language models
Read Full Literature

AI Semantic Synergy Context

Connecting this academic literature to real-world market discussions and products.

crossref.org › academic paper
0%

Self-Collaboration Code Generation via ChatGPT

Although large language models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex...
crossref.org › academic paper
0%

When large language models meet personalization: perspectives of challenges and opportunities

AbstractThe advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large lan...
crossref.org › academic paper
0%

VeriGen: A Large Language Model for Verilog Code Generation

In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by automatically completing partial Verilog code, a common language for designing and modeling d...
roipad.com › trend story
0%

Apple: Embarrassingly Simple Self-Distillation Improves Code Generation

Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple ...
crossref.org › academic paper
0%

Large Language Models for Software Engineering: A Systematic Literature Review

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless...

Frequently Asked Questions (FAQ)

Curated market intelligence mapped to this research.

What is the core focus of the research titled 'Self-Planning Code Generation with Large Language Models'?

This literature focuses on: 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 decom...

Are there open-source GitHub repositories related to Self-Planning Code Generation with Large Language Models?

Yes, open-source projects like PKU-YuanGroup/Helios (Helios: Real Real-Time Long Video Generation Model) are actively building upon these concepts.

Which startups are commercializing the technology behind Self-Planning Code Generation with Large Language Models?

Products like Nano Banana 2 are bringing this to market. Their focus is: Google's latest AI image generation model .

What other academic literature is closely related to 'Self-Planning Code Generation with Large Language Models'?

Yes, highly correlated activity was mapped. An entry titled 'Self-Collaboration Code Generation via ChatGPT' discusses this: Although large language models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world s...

Are there commercial applications of 'Self-Planning Code Generation with Large Language Models' in market news publications?

Yes, highly correlated activity was mapped. An entry titled 'Apple: Embarrassingly Simple Self-Distillation Improves Code Generation' discusses this: Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement l...

Cite this Market Intelligence Report

Reference our AI-mapped synergy between this research and the commercial market to instantly build authority.

Commercial Realization

Startups and Open Source tools heavily associated with the concepts explored in this paper.

Associated Media Narrative