按年被提到
20232023 · 3 次2026
软件工程与 AI 编程›代码生成与程序合成·arXiv:2309.12499 · cs.SE

CodePlan: Repository-level Coding using LLMs and Planning

Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade, Vageesh D C, Arun Iyer, Suresh Parthasarathy, Sriram Rajamani, B. Ashok, Shashank Shet · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-09-25 · 最近 2024-05-06
2不同的人
2活跃月份
3讨论串
126被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Software engineering activities such as package migration, fixing errors reports from static analysis or testing, and adding type annotations or other specifications to a codebase, involve pervasively editing the entire repository of code. We formulate these activities as repository-level coding tasks. Recent tools like GitHub Copilot, which are powered by Large Language Models (LLMs), have succeeded in offering high-quality solutions to localized coding problems. Repository-level coding tasks are more involved and cannot be solved directly using LLMs, since code within a repository is inter-dependent and the entire repository may be too large to fit into the prompt. We frame repository-level coding as a planning problem and present a task-agnostic framework, called CodePlan to solve it. CodePlan synthesizes a multi-step chain of edits (plan), where each step results in a call to an LLM on a code location with context derived from the entire repository, previous code changes and task-specific instructions. CodePlan is based on a novel combination of an incremental dependency analysis, a change may-impact analysis and an adaptive planning algorithm. We evaluate the effectiveness of CodePlan on two repository-level tasks: package migration (C#) and temporal code edits (Python). Each task is evaluated on multiple code repositories, each of which requires inter-dependent changes to many files (between 2-97 files). Coding tasks of this level of complexity have not been automated using LLMs before. Our results show that CodePlan has better match with the ground truth compared to baselines. CodePlan is able to get 5/6 repositories to pass the validity checks (e.g., to build without errors and make correct code edits) whereas the baselines (without planning but with the same type of contextual information as CodePlan) cannot get any of the repositories to pass them.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论og_kalu · 2023-09

“>And it is not true that computing power will continue to reduce; Moore's Law has been dead for some time now, and if incremental growth in LLMs require exponential growth in computing power the marginal difference won't matter. This is a lot of unfounded assumptions. You don't need Moore's Law. GPU's are not really made with ML training in mind. You do…”

ChatGPT can now see, hear, and speak – openai.com原评论 ↗
评论og_kalu · 2023-09

“>It can't even generate flashcards from a textbook chapter, because it can't load the entire chapter into memory. Heck, it doesn't even know what textbook I'm talking about; I have to provide the content! Okay...? That's a context window problem. and you could manage it if you sent the textbook in chunks. >The improvement GPT 5 would have to provide is …”

ChatGPT can now see, hear, and speak – openai.com原评论 ↗
评论shihanwan1 · 2024-05

“Hey HN, We are open sourcing (https://github.com/xeol-io/bumpgen/), a tool that uses an LLM to upgrade your dependencies to their newer versions. We are building this for our customers (security teams) who need to upgrade their dependencies for security and compliance but lack engineering resources. Most patching tend to be painless but major version upg…”

Show HN: Can AI keep my code up-to-date?原评论 ↗
被提交为 story · 1 次