docs: draft agent-oriented linting paper#67
Draft
danielchen0 wants to merge 18 commits into
Draft
Conversation
arnavsurve
reviewed
May 17, 2026
| \maketitle | ||
|
|
||
| \begin{abstract} | ||
| Large language model agents increasingly generate complete application code for web, mobile, and backend targets, but generated applications fail in ways that traditional linters do not emphasize. In particular, generated React, Next.js, Expo, React Native, and serverless TypeScript projects often fail through framework-specific integration mistakes: browser APIs used during server rendering, missing declarations that a component must run on the client, invalid routing conventions, mobile layout constraints, unsafe serverless loops, or platform-incompatible imports. These defects may be syntactically valid, type-correct, and invisible until build, preview deployment, device testing, or runtime. |
Contributor
There was a problem hiding this comment.
could include something about performance or smaller iteration cycles due to the feedback loop being tied to the agent's action lifecycle, not runtime/build time
Contributor
There was a problem hiding this comment.
I know it's mentioned later on but might be nice to have as a hook idk if that's a thing in academic papers
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Drafts an arXiv-style paper for laint around the idea of agent-oriented linting for generated JSX/TSX applications. The draft frames laint as a feedback-loop tool for catching framework-specific generated-app failures before build, preview, or runtime.
This is intentionally a draft PR: the paper has the system description, rule taxonomy, and evaluation plan, but still needs measured results before it should be treated as submission-ready.
Verification
makeinpaper/buildsmain.pdfcleanlypaper/main.logfor undefined refs/citations and overfull/warning/error linesNext