Learning to Commit: Generating Organic Pull Requests via Online Repository Memory

Published on Mar 27

·

Submitted by

Mo Li

on Mar 30

Authors:

,

,

,

Abstract

Learning to Commit framework enhances LLM coding agents by using historical commit patterns to improve code organicity and adherence to project-specific conventions.

AI-generated summary

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity: generated code ignores project-specific conventions, duplicates functionality already provided by internal APIs, and violates implicit architectural constraints accumulated over years of development. Simply exposing an agent to the latest repository snapshot is not enough: the snapshot reveals the final state of the codebase, but not the repository-specific change patterns by which that state was reached. We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory. Given a repository with a strict chronological split, the agent performs supervised contrastive reflection on earlier commits: it blindly attempts to resolve each historical issue, compares its prediction against the oracle diff, and distils the gap into a continuously growing set of skills-reusable patterns capturing coding style, internal API usage, and architectural invariants. When a new PR description arrives, the agent conditions its generation on these accumulated skills, producing changes grounded in the project's own evolution rather than generic pretraining priors. Evaluation is conducted on genuinely future, merged pull requests that could not have been seen during the skill-building phase, and spans multiple dimensions including functional correctness, code-style consistency, internal API reuse rate, and modified-region plausibility. Experiments on an expert-maintained repository with rich commit history show that Online Repository Memory effectively improves organicity scores on held-out future tasks.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2603.26664

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.26664 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.26664 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.26664 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.