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

• URL: http://arxiv.org/abs/2603.26664v1
• Date: Fri, 27 Mar 2026 17:58:56 GMT
• Title: Learning to Commit: Generating Organic Pull Requests via Online Repository Memory
• Abstract summary: Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject.<n>We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory.
• Score: 11.042326503752756
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Repository Boundaries: Cross-Repository Graph Retrieval for Code Generation [15.95046921483187]
  CrossCoder is a cross-repository code generation framework that explicitly incorporates external libraries into the retrieval context.<n>We show that CrossCoder consistently improves both functional correctness (up to 6.3% on pass@1) and robustness to dependency-version changes.
  arXiv  Detail & Related papers  (2026-09-09T10:14:14Z)
• Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation [53.85136813868056]
  ACToR is an adaptive critical token-aware retrieval framework for repository-level code generation.<n>We show that ACToR consistently outperforms state-of-the-art methods on repository-level benchmarks.
  arXiv  Detail & Related papers  (2026-09-01T17:59:39Z)
• DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories [116.27249583403871]
  We propose a state-aware framework for paper-to-code reproduction based on execution-state-aware subplanning.<n>DeepRepro transforms evolving repository states and runtime feedback into fine-grained implementation subplans.<n>Experiments on PaperBench Code-Dev show that DeepRepro consistently outperforms strong scientific and commercial code-agent baselines.
  arXiv  Detail & Related papers  (2026-08-27T02:54:30Z)
• Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution [5.10403054516716]
  Existing datasets evaluate performance on isolated, single pull request (PR) tasks in a stateless manner.<n>We introduce an automated coding task generation framework, which helps generate our dataset SWE-STEPS.
  arXiv  Detail & Related papers  (2026-04-03T13:44:40Z)
• GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization [50.009407518866965]
  Repository-level bug localization is a critical software engineering challenge.<n>GNNs offer a promising alternative due to their ability to model complex, repository-wide dependencies.<n>We introduce GREPO, the first GNN benchmark for repository-scale bug localization tasks.
  arXiv  Detail & Related papers  (2026-02-14T23:22:15Z)
• Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond [13.550121154853715]
  We present Hydra, a repository-level code generation framework that treats code as structured code rather than natural language.<n>We show that Hydra achieves state-of-the-art performance across open- and closed-source CodeLLMs.
  arXiv  Detail & Related papers  (2026-02-12T07:44:00Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• In Line with Context: Repository-Level Code Generation via Context Inlining [11.065371614078723]
  In this paper, we introduce InlineCoder, a novel framework for repository-level code generation.<n>InlineCoder enhances the understanding of repository context by inlining the unfinished function into its call graph.
  arXiv  Detail & Related papers  (2026-01-01T15:56:24Z)
• NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents [79.29376673236142]
  Existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems.<n>We present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents.
  arXiv  Detail & Related papers  (2025-12-14T15:12:13Z)
• Improving Code Localization with Repository Memory [33.423769985220005]
  We introduce tools that allow the agent to retrieve from a non-parametric memory encompassing recent historical commits and linked issues.<n>We demonstrate that augmenting such a memory can significantly improve LocAgent, a state-of-the-art localization framework.
  arXiv  Detail & Related papers  (2025-10-01T15:10:15Z)
• LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning [15.20947984949809]
  We propose ColaUntangle, a new collaborative consultation framework for commit untangling.<n>ColaUntangle integrates Large Language Model (LLM)-driven agents in a multi-agent architecture.<n>We evaluate ColaUntangle on two widely-used datasets (1,612 C# and 14k Java tangled commits)
  arXiv  Detail & Related papers  (2025-07-22T09:42:13Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration [64.19431011897515]
  This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue resolution.<n>Our approach introduces a top-down method to condense critical repository information into a knowledge graph, reducing complexity, and employs a Monte Carlo tree search based strategy.<n>In production deployment and evaluation at Alibaba Cloud, LingmaAgent automatically resolved 16.9% of in-house issues faced by development engineers, and solved 43.3% of problems after manual intervention.
  arXiv  Detail & Related papers  (2024-06-03T15:20:06Z)
• RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation [96.75695811963242]
  RepoCoder is a framework to streamline the repository-level code completion process. It incorporates a similarity-based retriever and a pre-trained code language model. It consistently outperforms the vanilla retrieval-augmented code completion approach.
  arXiv  Detail & Related papers  (2023-03-22T13:54:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.