Related papers: Fine-grained Multi-Document Extraction and Generation of Code Change Rationale

Fine-grained Multi-Document Extraction and Generation of Code Change Rationale

URL: http://arxiv.org/abs/2604.10345v1
Date: Sat, 11 Apr 2026 20:49:36 GMT
Title: Fine-grained Multi-Document Extraction and Generation of Code Change Rationale
Abstract summary: We study how rationale components (e.g., a change's goal, need, and alternative) are distributed across artifacts.<n>We introduce ARGUS, an LLM-based approach that identifies sentences expressing goal, need, and alternative across a commit's artifacts.
Score: 9.038241584076468
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Understanding the reasons behind past code changes is critical for many software engineering tasks, including refactoring and reviewing code, diagnosing bugs, and implementing new features. Unfortunately, locating and reconstructing this rationale can be difficult for developers because the information is often fragmented, inconsistently documented, and scattered across different artifacts such as commit messages, issue reports, and PRs. In this paper, we address this challenge in two steps. First, we conduct an empirical study of 63 commits from five open-source Java projects to analyze how rationale components (e.g., a change's goal, need, and alternative) are distributed across artifacts. We find that the rationale is highly fragmented: commit messages and pull requests primarily capture goals, while needs and alternatives are more often found in issues and PRs. Other components are scarce but found in artifacts other than commit messages. No single artifact type captures all components, underscoring the need for cross-document reasoning and synthesis. Second, we introduce ARGUS, an LLM-based approach that identifies sentences expressing goal, need, and alternative across a commit's artifacts and creates concise rationale summaries to support code comprehension and maintenance tasks. We evaluated ARGUS on the 63 commits and compared its performance against baseline variants. The best-performing version achieved 51.4% precision and 93.2% recall for rationale identification, while producing rationale summaries rated as accurate. A user study with 12 Java developers further showed that these summaries were perceived as useful and helpful for tasks such as code review, documentation, and debugging. Our results highlight the need for multi-document reasoning in capturing rationale and demonstrate the potential of ARGUS to help developers understand and maintain software systems.

Related papers

An Empirical Study on the Impact of Change Granularity in Refactoring Detection [5.134247368862501]
We call these types of changes (CGRs) and ephemerals (EPRs) as coarse-graineds (CGRs) and ephemerals (EPRs)<n>We investigated the features and causes of CGRs and EPRs through an empirical study of 32 open-source Java projects and found that both commonly occur during development.<n>In addition, we found that types related to splitting or merging classes and packages, as well as those involving modifications to the inheritance structure, tend to be CGRs, and types targeting small objects such as variables and attributes.
arXiv Detail & Related papers (2026-09-07T13:35:58Z)
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)
The Value of Effective Pull Request Description [5.518378568494161]
In pull-based development, code contributions are submitted as pull requests (PRs) to undergo reviews and approval by other developers.<n>We conducted a grey literature review of guidelines on writing PR descriptions and derived a taxonomy of eight recommended elements.<n>We analyzed 80K GitHub PRs across 156 projects and five programming languages to assess associations between these elements and code review outcomes.
arXiv Detail & Related papers (2026-02-16T10:15:21Z)
TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
arXiv Detail & Related papers (2025-11-07T16:08:34Z)
Contextual Code Retrieval for Commit Message Generation: A Preliminary Study [18.46986692375691]
A commit message describes the main code changes in a commit and plays a crucial role in software maintenance.<n>Existing commit message generation approaches typically frame it as a direct mapping which inputs a code diff and produces a brief descriptive sentence as output.<n>We argue that relying solely on the code diff is insufficient, as raw code diff fails to capture the full context needed for generating high-quality commit messages.
arXiv Detail & Related papers (2025-07-23T16:54:57Z)
SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers [16.80818230868491]
This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers.<n>To facilitate rigorous evaluation, we introduce SciReplicate-Bench, a benchmark of 100 tasks from 36 NLP papers published in 2024.<n>Building on SciReplicate-Bench, we propose Sci-Reproducer, a dual-agent framework consisting of a Paper Agent that interprets algorithmic concepts from literature and a Code Agent that retrieves dependencies from repositories and implements solutions.
arXiv Detail & Related papers (2025-03-31T22:02:24Z)
Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
arXiv Detail & Related papers (2025-02-18T15:56:34Z)
An Empirical Study on the Impact of Code Duplication-aware Refactoring Practices on Quality Metrics [5.516979718589074]
We extract a corpus of 332 commits applied and documented by developers during their daily changes from 128 open-source Java projects.<n>We empirically analyze the impact of these operations on a set of common state-of-the-art design quality metrics.
arXiv Detail & Related papers (2025-02-06T13:34:25Z)
CodeRAG-Bench: Can Retrieval Augment Code Generation? [78.37076502395699]
We conduct a systematic, large-scale analysis of code generation using retrieval-augmented generation.<n>We first curate a comprehensive evaluation benchmark, CodeRAG-Bench, encompassing three categories of code generation tasks.<n>We examine top-performing models on CodeRAG-Bench by providing contexts retrieved from one or multiple sources.
arXiv Detail & Related papers (2024-06-20T16:59:52Z)
On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing [82.96523584351314]
We decouple the task of context retrieval from the other components of the repository-level code editing pipelines. We conclude that while the reasoning helps to improve the precision of the gathered context, it still lacks the ability to identify its sufficiency.
arXiv Detail & Related papers (2024-06-06T19:44:17Z)
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.