DepRepair: LLM-Based Source-Code Repair for Dependency Breaking Changes
2026-07-20 • Software Engineering
Software Engineering
AI summaryⓘ
The authors study the problem of software breaking when third-party libraries update and change in ways that can cause errors in the software that depends on them. They created a benchmark called DepBench with real examples and tests to evaluate fixes. They propose DepRepair, a method that uses large language models (LLMs) and carefully filtered information from library updates to automatically fix these problems in the dependent code. Their approach improves success rates in fixing software breakages compared to using raw update information. This shows that organizing update data helps automated repair tools work better.
dependency breaking changesthird-party librariesautomated software repairlarge language modelsDepBenchDepRepairAPI diffsrelease notessoftware testingcross-repository repair
Authors
Shenghao Yang, Bo Lu, Yaochen Liu, Yu Kang, Qiongfang Zhang, Chetan Bansal, Saravan Rajmohan, Minghua Ma
Abstract
Modern software projects depend on numerous third-party libraries, whose updates often introduce breaking changes. Adapting consumer code to such changes remains labor-intensive and error-prone. Existing work either characterizes dependency breaking changes without producing a verified consumer-side patch, or studies automated repair only in settings where the failure and repair context are contained within the target repository. However, dependency breaking changes violate this assumption: the decisive repair evidence lies upstream in release notes and API diffs, and no failing test localizes where the consumer breaks, leaving the repair under-informed. To study this cross-repository problem on real data, we introduce DepBench, a benchmark of 95 real-world dependency-update instances across four ecosystems, each paired with a Docker-based executable oracle that runs the consumer's own tests. To address these challenges, we propose DepRepair, a single-call LLM approach that grounds repair in structured upstream evidence through three components: an evidence filter that distills relevant upstream changes, a usage locator that identifies affected consumer sites, and a subcategory-aware guide that tailors repairs to the breaking-change type. Evaluated on DepBench, DepRepair attains the highest executable pass rate on each backbone, achieving 89.5% with GPT-5.5 and 82.1% with Claude Opus 4.6. We further find that raw upstream evidence reduces LLM and agent pass rates by 7--23 percentage points, whereas structured evidence consistently improves them.