[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83570-en":3,"doc-seo-83570-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83570,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue","Open-source libraries and tools are widely reused, but compatibility maintenance is expensive and often stops when maintainers leave or ecosystems evolve. RepoRescue studies whether LLM agents can perform compatibility rescue: adapt historically working repositories to modern runtimes and dependencies without changing intended behavior. The agent receives only the repository and a failing modern environment, then diagnoses failures, identifies affected code, and produces a whole-suite source-code rescue. Experiments on 193 Python and 122 Java repositories evaluate restoration success, source-only effects, runtime-blocked test editing, difficulty, and practical validation.","arXiv :2607 .0 12 13v 1 [ cs . SE] 1 Jul 2026  \nRepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue  \nZhihao Lin 1 Mingyi Zhou 1 Zhensu Sun2 Yizhuo Yang 1 Renyu Yang 1 David Lo2 Li Li 1,*  \n1 Beihang University, Beijing, China 2 Singapore Management University, Singapore  \n{mathieulin, zhoumingyi, yangyizhuo, [renyuyang}@buaa.edu.cn](renyuyang}@buaa.edu.cn), [lilicoding@ieee.org](lilicoding@ieee.org)[ ](lilicoding@ieee.org)[zhensuuu@gmail.com](zhensuuu@gmail.com), [davidlo@smu.edu.sg](davidlo@smu.edu.sg)  \n* Corresponding author.  \nAbstract. Open-source libraries and tools are widely reused, but compatibility maintenance is expensive. Once maintainers leave, otherwise useful repositories can stop working as runtimes and dependencies evolve. We study whether LLM agents can perform this form of maintenance: adapting old repositories so that they work on modern environments. We call this task compatibility rescue. Unlike bug repair, where a program violates its intended behavior in the environment for which it was written, compatibility rescue starts from a repository that still works in its original environment and then fails after the runtime or dependency ecosystem changes. RepoRescue gives the agent only the repository and its failing modern environment. The agent must diagnose the failure, locate the affected code, and produce a source-code rescue that restores the whole historical suite. We build RepoRescue from 193 Python and 122 Java repositories, each checked to pass in its historical environment and fail after modernization before agents attempt a rescue. We run five deployed agent systems on Python and three on Java. Pass rate tells us whether the test suite was restored. To check whether the patch repaired source code, we also rerun each submitted patch after removing test-file edits; we call this source-only evaluation because it asks whether the remaining source changes alone restore the suite. We further add a runtime-enforced regime that blocks test edits during the session and practical-use validation for repositories whose original suites pass after rescue. We report four findings: (1) All four Claude Code systems sometimes edit failing tests even when the prompt forbids it; when test edits are blocked at runtime, Kimi still rescues 41.5% of repositories. (2) The systems succeed on different repositories, and their union (62.7%) exceeds the best single system (51.8%) by 10.9 percentage points. (3) Difficulty tracks the amount of cross-file reasoning required. On 14 repositories that need coordinated whole-codebase changes, GPT-5.2 through Codex is recorded as passing all 14, while every Claude Code system passes at most 2; the traces point to gaps in planning and coordination. (4) A passing test suite is only a first signal: among 34 unmaintained Python candidates whose original suites pass after rescue, 22 work in realistic scenarios, and 12 pass bug-hunt with patches that address the compatibility failure. As a benchmark, RepoRescue measures these capabilities jointly and labels each rescue on a reasoning-level hierarchy, from mechanical edits to whole-codebase coordination.  \n1 Introduction  \nSoftware often outlives its maintainers. Libraries can stop receiving releases for many reasons: maintainers move on, funding ends, or the project becomes stable enough that no one keeps updating  \nhistorical Phase 0: ecosystem drift: Phase 1: Phase 2:  \nenvironment historical env passes runtime dependencies modern env fails source-only rescue  \nFigure 1: Overview of RepoRescue. We admit repositories that pass in a historical environment (Phase 0) and fail after ecosystem drift (Phase 1), then ask an agent to produce a source-only rescue (Phase 2) . We evaluate each outcome through full-patch pass, source-only audit, runtime blocking, and realistic scenario validation.  \nit. The code may still be useful, but the environment around it does not stand still because Python, Java, build tools","cbCaihryKkgo67NY","https://ap.wps.com/l/cbCaihryKkgo67NY","pdf",1134982,4,1,20,"English","en",105,"# Introduction\n## Compatibility rescue setting and motivation\n## Distinction from general bug repair\n## Evaluation methodology overview","[{\"question\":\"What is compatibility rescue in RepoRescue?\",\"answer\":\"Compatibility rescue adapts historically working software so it keeps working under modern runtimes or evolving dependencies, without changing its intended behavior. RepoRescue distinguishes this from bug repair by starting from a version that previously worked and then broke due to ecosystem drift.\"},{\"question\":\"What information does an LLM agent receive during the task?\",\"answer\":\"The agent is given only the repository and its failing modern environment. It must diagnose the failure, locate affected code, and generate a source-code rescue that restores the historical test-suite behavior.\"},{\"question\":\"How is success measured in the study?\",\"answer\":\"Pass rate is used to determine whether the test suite was restored after rescue. The study also performs a source-only evaluation by rerunning patches after removing test-file edits, and adds a runtime-enforced regime that blocks test edits during the session.\"}]",1784188910,50,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"reporescue-an-empirical-study-of-llm-agents-on-whole-repository-compatibility-rescue","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/reporescue-an-empirical-study-of-llm-agents-on-whole-repository-compatibility-rescue/83570/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is compatibility rescue in RepoRescue?","Question",{"text":75,"@type":76},"Compatibility rescue adapts historically working software so it keeps working under modern runtimes or evolving dependencies, without changing its intended behavior. RepoRescue distinguishes this from bug repair by starting from a version that previously worked and then broke due to ecosystem drift.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What information does an LLM agent receive during the task?",{"text":80,"@type":76},"The agent is given only the repository and its failing modern environment. It must diagnose the failure, locate affected code, and generate a source-code rescue that restores the historical test-suite behavior.",{"name":82,"@type":73,"acceptedAnswer":83},"How is success measured in the study?",{"text":84,"@type":76},"Pass rate is used to determine whether the test suite was restored after rescue. The study also performs a source-only evaluation by rerunning patches after removing test-file edits, and adds a runtime-enforced regime that blocks test edits during the session.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":22,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":22,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]