LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Han, Junxiao, Wang, Yarong, Gu, Xiaodong, Gao, Cuiyun, Wan, Yao, Han, Song, Lo, David, Deng, Shuiguang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
di: Han, Junxiao, et al.
Pubblicazione: (2025)

CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature Analysis
di: Wang, Yunkun, et al.
Pubblicazione: (2026)

Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair
di: Li, Guochang, et al.
Pubblicazione: (2024)

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution
di: Xu, Haoran, et al.
Pubblicazione: (2025)

ChatUniTest: A Framework for LLM-Based Test Generation
di: Chen, Yinghao, et al.
Pubblicazione: (2023)

GrepRAG: An Empirical Study and Optimization of Grep-Like Retrieval for Code Completion
di: Wang, Baoyi, et al.
Pubblicazione: (2026)

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion
di: Wang, Xingliang, et al.
Pubblicazione: (2025)

A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
di: Yang, Zezhou, et al.
Pubblicazione: (2025)

An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities
di: Yang, Zezhou, et al.
Pubblicazione: (2025)

SR-Eval: Evaluating LLMs on Code Generation under Stepwise Requirement Refinement
di: Zhan, Zexun, et al.
Pubblicazione: (2025)

Search-Based LLMs for Code Optimization
di: Gao, Shuzheng, et al.
Pubblicazione: (2024)

MigrateLib: a tool for end-to-end Python library migration
di: Islam, Mohayeminul, et al.
Pubblicazione: (2025)

EpiDroid: Dependency-Guided Recomposition for Deep State Discovery in Mobile GUI Testing
di: Song, Jiahui, et al.
Pubblicazione: (2026)

APIGen: Generative API Method Recommendation
di: Chen, Yujia, et al.
Pubblicazione: (2024)

Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
di: Wu, Fan, et al.
Pubblicazione: (2026)

A Systematic Literature Review of Code Hallucinations in LLMs: Characterization, Mitigation Methods, Challenges, and Future Directions for Reliable AI
di: Gao, Cuiyun, et al.
Pubblicazione: (2025)

Benchmarking LLMs for Fine-Grained Code Review with Enriched Context in Practice
di: Hu, Ruida, et al.
Pubblicazione: (2025)

SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
di: Gu, Wenchao, et al.
Pubblicazione: (2025)

HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMs
di: Wu, Yusen, et al.
Pubblicazione: (2026)

What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?
di: Gao, Shuzheng, et al.
Pubblicazione: (2023)

Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware
di: Chen, Yujia, et al.
Pubblicazione: (2025)

Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression
di: Zhong, Jianping, et al.
Pubblicazione: (2026)

Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios
di: Hu, Ruida, et al.
Pubblicazione: (2026)

VecIntrinBench: Benchmarking Cross-Architecture Intrinsic Code Migration for RISC-V Vector
di: Han, Liutong, et al.
Pubblicazione: (2025)

ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code
di: Feng, Jia, et al.
Pubblicazione: (2024)

When Model Editing Meets Service Evolution: A Knowledge-Update Perspective for Service Recommendation
di: Fan, Guodong, et al.
Pubblicazione: (2026)

AndroLibZoo: A Reliable Dataset of Libraries Based on Software Dependency Analysis
di: Samhi, Jordan, et al.
Pubblicazione: (2023)

A Closer Look into Transformer-Based Code Intelligence Through Code Transformation: Challenges and Opportunities
di: Li, Yaoxian, et al.
Pubblicazione: (2022)

SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
di: Gao, Shuzheng, et al.
Pubblicazione: (2025)

Analyzing C/C++ Library Migrations at the Package-level: Prevalence, Domains, Targets and Rationals across Seven Package Management Tools
di: Gu, Haiqiao, et al.
Pubblicazione: (2025)

CatchAll: Repository-Aware Exception Handling with Knowledge-Guided LLMs
di: Tao, Qingxiao, et al.
Pubblicazione: (2026)

Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
di: Chen, Yujia, et al.
Pubblicazione: (2026)

APIRAT: Integrating Multi-source API Knowledge for Enhanced Code Translation with LLMs
di: Wang, Chaofan, et al.
Pubblicazione: (2025)

A Real-World Benchmark for Evaluating Fine-Grained Issue Solving Capabilities of Large Language Models
di: Hu, Ruida, et al.
Pubblicazione: (2024)

The Current Challenges of Software Engineering in the Era of Large Language Models
di: Gao, Cuiyun, et al.
Pubblicazione: (2024)

What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond
di: Gu, Wenchao, et al.
Pubblicazione: (2025)

LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation
di: Kuhar, Sachit, et al.
Pubblicazione: (2024)

Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
di: Wen, Xin-Cheng, et al.
Pubblicazione: (2025)

JMigBench: A Benchmark for Evaluating LLMs on Source Code Migration (Java 8 to Java 11)
di: Amin, Nishil, et al.
Pubblicazione: (2026)

RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry
di: Wang, Chaozheng, et al.
Pubblicazione: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"it"
ui	"standard"
VUFIND_SESSION	"d7c0849960c2ba0e10052915b5b7e4a4"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790990799.9152 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d7c0849960c2ba0e10052915b5b7e4a4" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=it; ui=standard; VUFIND_SESSION=d7c0849960c2ba0e10052915b5b7e4a4"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"49017"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2508_09791/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2508_09791/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790990799.9065
REQUEST_TIME	1790990799

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler