SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rashid, Muhammad Shihab, Bock, Christian, Zhuang, Yuan, Buchholz, Alexander, Esler, Tim, Valentin, Simon, Franceschi, Luca, Wistuba, Martin, Sivaprasad, Prabhu Teja, Kim, Woo Jung, Deoras, Anoop, Zappella, Giovanni, Callot, Laurent
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Need
por: Wistuba, Martin, et al.
Publicado: (2024)

CoRet: Improved Retriever for Code Editing
por: Fehr, Fabio, et al.
Publicado: (2025)

REDO: Execution-Free Runtime Error Detection for COding Agents
por: Li, Shou, et al.
Publicado: (2024)

PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio
por: Chen, Yuanjian, et al.
Publicado: (2026)

Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation
por: Guinet, Gauthier, et al.
Publicado: (2024)

Multi-IaC-Eval: Benchmarking Cloud Infrastructure as Code Across Multiple Formats
por: Davidson, Sam, et al.
Publicado: (2025)

PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data
por: Cheng, Pu, et al.
Publicado: (2026)

TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback
por: Jana, Prithwish, et al.
Publicado: (2026)

Lightweight reranking for language model generations
por: Jain, Siddhartha, et al.
Publicado: (2023)

CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
por: Kim, Myeongsoo, et al.
Publicado: (2025)

Hyperband-based Bayesian Optimization for Black-box Prompt Selection
por: Schneider, Lennart, et al.
Publicado: (2024)

Effortless Spontaneity
por: Esler, Dylan
Publicado: (2024)

Gestaltung medizinisch-sozialer Netzwerke
por: Wistuba, Martin
Publicado: (2019)

DevBench: A multimodal developmental benchmark for language learning
por: Tan, Alvin Wei Ming, et al.
Publicado: (2024)

SWE-Bench+: Enhanced Coding Benchmark for LLMs
por: Aleithan, Reem, et al.
Publicado: (2024)

Reconversión de industrias ligadas a recursos naturales: La promesa incumplida de la industria salmonera en Chile
por: Mirna Bräuning Wistuba
Publicado: (2017)

iSafetyBench: A video-language benchmark for safety in industrial environment
por: Abdullah, Raiyaan, et al.
Publicado: (2025)

SWE-Bench-CL: Continual Learning for Coding Agents
por: Joshi, Thomas, et al.
Publicado: (2025)

UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
por: Yu, Boxi, et al.
Publicado: (2025)

SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization
por: Chaudhari, Shravan, et al.
Publicado: (2025)

SWE Context Bench: A Benchmark for Context Learning in Coding
por: Zhu, Jiayuan, et al.
Publicado: (2026)

MigrationBench: Repository-Level Code Migration Benchmark from Java 8
por: Liu, Linbo, et al.
Publicado: (2025)

What's in a Benchmark? The Case of SWE-Bench in Automated Program Repair
por: Martinez, Matias, et al.
Publicado: (2026)

Does SWE-Bench-Verified Test Agent Ability or Model Memory?
por: Prathifkumar, Thanosan, et al.
Publicado: (2025)

Pre-trained Recommender Systems: A Causal Debiasing Perspective
por: Lin, Ziqian, et al.
Publicado: (2023)

Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation
por: Garg, Spandan, et al.
Publicado: (2025)

SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks
por: Mhatre, Sanket, et al.
Publicado: (2025)

The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason
por: Liang, Shanchao, et al.
Publicado: (2025)

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
por: Yang, John, et al.
Publicado: (2024)

CESNET repositories
por: Šimek, Mirek
Publicado: (2025)

Thesis repository
por: Traks, Magnus
Publicado: (2026)

Quantum Computation Using Large Spin Qudits
por: Omanakuttan, Sivaprasad
Publicado: (2024)

NORMY: Non-Uniform History Modeling for Open Retrieval Conversational Question Answering
por: Rashid, Muhammad Shihab, et al.
Publicado: (2024)

Resolution Matters: An Evaluation of EFlows Assessment Methods Used for Hydropower in Developing Countries
por: Hassan Bukhari, et al.
Publicado: (2025)

Renal Denervation—“Gizmo Idolatry” Fact Checker
por: Markus P. Schlaich, et al.
Publicado: (2025)

Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs
por: Rahdari, Behnam, et al.
Publicado: (2023)

ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
por: Wu, Yating, et al.
Publicado: (2026)

Lossless Token Sequence Compression via Meta-Tokens
por: Harvill, John, et al.
Publicado: (2025)

Fewer Truncations Improve Language Modeling
por: Ding, Hantian, et al.
Publicado: (2024)

Calumet Creek DOC, discharge and SWE data (SWE)
por: Meingast, Karl M, et al.
Publicado: (2019)

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
VUFIND_SESSION	"2ea9ed76fce2feaf1c899eb33008d0f0"
language	"es"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1791170434.4619 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "2ea9ed76fce2feaf1c899eb33008d0f0" ]`]
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	"VUFIND_SESSION=2ea9ed76fce2feaf1c899eb33008d0f0; language=es; ui=standard"
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	"216.73.217.58"
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	"4060"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2504_08703/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2504_08703/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1791170434.4548
REQUEST_TIME	1791170434

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler