OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Xiaomeng, Zhang, Yinger, Huang, Fei, Tu, Jianhong, Su, Yang, Deng, Lianghao, Liu, Yuxuan, Liu, Yantao, Liu, Dayiheng, Ho, Tsung-Yi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows
di: Chen, Zixin, et al.
Pubblicazione: (2026)

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
di: Zhang, Yinger, et al.
Pubblicazione: (2026)

HumanStudy-Bench: Towards AI Agent Design for Participant Simulation
di: Liu, Xuan, et al.
Pubblicazione: (2026)

PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
di: Liu, Ruoqi, et al.
Pubblicazione: (2026)

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
di: Lin, Justin W., et al.
Pubblicazione: (2025)

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability
di: Xiao, Zikai, et al.
Pubblicazione: (2025)

LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
di: Long, Xiang, et al.
Pubblicazione: (2026)

CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments
di: Yu, Yi, et al.
Pubblicazione: (2026)

TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks
di: Xu, Hanwen, et al.
Pubblicazione: (2025)

BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
di: Zhang, Andy K., et al.
Pubblicazione: (2025)

StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
di: Chen, Yanxu, et al.
Pubblicazione: (2025)

MobileBench-OL: A Comprehensive Chinese Benchmark for Evaluating Mobile GUI Agents in Real-World Environment
di: Wu, Qinzhuo, et al.
Pubblicazione: (2026)

IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment
di: Wu, Dekun, et al.
Pubblicazione: (2025)

WebWorld: A Large-Scale World Model for Web Agent Training
di: Xiao, Zikai, et al.
Pubblicazione: (2026)

BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
di: Li, Yuxuan, et al.
Pubblicazione: (2026)

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
di: Ni, Ziyi, et al.
Pubblicazione: (2025)

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
di: Wang, Zhenting, et al.
Pubblicazione: (2025)

ToolRM: Towards Agentic Tool-Use Reward Modeling
di: Li, Renhao, et al.
Pubblicazione: (2025)

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
di: Wang, Bowen, et al.
Pubblicazione: (2026)

HWE-Bench: Benchmarking LLM Agents on Real-World Hardware Bug Repair Tasks
di: Cui, Fan, et al.
Pubblicazione: (2026)

CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
di: Zhu, Yuxuan, et al.
Pubblicazione: (2025)

ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
di: Tang, Yuanbo, et al.
Pubblicazione: (2026)

Is Machine Learning Unsafe and Irresponsible in Social Sciences? Paradoxes and Reconsidering from Recidivism Prediction Tasks
di: Liu, Jianhong, et al.
Pubblicazione: (2023)

EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation
di: Liu, Yi, et al.
Pubblicazione: (2026)

CR-Bench: Evaluating the Real-World Utility of AI Code Review Agents
di: Pereira, Kristen, et al.
Pubblicazione: (2026)

MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
di: Liu, Wenrui, et al.
Pubblicazione: (2025)

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
di: Chen, Jiacheng, et al.
Pubblicazione: (2024)

TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
di: Xu, Frank F., et al.
Pubblicazione: (2024)

TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
di: Shen, Yuanzhe, et al.
Pubblicazione: (2026)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
di: Zhang, Zehua, et al.
Pubblicazione: (2025)

DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows
di: Liu, Zhou, et al.
Pubblicazione: (2025)

SWE-Universe: Scale Real-World Verifiable Environments to Millions
di: Chen, Mouxiang, et al.
Pubblicazione: (2026)

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
di: Liang, Jiarong, et al.
Pubblicazione: (2026)

ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
di: Jha, Saurabh, et al.
Pubblicazione: (2025)

ClawBench: Can AI Agents Complete Everyday Online Tasks?
di: Zhang, Yuxuan, et al.
Pubblicazione: (2026)

SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking
di: Liu, Guohong, et al.
Pubblicazione: (2026)

Accurate Gauge-Invariant Tensor Network Simulations for Abelian Lattice Gauge Theory in (2+1)D: ground state and real-time dynamics
di: Wu, Yantao, et al.
Pubblicazione: (2025)

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
di: He, Wei, et al.
Pubblicazione: (2025)

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
di: Dong, Guanting, et al.
Pubblicazione: (2026)

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
di: Zhong, Shanshan, et al.
Pubblicazione: (2026)

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	"df2d858ae13d18420aaa35382b8b8c4b"
language	"it"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790990279.7667 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "df2d858ae13d18420aaa35382b8b8c4b" ]`]
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=df2d858ae13d18420aaa35382b8b8c4b; language=it; 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	"216.73.217.142"
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	"52387"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2604_10866/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2604_10866/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790990279.7622
REQUEST_TIME	1790990279

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler