Evaluating Language-Model Agents on Realistic Autonomous Tasks

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kinniment, Megan, Sato, Lucas Jun Koba, Du, Haoxing, Goodrich, Brian, Hasin, Max, Chan, Lawrence, Miles, Luke Harold, Lin, Tao R., Wijk, Hjalmar, Burget, Joel, Ho, Aaron, Barnes, Elizabeth, Christiano, Paul
Format:	Preprint
Veröffentlicht:	2023
Schlagworte:	Computation and Language Artificial Intelligence Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Measuring AI Ability to Complete Long Software Tasks
von: Kwa, Thomas, et al.
Veröffentlicht: (2025)

HCAST: Human-Calibrated Autonomy Software Tasks
von: Rein, David, et al.
Veröffentlicht: (2025)

RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts
von: Wijk, Hjalmar, et al.
Veröffentlicht: (2024)

Autonomous Code Evolution Meets NP-Completeness
von: Yu, Cunxi, et al.
Veröffentlicht: (2025)

VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool
von: Ho, Chia-Tung, et al.
Veröffentlicht: (2024)

Energetic Variational Approaches for inviscid multiphase flow systems with surface flow and tension
von: Koba, Hajime
Veröffentlicht: (2022)

Global solvability for the heat equations in two half spaces and an interface
von: Koba, Hajime
Veröffentlicht: (2024)

Energetic variational approaches for multiphase flow systems with phase transition
von: Koba, Hajime
Veröffentlicht: (2022)

Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC
von: Yu, Cunxi, et al.
Veröffentlicht: (2026)

Unveiling Voices: A Co-Hashtag Analysis of TikTok Discourse on the 2023 Israel-Palestine Crisis
von: Hasin, Rozin
Veröffentlicht: (2025)

Prosthetics of the Indian State: The e-Shram Portal for Unorganized Workers in India
von: Hasin, Rozin
Veröffentlicht: (2025)

Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph
von: Nainani, Jatin, et al.
Veröffentlicht: (2025)

Large Language Model (LLM) for Standard Cell Layout Design Optimization
von: Ho, Chia-Tung, et al.
Veröffentlicht: (2024)

Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
von: Jang, Lawrence Keunho, et al.
Veröffentlicht: (2026)

Development of a Testbed for Autonomous Vehicles: Integrating MPC Control with Monocular Camera Lane Detection
von: Rahman, Shantanu, et al.
Veröffentlicht: (2025)

DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
von: Chang, Chen-Chia, et al.
Veröffentlicht: (2024)

Set Realistic Expectations for Major Gifts Officers
von: Megan Venzin
Veröffentlicht: (2025)

Redes neurais em análises de qualidade de água
von: Daniel Christiano
Veröffentlicht: (2011)

Meiklejohn Institute: Resource Center for Academic Freedom
von: Christiano, David
Veröffentlicht: (1975)

As conseqüências das novas leis de segurança sobre a comunicação local e global
von: Christiano German
Veröffentlicht: (2002)

Interpreting Humani Generis: The Evolution Controversy in the Melbourne Catholic Press, 1960–61*
von: Joel Barnes
Veröffentlicht: (2024)

Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving
von: Nunes, Lucas, et al.
Veröffentlicht: (2025)

Stochastic Control Barrier Functions for Economics
von: van Wijk, David
Veröffentlicht: (2023)

EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments
von: Liu, Zefang, et al.
Veröffentlicht: (2025)

Marco: Configurable Graph-Based Task Solving and Multi-AI Agents Framework for Hardware Design
von: Ho, Chia-Tung, et al.
Veröffentlicht: (2025)

The pleurocerid fauna of the Falls of the Ohio
von: Goodrich, Calvin
Veröffentlicht: (1929)

Arboretum viburnums: part II
von: Goodrich, Ross
Veröffentlicht: (1968)

Certain remarks about labels
von: Goodrich, Calvin
Veröffentlicht: (1942)

Civilization and aquatic mollusks
von: Goodrich, Calvin
Veröffentlicht: (1940)

Some misplaced pleurocerids
von: Goodrich, Calvin
Veröffentlicht: (1927)

Faithful Translators
von: Goodrich, Jaime
Veröffentlicht: (2018)

The Technology Vendor's Conference: An Information Technology Planning Success Story.
von: Goodrich, Jeanne
Veröffentlicht: (1999)

Seize the Means of Prediction! Data, Domination, and Antitrust
von: James Goodrich
Veröffentlicht: (2025)

QUALIDADE NUTRICIONAL E ESCORE QUÍMICO DE AMINOÁCIDOS DE DIFERENTES FONTES PROTÉICAS
von: Christiano Vieira PIRES
Veröffentlicht: (2006)

Pacto pela Saúde: efeito do tempo na eficácia da gestão municipal
von: Darlan Christiano Kroth
Veröffentlicht: (2019)

ÍNDICE TORNOZELO BRAÇO: SUA RELAÇÃO COM ÍNDICES ANTROPOMÉTRICOS E INDICAÇÃO COMO UM COMPONENTE DE AVALIAÇÕES FÍSICAS
von: Christiano Bertoldo Urtado
Veröffentlicht: (2009)

NO LIMIAR DA QUARTA REVOLUÇÃO INDUSTRIAL: INICIATIVAS PARA SUSTENTABILIDADE POR EMPRESAS LÍDERES DO SETOR AUTOMOTIVO RUMO À NOVA ECONOMIA
von: Christiano Alves Farias
Veröffentlicht: (2013)

Evolução da resistência bacteriana em infecção comunitária do trato urinário em idosos
von: Christiano Patrício Póvoa
Veröffentlicht: (2019)

Restrição veicular e tributação: o pedágio urbano enquanto solução urbanística e espécie tributária
von: Christiano Piccioni Toralles
Veröffentlicht: (2010)

Análise da operacionalização da política de aquisição de alimentos da agricultura familiar por parte dos municípios: o caso do PNAE em três microrregiões do Oeste Catarinense
von: Darlan Christiano Kroth
Veröffentlicht: (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	"d6d769440bbc579041b3e184234dee59"
language	"de"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790827514.8149 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d6d769440bbc579041b3e184234dee59" ]`]
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=d6d769440bbc579041b3e184234dee59; language=de; 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	"216.73.216.147"
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	"30600"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2312_11671/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2312_11671/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790827514.8107
REQUEST_TIME	1790827514

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler