Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Koblischke, Nolan, Jang, Hyunseok, Menou, Kristen, Ali-Dib, Mohamad
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence Instrumentation and Methods for Astrophysics Computational Physics
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Physics simulation capabilities of LLMs
von: Ali-Dib, Mohamad, et al.
Veröffentlicht: (2023)

SpectraFM: Tuning into Stellar Foundation Models
von: Koblischke, Nolan, et al.
Veröffentlicht: (2024)

Semantic search for 100M+ galaxy images using AI-generated captions
von: Koblischke, Nolan, et al.
Veröffentlicht: (2025)

ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?
von: Ye, Christine, et al.
Veröffentlicht: (2025)

Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
von: Xu, Licong, et al.
Veröffentlicht: (2025)

Rapid Parameter Estimation for Extreme Mass Ratio Inspirals Using Machine Learning
von: Liang, Bo, et al.
Veröffentlicht: (2024)

Binary Star Evolution Modules in REBOUNDx
von: Ali-Dib, Mohamad
Veröffentlicht: (2026)

SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction
von: Roy, Sujit, et al.
Veröffentlicht: (2025)

Small amplitude red giants elucidate the nature of the Tip of the Red Giant Branch as a standard candle
von: Anderson, Richard I., et al.
Veröffentlicht: (2023)

Evaluating Retrieval-Augmented Generation Agents for Autonomous Scientific Discovery in Astrophysics
von: Xu, Xueqing, et al.
Veröffentlicht: (2025)

AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
von: Chen, Claire, et al.
Veröffentlicht: (2026)

AI Agents for Ground-Based Gamma Astronomy
von: Kostunin, D., et al.
Veröffentlicht: (2025)

AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
von: Shi, Jinghang, et al.
Veröffentlicht: (2025)

CLiMB: A Domain-Informed Novelty Detection Clustering Framework for Galactic Archaeology and Scientific Discovery
von: Monti, Lorenzo, et al.
Veröffentlicht: (2026)

MARVEL: A Multi Agent-based Research Validator and Enabler using Large Language Models
von: Mukund, Nikhil, et al.
Veröffentlicht: (2026)

AstroReview: An LLM-driven Multi-Agent Framework for Telescope Proposal Peer Review and Refinement
von: Wang, Yutong, et al.
Veröffentlicht: (2025)

Revealing hidden correlations from complex spatial distributions: Adjacent Correlation Analysis
von: Li, Guang-Xing
Veröffentlicht: (2025)

Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
von: Xu, Licong, et al.
Veröffentlicht: (2026)

gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
von: Islam, Tousif, et al.
Veröffentlicht: (2026)

Iterated Agent for Symbolic Regression
von: Song, Zhuo-Yang, et al.
Veröffentlicht: (2025)

Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models
von: Li, Yun Qi, et al.
Veröffentlicht: (2024)

Space AI: Leveraging Artificial Intelligence for Space to Improve Life on Earth
von: Wang, Ziyang
Veröffentlicht: (2025)

Imagining the Alien: Human Projections and Cognitive Limitations
von: Djorgovski, S. G.
Veröffentlicht: (2026)

FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records
von: Zhu, Bingke, et al.
Veröffentlicht: (2025)

On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations
von: Wang, Ziyang
Veröffentlicht: (2026)

StarWhisper Telescope: An AI framework for automating end-to-end astronomical observations
von: Wang, Cunshi, et al.
Veröffentlicht: (2024)

Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)
von: Pinheiro, Lucas Carrit Delgado, et al.
Veröffentlicht: (2025)

Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program
von: Carrasco, Alejandro, et al.
Veröffentlicht: (2025)

Large Language Models for Limited Noisy Data: A Gravitational Wave Identification Study
von: Li, Yixuan, et al.
Veröffentlicht: (2025)

StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
von: Li, Weijian, et al.
Veröffentlicht: (2025)

Agent Mars: Multi-Agent Simulation for Multi-Planetary Life Exploration and Settlement
von: Wang, Ziyang
Veröffentlicht: (2026)

Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation
von: Engel, Andrew, et al.
Veröffentlicht: (2025)

AstroM$^3$: A self-supervised multimodal model for astronomy
von: Rizhko, Mariia, et al.
Veröffentlicht: (2024)

AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data
von: Truong, Tuan, et al.
Veröffentlicht: (2025)

Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
von: Rawat, Shivam, et al.
Veröffentlicht: (2026)

Explainable machine learning workflows for radio astronomical data processing
von: Yatawatta, S., et al.
Veröffentlicht: (2026)

Energy and polarization based on-line interference mitigation in radio interferometry
von: Yatawatta, Sarod, et al.
Veröffentlicht: (2024)

SM-Net: Learning a Continuous Spectral Manifold from Multiple Stellar Libraries
von: Anwar, Omar, et al.
Veröffentlicht: (2026)

InferA: A Smart Assistant for Cosmological Ensemble Data
von: Tam, Justin Z., et al.
Veröffentlicht: (2025)

Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program
von: Carrasco, Alejandro, et al.
Veröffentlicht: (2024)

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
ui	"standard"
language	"de"
VUFIND_SESSION	"a5738a277746488b1f7aefb35f6d1152"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790843623.5371 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a5738a277746488b1f7aefb35f6d1152" ]`]
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	"ui=standard; language=de; VUFIND_SESSION=a5738a277746488b1f7aefb35f6d1152"
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	"11471"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2501_18411/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2501_18411/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790843623.5288
REQUEST_TIME	1790843623

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler