AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Jiatao, Ye, Mao, Peng, Cheng, Yin, Xunjian, Wan, Xiaojun
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models
von: Li, Jiatao, et al.
Veröffentlicht: (2024)

Who Writes What: Unveiling the Impact of Author Roles on AI-generated Text Detection
von: Li, Jiatao, et al.
Veröffentlicht: (2025)

ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions
von: Zhang, Xu, et al.
Veröffentlicht: (2024)

Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability
von: Hu, Xinyu, et al.
Veröffentlicht: (2024)

Error-Robust Retrieval for Chinese Spelling Check
von: Yin, Xunjian, et al.
Veröffentlicht: (2022)

Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation
von: Yin, Xunjian, et al.
Veröffentlicht: (2024)

DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models
von: Xie, Jinxiang, et al.
Veröffentlicht: (2024)

Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction
von: Li, Yilin, et al.
Veröffentlicht: (2025)

EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning
von: Zhang, Junzhe, et al.
Veröffentlicht: (2024)

SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval
von: Li, Jiatao, et al.
Veröffentlicht: (2024)

Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldview
von: Li, Jiatao, et al.
Veröffentlicht: (2025)

MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
von: Zhang, Junzhe, et al.
Veröffentlicht: (2024)

Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review
von: Li, Jiatao, et al.
Veröffentlicht: (2025)

LEDOM: Reverse Language Model
von: Yin, Xunjian, et al.
Veröffentlicht: (2025)

Differentiable Evolutionary Reinforcement Learning
von: Cheng, Sitao, et al.
Veröffentlicht: (2025)

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
von: Cheng, Sitao, et al.
Veröffentlicht: (2024)

Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation
von: Ruan, Jie, et al.
Veröffentlicht: (2024)

Coding Agents are Effective Long-Context Processors
von: Cao, Weili, et al.
Veröffentlicht: (2026)

AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection
von: Yang, Tiankai, et al.
Veröffentlicht: (2025)

UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localization
von: Zhang, Huixuan, et al.
Veröffentlicht: (2025)

AI-generated text boundary detection with RoFT
von: Kushnareva, Laida, et al.
Veröffentlicht: (2023)

BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation
von: Li, Zhaoyi, et al.
Veröffentlicht: (2026)

Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection
von: Jung, Minseok, et al.
Veröffentlicht: (2025)

Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm
von: Mo, Yuhong, et al.
Veröffentlicht: (2024)

Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection
von: Miralles-González, Pablo, et al.
Veröffentlicht: (2025)

Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models
von: Chen, Xiang, et al.
Veröffentlicht: (2023)

How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
von: Zhang, Huixuan, et al.
Veröffentlicht: (2025)

MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds
von: Wu, Junxi, et al.
Veröffentlicht: (2025)

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
von: Cheng, Sitao, et al.
Veröffentlicht: (2025)

The Geometry of Reasoning: Flowing Logics in Representation Space
von: Zhou, Yufa, et al.
Veröffentlicht: (2025)

AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMs
von: Siro, Clemencia, et al.
Veröffentlicht: (2024)

WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness
von: Huang, Baizhou, et al.
Veröffentlicht: (2024)

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations
von: Zhou, Yinghan, et al.
Veröffentlicht: (2025)

LLM-based NLG Evaluation: Current Status and Challenges
von: Gao, Mingqi, et al.
Veröffentlicht: (2024)

M$^{3}$T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark
von: Zhang, Huixuan, et al.
Veröffentlicht: (2025)

Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models
von: Zhang, Huixuan, et al.
Veröffentlicht: (2024)

Enhancing Jailbreak Attacks with Diversity Guidance
von: Zhang, Xu, et al.
Veröffentlicht: (2024)

SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs
von: Zhang, Zhenliang, et al.
Veröffentlicht: (2025)

CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing
von: Yu, Zhenghan, et al.
Veröffentlicht: (2025)

QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs
von: Zhu, Junlin, et al.
Veröffentlicht: (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
ui	"standard"
VUFIND_SESSION	"b7e8b9addcb305bed95cae888fd4898f"
language	"de"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790888864.5593 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "b7e8b9addcb305bed95cae888fd4898f" ]`]
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; VUFIND_SESSION=b7e8b9addcb305bed95cae888fd4898f; language=de"
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	"63639"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2505_15261/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2505_15261/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790888864.5551
REQUEST_TIME	1790888864

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler