Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Yifu, Xu, Zishan, Yao, Zhiyuan, Lu, Yuquan, Lin, Jiaye, Hu, Sen, Tang, Zhenheng, Wang, Huacan, Chen, Ronghao
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning
par: Xu, Zishan, et autres
Publié: (2025)

Decoupling Continual Semantic Segmentation
par: Guo, Yifu, et autres
Publié: (2025)

Zero-Forgetting CISS via Dual-Phase Cognitive Cascades
par: Lu, Yuquan, et autres
Publié: (2026)

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
par: Liu, Chengwen, et autres
Publié: (2026)

AgentComp: From Agentic Reasoning to Compositional Mastery in Text-to-Image Models
par: Zarei, Arman, et autres
Publié: (2025)

ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attacks
par: Rong, Gabriel Lee Jun, et autres
Publié: (2026)

Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent
par: Chen, Wei, et autres
Publié: (2024)

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
par: Bian, Haonan, et autres
Publié: (2026)

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
par: Huang, Wenxuan, et autres
Publié: (2025)

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
par: Chng, Yong Xien, et autres
Publié: (2025)

Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization
par: Yang, Tiancheng, et autres
Publié: (2025)

InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
par: Hou, Bohan, et autres
Publié: (2026)

VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation
par: Li, Bo, et autres
Publié: (2026)

ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
par: Guo, Zichun, et autres
Publié: (2026)

Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives
par: Li, Daiqiang, et autres
Publié: (2026)

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
par: Sun, Haoyuan, et autres
Publié: (2025)

RadFabric: Agentic AI System with Reasoning Capability for Radiology
par: Chen, Wenting, et autres
Publié: (2025)

End-to-end Semantic-centric Video-based Multimodal Affective Computing
par: Lin, Ronghao, et autres
Publié: (2024)

SkyNative: A Native Multimodal Framework for Remote Sensing Visual Evidence Reasoning
par: Yang, Xiao, et autres
Publié: (2026)

Show-o2: Improved Native Unified Multimodal Models
par: Xie, Jinheng, et autres
Publié: (2025)

Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
par: Huo, Yu, et autres
Publié: (2026)

UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
par: Mao, Weijia, et autres
Publié: (2025)

Multi-source Multimodal Progressive Domain Adaption for Audio-Visual Deception Detection
par: Lin, Ronghao, et autres
Publié: (2025)

Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
par: Yang, Wenhao, et autres
Publié: (2026)

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
par: Mao, Weijia, et autres
Publié: (2025)

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
par: Shiri, Fatemeh, et autres
Publié: (2024)

Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning
par: Gu, Zishan, et autres
Publié: (2024)

CoReS: Orchestrating the Dance of Reasoning and Segmentation
par: Bao, Xiaoyi, et autres
Publié: (2024)

OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning
par: Zhao, Shifang, et autres
Publié: (2025)

LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection
par: Li, Weijia, et autres
Publié: (2025)

MuDD: A Multimodal Deception Detection Dataset and GSR-Guided Progressive Distillation for Non-Contact Deception Detection
par: Jiang, Peiyuan, et autres
Publié: (2026)

SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language Models
par: Hu, Zhiyuan, et autres
Publié: (2025)

DeepEyesV2: Toward Agentic Multimodal Model
par: Hong, Jack, et autres
Publié: (2025)

CloneMem: Benchmarking Long-Term Memory for AI Clones
par: Hu, Sen, et autres
Publié: (2026)

FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation
par: Zhang, Liuzhou, et autres
Publié: (2026)

UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
par: Chen, Yanzhe, et autres
Publié: (2025)

DUALVISION: RGB-Infrared Multimodal Large Language Models for Robust Visual Reasoning
par: Majeedi, Abrar, et autres
Publié: (2026)

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
par: Huang, Wenxuan, et autres
Publié: (2026)

Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation
par: Zhang, Jing, et autres
Publié: (2026)

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
par: Chen, Dongyang, et autres
Publié: (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
language	"fr"
ui	"standard"
VUFIND_SESSION	"614ae75d0f72f080275bf113dcc86291"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790883836.3014 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "614ae75d0f72f080275bf113dcc86291" ]`]
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	"language=fr; ui=standard; VUFIND_SESSION=614ae75d0f72f080275bf113dcc86291"
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	"15187"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2511_15351/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2511_15351/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790883836.2972
REQUEST_TIME	1790883836

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler