Embodied Task Planning via Graph-Informed Action Generation with Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Xiang, Yan, Ning, Mortazavi, Masood
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

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
di: Tang, Yimin, et al.
Pubblicazione: (2024)

Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning
di: Zhang, Tao, et al.
Pubblicazione: (2024)

Surgical Action Planning with Large Language Models
di: Xu, Mengya, et al.
Pubblicazione: (2025)

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
di: Zhang, Wenqi, et al.
Pubblicazione: (2025)

Large Language Models as Generalizable Policies for Embodied Tasks
di: Szot, Andrew, et al.
Pubblicazione: (2023)

Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
di: Fei, Zhaoye, et al.
Pubblicazione: (2025)

P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task
di: Xu, Weiye, et al.
Pubblicazione: (2024)

A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks
di: Ni, Xuanfan, et al.
Pubblicazione: (2024)

SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models
di: Wu, Yi, et al.
Pubblicazione: (2024)

EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
di: Du, Mengfei, et al.
Pubblicazione: (2024)

LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments
di: Jia, Zixia, et al.
Pubblicazione: (2024)

Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs
di: Sun, Jia Ao, et al.
Pubblicazione: (2025)

EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory
di: Fan, Wenzhe, et al.
Pubblicazione: (2025)

AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
di: Hu, Mengkang, et al.
Pubblicazione: (2024)

SAP-Bench: Benchmarking Multimodal Large Language Models in Surgical Action Planning
di: Xu, Mengya, et al.
Pubblicazione: (2025)

Task Calibration: Calibrating Large Language Models on Inference Tasks
di: Li, Yingjie, et al.
Pubblicazione: (2024)

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
di: Du, Yiyang, et al.
Pubblicazione: (2026)

Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning
di: Yue, Yuanhao, et al.
Pubblicazione: (2024)

Interactive Task Planning with Language Models
di: Li, Boyi, et al.
Pubblicazione: (2023)

Figuratively Speaking: Authorship Attribution via Multi-Task Figurative Language Modeling
di: Katsios, Gregorios A, et al.
Pubblicazione: (2024)

GCoder: Improving Large Language Model for Generalized Graph Problem Solving
di: Zhang, Qifan, et al.
Pubblicazione: (2024)

Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
di: Samarinas, Chris, et al.
Pubblicazione: (2024)

LLM-driven Knowledge Distillation for Dynamic Text-Attributed Graphs
di: Roy, Amit, et al.
Pubblicazione: (2025)

TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning
di: Li, Xiang, et al.
Pubblicazione: (2024)

Large Language Models as Planning Domain Generators
di: Oswald, James, et al.
Pubblicazione: (2024)

Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving
di: Xie, Jingran, et al.
Pubblicazione: (2025)

Anatomy of a Feeling: Narrating Embodied Emotions via Large Vision-Language Models
di: Saim, Mohammad, et al.
Pubblicazione: (2025)

PULSE: Privileged Knowledge Transfer from Rich to Deployable Sensors for Embodied Multi-Sensory Learning
di: Zhao, Zihan, et al.
Pubblicazione: (2025)

Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model
di: Cui, Jiaxi, et al.
Pubblicazione: (2023)

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
di: Wang, Siyin, et al.
Pubblicazione: (2025)

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
di: Liang, Xun, et al.
Pubblicazione: (2024)

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?
di: Yang, Zhihui, et al.
Pubblicazione: (2025)

Controlling Large Language Model with Latent Actions
di: Jia, Chengxing, et al.
Pubblicazione: (2025)

Planning with Logical Graph-based Language Model for Instruction Generation
di: Zhang, Fan, et al.
Pubblicazione: (2023)

From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs
di: Liu, Yulong, et al.
Pubblicazione: (2024)

When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
di: Ning, Yuting, et al.
Pubblicazione: (2026)

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

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
di: Yang, Rui, et al.
Pubblicazione: (2025)

World Action Models: The Next Frontier in Embodied AI
di: Wang, Siyin, et al.
Pubblicazione: (2026)

Evaluating the Generation Capabilities of Large Chinese Language Models
di: Zeng, Hui, et al.
Pubblicazione: (2023)

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	"aa037c34e35ad88551efb85a88794408"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790899886.0944 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "aa037c34e35ad88551efb85a88794408" ]`]
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=aa037c34e35ad88551efb85a88794408; language=it"
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	"55714"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2601_21841/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2601_21841/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790899886.0899
REQUEST_TIME	1790899886

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler