Can LLMs Translate Human Instructions into a Reinforcement Learning Agent's Internal Emergent Symbolic Representation?

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ma, Ziqi, Nguyen, Sao Mai, Xu, Philippe
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language Robotics
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Unsupervised Motion Retargeting for Human-Robot Imitation
von: Annabi, Louis, et al.
Veröffentlicht: (2024)

REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?
von: Jiang, Chenxi, et al.
Veröffentlicht: (2025)

Low-Back Pain Physical Rehabilitation by Movement Analysis in Clinical Trial
von: Nguyen, Sao Mai
Veröffentlicht: (2026)

Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs
von: Sun, Chuanneng, et al.
Veröffentlicht: (2024)

The intrinsic motivation of reinforcement and imitation learning for sequential tasks
von: Nguyen, Sao Mai
Veröffentlicht: (2024)

AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers
von: Chen, Yongchao, et al.
Veröffentlicht: (2023)

Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs
von: Hu, Zichao, et al.
Veröffentlicht: (2024)

Reconciling Spatial and Temporal Abstractions for Goal Representation
von: Zadem, Mehdi, et al.
Veröffentlicht: (2024)

Can LLMs plan paths with extra hints from solvers?
von: Wu, Erik, et al.
Veröffentlicht: (2024)

Unsupervised, Bottom-up Category Discovery for Symbol Grounding with a Curious Robot
von: Henry, Catherine, et al.
Veröffentlicht: (2024)

In-Context Learning Enables Robot Action Prediction in LLMs
von: Yin, Yida, et al.
Veröffentlicht: (2024)

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning
von: Dao, Alan, et al.
Veröffentlicht: (2025)

Skeleton-Based Transformer for Classification of Errors and Better Feedback in Low Back Pain Physical Rehabilitation Exercises
von: Marusic, Aleksa, et al.
Veröffentlicht: (2025)

Mental Modeling of Reinforcement Learning Agents by Language Models
von: Lu, Wenhao, et al.
Veröffentlicht: (2024)

Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
von: Poddar, Sriyash, et al.
Veröffentlicht: (2024)

PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models
von: Zhu, Wang Bill, et al.
Veröffentlicht: (2025)

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation
von: Chen, Yongchao, et al.
Veröffentlicht: (2025)

Coherence-Driven Multimodal Safety Dialogue with Active Learning for Embodied Agents
von: Hassan, Sabit, et al.
Veröffentlicht: (2024)

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
von: Yang, Haolin, et al.
Veröffentlicht: (2025)

CARTIER: Cartographic lAnguage Reasoning Targeted at Instruction Execution for Robots
von: Rivkin, Dmitriy, et al.
Veröffentlicht: (2023)

Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models
von: Chia, Yew Ken, et al.
Veröffentlicht: (2024)

JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents
von: Zheng, Kaizhi, et al.
Veröffentlicht: (2022)

LLMs for Robotic Object Disambiguation
von: Jiang, Connie, et al.
Veröffentlicht: (2024)

PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning
von: Sun, Yirong, et al.
Veröffentlicht: (2025)

FASIONAD++ : Integrating High-Level Instruction and Information Bottleneck in FAt-Slow fusION Systems for Enhanced Safety in Autonomous Driving with Adaptive Feedback
von: Qian, Kangan, et al.
Veröffentlicht: (2025)

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
von: Deng, Zhirui, et al.
Veröffentlicht: (2024)

CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning
von: Manas, Kumar, et al.
Veröffentlicht: (2024)

ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees
von: Sundarsingh, David Smith, et al.
Veröffentlicht: (2025)

Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
von: Dorbala, Vishnu Sashank, et al.
Veröffentlicht: (2023)

A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings
von: Cohen, Vanya, et al.
Veröffentlicht: (2024)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
von: Wang, Haozhe, et al.
Veröffentlicht: (2025)

PROGrasp: Pragmatic Human-Robot Communication for Object Grasping
von: Kang, Gi-Cheon, et al.
Veröffentlicht: (2023)

Instruct Large Language Models to Drive like Humans
von: Zhang, Ruijun, et al.
Veröffentlicht: (2024)

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
von: Li, Manling, et al.
Veröffentlicht: (2024)

AgentRefine: Enhancing Agent Generalization through Refinement Tuning
von: Fu, Dayuan, et al.
Veröffentlicht: (2025)

Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback
von: Zhu, Wang, et al.
Veröffentlicht: (2024)

LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
von: Sun, Chuanneng, et al.
Veröffentlicht: (2024)

Applying General Turn-taking Models to Conversational Human-Robot Interaction
von: Skantze, Gabriel, et al.
Veröffentlicht: (2025)

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
von: Xi, Jiajun, et al.
Veröffentlicht: (2024)

LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning
von: Singh, Utsav, 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
language	"de"
VUFIND_SESSION	"57902ef8b0d98f9e7179b4730896f0fa"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790847438.4265 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "57902ef8b0d98f9e7179b4730896f0fa" ]`]
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=de; VUFIND_SESSION=57902ef8b0d98f9e7179b4730896f0fa; 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	"63345"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2510_24259/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2510_24259/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790847438.4194
REQUEST_TIME	1790847438

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler