Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gupta, Vatsal, Sreenivasamurthy, Darshan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

On Policy Reuse: An Expressive Language for Representing and Executing General Policies that Call Other Policies
by: Bonet, Blai, et al.
Published: (2024)

APEX: Agent Payment Execution with Policy for Autonomous Agent API Access
by: Uddin, Mohd Safwan, et al.
Published: (2026)

P^2O: Joint Policy and Prompt Optimization
by: Lu, Xinyu, et al.
Published: (2026)

Credo: Declarative Control of LLM Pipelines via Beliefs and Policies
by: Lu, Duo, et al.
Published: (2026)

From Natural Language to Executable Narsese: A Neuro-Symbolic Benchmark and Pipeline for Reasoning with NARS
by: Gabriel, Mina, et al.
Published: (2026)

ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
by: Palattuparambil, Ajsal Shereef, et al.
Published: (2026)

Probing the Limits of Stylistic Alignment in Vision-Language Models
by: Farajidizaji, Asma, et al.
Published: (2025)

OM2P: Offline Multi-Agent Mean-Flow Policy
by: Li, Zhuoran, et al.
Published: (2025)

LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance
by: Wang, Yu, et al.
Published: (2025)

LLM-Supported Natural Language to Bash Translation
by: Westenfelder, Finnian, et al.
Published: (2025)

POEX: Towards Policy Executable Jailbreak Attacks Against the LLM-based Robots
by: Lu, Xuancun, et al.
Published: (2024)

CPGPrompt: Translating Clinical Guidelines into LLM-Executable Decision Support
by: Deng, Ruiqi, et al.
Published: (2026)

The Last Fingerprint: How Markdown Training Shapes LLM Prose
by: Freeburg, E. M.
Published: (2026)

SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
by: Arachchige, Nadun Ranawaka, et al.
Published: (2025)

Revisiting the Role of Natural Language Code Comments in Code Translation
by: Gupta, Monika, et al.
Published: (2026)

Policy Optimized Text-to-Image Pipeline Design
by: Gadot, Uri, et al.
Published: (2025)

CAPE: Capability Achievement via Policy Execution
by: Ball, David
Published: (2025)

MiniLLM: On-Policy Distillation of Large Language Models
by: Gu, Yuxian, et al.
Published: (2023)

A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks
by: Vatsal, Shubham, et al.
Published: (2024)

PolicyBank: Evolving Policy Understanding for LLM Agents
by: Choi, Jihye, et al.
Published: (2026)

LLM Company Policies and Policy Implications in Software Organizations
by: Khojah, Ranim, et al.
Published: (2025)

Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets
by: Gupta, Vatsal, et al.
Published: (2023)

Real-Time Execution of Action Chunking Flow Policies
by: Black, Kevin, et al.
Published: (2025)

PolicyPad: Collaborative Prototyping of LLM Policies
by: Feng, K. J. Kevin, et al.
Published: (2025)

Policy of Thoughts: Scaling LLM Reasoning via Test-time Policy Evolution
by: Jiao, Zhengbo, et al.
Published: (2026)

D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss
by: Zou, Guowei, et al.
Published: (2025)

Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions
by: Pan, Zhuoran, et al.
Published: (2026)

Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
by: Zhang, Chaoyuan, et al.
Published: (2025)

PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
by: Gundawar, Atharva, et al.
Published: (2025)

An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees
by: Chen, ZhenDong, et al.
Published: (2025)

Tree Search-Based Policy Optimization under Stochastic Execution Delay
by: Valensi, David, et al.
Published: (2024)

Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents
by: Vatsal, Shubham, et al.
Published: (2026)

CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World
by: Fu, Yankai, et al.
Published: (2025)

MutaGReP: Execution-Free Repository-Grounded Plan Search for Code-Use
by: Khan, Zaid, et al.
Published: (2025)

Policy-Aware Generative AI for Safe, Auditable Data Access Governance
by: Mandalawi, Shames Al, et al.
Published: (2025)

"I Apologize For Not Understanding Your Policy": Exploring the Specification and Evaluation of User-Managed Access Control Policies by AI Virtual Assistants
by: Mondragon, Jennifer, et al.
Published: (2025)

RAGent: Retrieval-based Access Control Policy Generation
by: Jayasundara, Sakuna Harinda, et al.
Published: (2024)

STELP: Secure Transpilation and Execution of LLM-Generated Programs
by: Shinde, Swapnil, et al.
Published: (2026)

A Policy-Driven Runtime Layer for Agentic LLM Serving
by: Zhang, Rui, et al.
Published: (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
VUFIND_SESSION	"60b2b6c871811559aafcaaf59c609694"
language	"en"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790712569.0912 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "60b2b6c871811559aafcaaf59c609694" ]`]
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	"VUFIND_SESSION=60b2b6c871811559aafcaaf59c609694; language=en; 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	"56223"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2603_15799/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2603_15799/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790712569.0852
REQUEST_TIME	1790712569

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
VUFIND_SESSION	"60b2b6c871811559aafcaaf59c609694"
language	"en"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790712569.0912 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "60b2b6c871811559aafcaaf59c609694" ]`]
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	"VUFIND_SESSION=60b2b6c871811559aafcaaf59c609694; language=en; 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	"56223"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2603_15799/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2603_15799/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790712569.0852
REQUEST_TIME	1790712569

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler

Similar Items

Similar Items

Environment & details:

Environment & details: