PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Yajie, Feng, Yue
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
por: Feng, Xinshun, et al.
Publicado: (2026)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
por: Li, Yibo, et al.
Publicado: (2026)

ToMCAT: Theory-of-Mind for Cooperative Agents in Teams via Multiagent Diffusion Policies
por: Sequeira, Pedro, et al.
Publicado: (2025)

PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training
por: Lv, Mingrui, et al.
Publicado: (2025)

One-Way Policy Optimization for Self-Evolving LLMs
por: Yang, Shuo, et al.
Publicado: (2026)

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
por: Zhou, Huilin, et al.
Publicado: (2026)

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
por: Wang, Junzhe, et al.
Publicado: (2026)

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
por: Zhang, Haozhen, et al.
Publicado: (2026)

InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
por: Huang, Chenyu, et al.
Publicado: (2026)

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
por: Liu, Jiaqi, et al.
Publicado: (2026)

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
por: Li, Yu, et al.
Publicado: (2026)

Group-in-Group Policy Optimization for LLM Agent Training
por: Feng, Lang, et al.
Publicado: (2025)

PolicyLong: Towards On-Policy Context Extension
por: Jia, Junlong, et al.
Publicado: (2026)

Policy Dispersion in Non-Markovian Environment
por: Qu, Bohao, et al.
Publicado: (2023)

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
por: Liu, Zongkai, et al.
Publicado: (2024)

Reinforcing Language Agents via Policy Optimization with Action Decomposition
por: Wen, Muning, et al.
Publicado: (2024)

UCPO: Uncertainty-Aware Policy Optimization
por: Zeng, Xianzhou, et al.
Publicado: (2026)

Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing
por: Khan, Azal Ahmad, et al.
Publicado: (2026)

AgentEvolver: Towards Efficient Self-Evolving Agent System
por: Zhai, Yunpeng, et al.
Publicado: (2025)

HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
por: Ding, Ken
Publicado: (2026)

Provable and Practical In-Context Policy Optimization for Self-Improvement
por: Yu, Tianrun, et al.
Publicado: (2026)

Intrinsic Reward Policy Optimization for Sparse-Reward Environments
por: Cho, Minjae, et al.
Publicado: (2026)

COPR: Continual Human Preference Learning via Optimal Policy Regularization
por: Zhang, Han, et al.
Publicado: (2024)

Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization
por: Xue, Yuan, et al.
Publicado: (2026)

POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
por: Menet, Nicolas, et al.
Publicado: (2026)

Calibration-Aware Policy Optimization for Reasoning LLMs
por: Wang, Ziqi, et al.
Publicado: (2026)

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
por: Luo, Haipeng, et al.
Publicado: (2023)

PA3: Policy-Aware Agent Alignment through Chain-of-Thought
por: Dipta, Shubhashis Roy, et al.
Publicado: (2026)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
por: Liu, Zeyuan, et al.
Publicado: (2026)

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
por: Li, Gengsheng, et al.
Publicado: (2026)

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
por: Wang, Jiaxuan, et al.
Publicado: (2026)

IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck
por: Deng, Huilin, et al.
Publicado: (2026)

Self-Evolving LLMs via Continual Instruction Tuning
por: Kang, Jiazheng, et al.
Publicado: (2025)

Decision Making in Non-Stationary Environments with Policy-Augmented Search
por: Pettet, Ava, et al.
Publicado: (2024)

Symbolic Learning Enables Self-Evolving Agents
por: Zhou, Wangchunshu, et al.
Publicado: (2024)

Towards Flash Thinking via Decoupled Advantage Policy Optimization
por: Tan, Zezhong, et al.
Publicado: (2025)

Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning
por: Lepel, Olivier, et al.
Publicado: (2024)

Structured Role-Aware Policy Optimization for Multimodal Reasoning
por: Jiang, Bingqing, et al.
Publicado: (2026)

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
por: Liang, Kun, et al.
Publicado: (2026)

ClawArena: Benchmarking AI Agents in Evolving Information Environments
por: Ji, Haonian, et al.
Publicado: (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	"es"
ui	"standard"
VUFIND_SESSION	"6e7236a787bdef21cd70f27cc4989c8c"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790932582.7702 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "6e7236a787bdef21cd70f27cc4989c8c" ]`]
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=es; ui=standard; VUFIND_SESSION=6e7236a787bdef21cd70f27cc4989c8c"
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	"34222"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2504_15313/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2504_15313/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790932582.7657
REQUEST_TIME	1790932582

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler