Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Wei, Cao, Defu, Pang, Jiacheng, Weng, Muyan, Liu, Yan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks
di: Weng, Muyan, et al.
Pubblicazione: (2026)

Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs
di: Yang, Wei, et al.
Pubblicazione: (2025)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
di: Ye, Wen, et al.
Pubblicazione: (2025)

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
di: Li, Zhongyi, et al.
Pubblicazione: (2026)

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

Intelligent Collaborative Optimization for Rubber Tyre Film Production Based on Multi-path Differentiated Clipping Proximal Policy Optimization
di: Ruan, Yinghao, et al.
Pubblicazione: (2025)

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
di: Liu, Jinbo, et al.
Pubblicazione: (2025)

Foundation Models for Demand Forecasting via Dual-Strategy Ensembling
di: Yang, Wei, et al.
Pubblicazione: (2025)

HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization
di: Zhang, Hao, et al.
Pubblicazione: (2026)

Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
di: Li, Yang, et al.
Pubblicazione: (2025)

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach
di: Tang, Xin, et al.
Pubblicazione: (2024)

Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation
di: Zhang, Haoji, et al.
Pubblicazione: (2026)

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
di: Liu, Tennison, et al.
Pubblicazione: (2025)

Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization
di: Carbonati, Andrea, et al.
Pubblicazione: (2026)

AMA: Adaptive Memory via Multi-Agent Collaboration
di: Huang, Weiquan, et al.
Pubblicazione: (2026)

HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
di: Yan, Yuping, et al.
Pubblicazione: (2026)

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
di: Chang, Ching, et al.
Pubblicazione: (2025)

Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning
di: Yang, Wei, et al.
Pubblicazione: (2025)

Self-Monitoring Benefits from Structural Integration: Lessons from Metacognition in Continuous-Time Multi-Timescale Agents
di: Xie, Ying
Pubblicazione: (2026)

TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis
di: Ye, Wen, et al.
Pubblicazione: (2024)

Multi-Agent Collaboration Mechanisms: A Survey of LLMs
di: Tran, Khanh-Tung, et al.
Pubblicazione: (2025)

TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration
di: Zhao, Jiuzhou, et al.
Pubblicazione: (2026)

Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
di: Bian, Haoyu, et al.
Pubblicazione: (2026)

Adaptive Event-Triggered Policy Gradient for Multi-Agent Reinforcement Learning
di: Siddique, Umer, et al.
Pubblicazione: (2025)

Evidence for Limited Metacognition in LLMs
di: Ackerman, Christopher
Pubblicazione: (2025)

Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces
di: Pan, Chaofan, et al.
Pubblicazione: (2025)

Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration
di: Wang, Zhimin, et al.
Pubblicazione: (2025)

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning
di: Tang, Shuo, et al.
Pubblicazione: (2024)

Cognition to Control - Multi-Agent Learning for Human-Humanoid Collaborative Transport
di: Zhang, Hao, et al.
Pubblicazione: (2026)

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
di: Wang, Chenyu, et al.
Pubblicazione: (2026)

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
di: Xi, Zhiheng, et al.
Pubblicazione: (2025)

AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence
di: Ma, Bo, et al.
Pubblicazione: (2025)

ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
di: Yang, Linyi, et al.
Pubblicazione: (2025)

MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
di: Han, Yichen, et al.
Pubblicazione: (2025)

PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
di: Liu, Yu, et al.
Pubblicazione: (2026)

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection
di: Cheng, Siyuan, et al.
Pubblicazione: (2026)

MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization
di: Zhang, Lanxue, et al.
Pubblicazione: (2025)

Exploring the Potential of Metacognitive Support Agents for Human-AI Co-Creation
di: Gmeiner, Frederic, et al.
Pubblicazione: (2025)

Joint Agent Memory and Exploration Learning via Novelty Signals
di: Tian, Shizuo, et al.
Pubblicazione: (2026)

Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting
di: Cao, Defu, et al.
Pubblicazione: (2025)

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	"ed76789417e352e3e983bb8391524723"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790867770.5566 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "ed76789417e352e3e983bb8391524723" ]`]
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=ed76789417e352e3e983bb8391524723; 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	"216.73.216.147"
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	"61725"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2603_07972/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_07972/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790867770.5414
REQUEST_TIME	1790867770

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler