Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Wei, He, Xiaonan, Zhang, Chuheng, Zhang, Xuyun, Xu, Xiaolong, Dou, Wanchun
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Policy Filtration for RLHF to Mitigate Noise in Reward Models
par: Zhang, Chuheng, et autres
Publié: (2024)

FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing
par: Jia, Yongzhe, et autres
Publié: (2024)

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
par: Jia, Yongzhe, et autres
Publié: (2024)

Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
par: Wang, Haoyu, et autres
Publié: (2026)

Proactive Dialogue Model with Intent Prediction
par: Luo, Yang
Publié: (2026)

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
par: Nathani, Deepak, et autres
Publié: (2026)

Affective Multimodal Agents with Proactive Knowledge Grounding for Emotionally Aligned Marketing Dialogue
par: Yu, Lin, et autres
Publié: (2025)

Enhancing Q-Value Updates in Deep Q-Learning via Successor-State Prediction
par: Zu, Lipeng, et autres
Publié: (2025)

IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning
par: Luo, Haohao, et autres
Publié: (2026)

PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation
par: Kaur, Kirandeep, et autres
Publié: (2026)

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
par: Zhang, Zijing, et autres
Publié: (2025)

Reward-RAG: Enhancing RAG with Reward Driven Supervision
par: Nguyen, Thang, et autres
Publié: (2024)

Stochastic Voronoi Ensembles for Anomaly Detection
par: Cao, Yang, et autres
Publié: (2026)

Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface
par: Hua, Wenyue, et autres
Publié: (2024)

Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations
par: Shen, Chenglei, et autres
Publié: (2026)

AgentRM: Enhancing Agent Generalization with Reward Modeling
par: Xia, Yu, et autres
Publié: (2025)

Provably Efficient Interactive-Grounded Learning with Personalized Reward
par: Zhang, Mengxiao, et autres
Publié: (2024)

Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning
par: Zhang, Heng, et autres
Publié: (2026)

WavReward: Spoken Dialogue Models With Generalist Reward Evaluators
par: Ji, Shengpeng, et autres
Publié: (2025)

Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown
par: Lou, Xingzhou, et autres
Publié: (2024)

Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards
par: Zhang, Hanping, et autres
Publié: (2025)

Aligning Spoken Dialogue Models from User Interactions
par: Wu, Anne, et autres
Publié: (2025)

ProAgent: Building Proactive Cooperative Agents with Large Language Models
par: Zhang, Ceyao, et autres
Publié: (2023)

Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
par: Kang, Xinyue, et autres
Publié: (2026)

What Do Latent Action Models Actually Learn?
par: Zhang, Chuheng, et autres
Publié: (2025)

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
par: Yao, Yihang, et autres
Publié: (2026)

Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm
par: Sukmana, Septian Enggar, et autres
Publié: (2026)

UserBench: An Interactive Gym Environment for User-Centric Agents
par: Qian, Cheng, et autres
Publié: (2025)

Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction
par: Wu, Yi, et autres
Publié: (2024)

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
par: Han, Zhixin, et autres
Publié: (2026)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
par: Ye, Rui, et autres
Publié: (2025)

Measuring User Understanding in Dialogue-based XAI Systems
par: Mindlin, Dimitry, et autres
Publié: (2024)

Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
par: Wang, Qi, et autres
Publié: (2025)

Timing Matters: Enhancing User Experience through Temporal Prediction in Smart Homes
par: Ganatra, Shrey, et autres
Publié: (2024)

Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks
par: He, Xiaoyang, et autres
Publié: (2024)

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
par: Hong, Joey, et autres
Publié: (2024)

Synthetic Interaction Data for Scalable Personalization in Large Language Models
par: Ma, Yuchen, et autres
Publié: (2026)

RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems
par: Ayed, Mehdi Ben, et autres
Publié: (2025)

Memory Injection Attacks on LLM Agents via Query-Only Interaction
par: Dong, Shen, et autres
Publié: (2025)

JAM: Keypoint-Guided Joint Prediction after Classification-Aware Marginal Proposal for Multi-Agent Interaction
par: Lin, Fangze, et autres
Publié: (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
language	"fr"
VUFIND_SESSION	"3370962c5babf7ac4dc8de4f124eb6c7"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790856783.8519 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "3370962c5babf7ac4dc8de4f124eb6c7" ]`]
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=fr; VUFIND_SESSION=3370962c5babf7ac4dc8de4f124eb6c7; 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	"4498"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2505_18731/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2505_18731/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790856783.8363
REQUEST_TIME	1790856783

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler