Imagen de Portada

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hou, Hongru, Mei, Tiehua, Geng, Denghui, Huang, Jinhui, Xu, Ao, Chen, Hengrui, Liang, Jiaqing, Yang, Deqing
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems
por: Mei, Tiehua, et al.
Publicado: (2025)

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
por: Mei, Tiehua, et al.
Publicado: (2026)

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
por: Liu, Mingjie, et al.
Publicado: (2025)

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
por: Zhang, Hao, et al.
Publicado: (2026)

Heterogeneous Influence Maximization in User Recommendation
por: Hou, Hongru, et al.
Publicado: (2025)

What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty
por: Zhang, Bowei, et al.
Publicado: (2025)

Adaptive Reinforcement Learning Planning: Harnessing Large Language Models for Complex Information Extraction
por: Ding, Zepeng, et al.
Publicado: (2024)

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
por: Lv, Minxuan, et al.
Publicado: (2026)

Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction
por: Ding, Zepeng, et al.
Publicado: (2024)

RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving
por: Ding, Zepeng, et al.
Publicado: (2025)

ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
por: Huang, Yizheng, et al.
Publicado: (2026)

ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
por: Ding, Hongxin, et al.
Publicado: (2025)

From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
por: Xu, Ke, et al.
Publicado: (2026)

LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration
por: Qiu, Ruiyu, et al.
Publicado: (2025)

Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization
por: Peng, Xiyue, et al.
Publicado: (2024)

VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
por: Tan, Junwen, et al.
Publicado: (2026)

Partial Policy Gradients for RL in LLMs
por: Mathur, Puneet, et al.
Publicado: (2026)

ProMRVL-CAD: Proactive Dialogue System with Multi-Round Vision-Language Interactions for Computer-Aided Diagnosis
por: Li, Xueshen, et al.
Publicado: (2025)

ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents
por: Ding, Lei, et al.
Publicado: (2026)

TreeRL: LLM Reinforcement Learning with On-Policy Tree Search
por: Hou, Zhenyu, et al.
Publicado: (2025)

Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning
por: Shen, Ye, et al.
Publicado: (2021)

Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
por: Yang, Hongru, et al.
Publicado: (2024)

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
por: Li, Ao, et al.
Publicado: (2026)

EDGE: Enhanced Grounded GUI Understanding with Enriched Multi-Granularity Synthetic Data
por: Chen, Xuetian, et al.
Publicado: (2024)

Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient
por: You, Haoxiang, et al.
Publicado: (2026)

DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization
por: Xie, Xuan, et al.
Publicado: (2025)

Closing the Loop: Coordinating Inventory and Recommendation via Deep Reinforcement Learning on Multiple Timescales
por: Jiang, Jinyang, et al.
Publicado: (2025)

Policy Improvement Reinforcement Learning
por: Wang, Huaiyang, et al.
Publicado: (2026)

Deep Research as Rubric for Reinforcement Learning
por: Mei, Wangyi, et al.
Publicado: (2026)

Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality
por: Ma, Shaocong, et al.
Publicado: (2025)

IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning
por: Luo, Haohao, et al.
Publicado: (2026)

Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling
por: Zhou, Xubin, et al.
Publicado: (2026)

ProGuard: Towards Proactive Multimodal Safeguard
por: Yu, Shaohan, et al.
Publicado: (2025)

Dynamical Persistent Homology via Wasserstein Gradient Flow
por: Wang, Minghua, et al.
Publicado: (2024)

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
por: Liu, Bingshuai, et al.
Publicado: (2025)

A Historical Interaction-Enhanced Shapley Policy Gradient Algorithm for Multi-Agent Credit Assignment
por: Ding, Ao, et al.
Publicado: (2025)

FlowIE: Efficient Image Enhancement via Rectified Flow
por: Zhu, Yixuan, et al.
Publicado: (2024)

ProMark: Proactive Diffusion Watermarking for Causal Attribution
por: Asnani, Vishal, et al.
Publicado: (2024)

ProCIS: A Benchmark for Proactive Retrieval in Conversations
por: Samarinas, Chris, et al.
Publicado: (2024)

Rectifying Regression in Reinforcement Learning
por: Ayoub, Alex, et al.
Publicado: (2025)