Imagen de Portada

IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Luo, Haohao, Li, Zexi, Xie, Yuexiang, Zhang, Wenhao, Li, Yaliang, Shen, Ying
Formato:	Preprint
Publicado:	2026
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

Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment
por: Zeng, Delong, et al.
Publicado: (2026)

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
por: Zhang, Wenhao, et al.
Publicado: (2025)

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
por: Wang, Shumin, et al.
Publicado: (2026)

Agent-Oriented Planning in Multi-Agent Systems
por: Li, Ao, et al.
Publicado: (2024)

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
por: Qian, Cheng, et al.
Publicado: (2025)

Learning Agent-Compatible Context Management for Long-Horizon Tasks
por: Yi, Lu, et al.
Publicado: (2026)

Exploring Selective Layer Fine-Tuning in Federated Learning
por: Sun, Yuchang, et al.
Publicado: (2024)

Tree-based Models for Vertical Federated Learning: A Survey
por: Qian, Bingchen, et al.
Publicado: (2025)

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
por: Yu, Yi, et al.
Publicado: (2026)

Knowledge Graph-Guided Retrieval Augmented Generation
por: Zhu, Xiangrong, et al.
Publicado: (2025)

Understanding Byzantine Robustness in Federated Learning with A Black-box Server
por: Zhao, Fangyuan, et al.
Publicado: (2024)

Proactive Dialogue Model with Intent Prediction
por: Luo, Yang
Publicado: (2026)

OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
por: Ye, Rui, et al.
Publicado: (2024)

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
por: Yao, Yi, et al.
Publicado: (2026)

KIMAs: A Configurable Knowledge Integrated Multi-Agent System
por: Li, Zitao, et al.
Publicado: (2025)

Very Large-Scale Multi-Agent Simulation in AgentScope
por: Pan, Xuchen, et al.
Publicado: (2024)

R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
por: Shi, Weijie, et al.
Publicado: (2026)

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
por: Nathani, Deepak, et al.
Publicado: (2026)

LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
por: Li, Wanli, et al.
Publicado: (2026)

PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
por: Xie, Zhifei, et al.
Publicado: (2026)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
por: Jiao, Qirui, et al.
Publicado: (2024)

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
por: Hou, Hongru, et al.
Publicado: (2026)

Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models
por: Chen, Die, et al.
Publicado: (2025)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
por: Li, Haozhan, et al.
Publicado: (2025)

TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
por: Wang, Jiaqi, et al.
Publicado: (2026)

AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
por: Jin, Jiarui, et al.
Publicado: (2026)

PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
por: Wang, Prince Zizhuang, et al.
Publicado: (2026)

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
por: Zhang, Shengtao, et al.
Publicado: (2026)

Morae: Proactively Pausing UI Agents for User Choices
por: Peng, Yi-Hao, et al.
Publicado: (2025)

DeepThink: Aligning Language Models with Domain-Specific User Intents
por: Li, Yang, et al.
Publicado: (2025)

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
por: Shi, Yucheng, et al.
Publicado: (2025)

MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning
por: Zhuang, Yuanxin, et al.
Publicado: (2025)

RLIF: Interactive Imitation Learning as Reinforcement Learning
por: Luo, Jianlan, et al.
Publicado: (2023)

PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
por: Chai, Yuxiang, et al.
Publicado: (2026)

JuggleRL: Mastering Ball Juggling with a Quadrotor via Deep Reinforcement Learning
por: Ji, Shilong, et al.
Publicado: (2025)

Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning
por: Feng, Yichun, et al.
Publicado: (2025)

MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networking
por: Hossain, Md. Kamrul, et al.
Publicado: (2026)

Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
por: Li, Maodong, et al.
Publicado: (2026)

RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment
por: Yang, Suorong, et al.
Publicado: (2025)

Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs
por: Wei, Fei, et al.
Publicado: (2025)