Cover Image

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Wenlin, Li, Xiangyang, Dong, Kuicai, Wang, Yichao, Jia, Pengyue, Li, Xiaopeng, Zhang, Yingyi, Xu, Derong, Du, Zhaocheng, Guo, Huifeng, Tang, Ruiming, Zhao, Xiangyu
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Survey of Personalization: From RAG to Agent
by: Li, Xiaopeng, et al.
Published: (2025)

SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval
by: Li, Xiaopeng, et al.
Published: (2024)

Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing
by: Zhang, Wenlin, et al.
Published: (2026)

LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration
by: Zhang, Yingyi, et al.
Published: (2025)

Deep Research: A Survey of Autonomous Research Agents
by: Zhang, Wenlin, et al.
Published: (2025)

SampleLLM: Optimizing Tabular Data Synthesis in Recommendations
by: Gao, Jingtong, et al.
Published: (2025)

To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
by: Zhang, Wenlin, et al.
Published: (2026)

Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
by: Li, Xiaopeng, et al.
Published: (2026)

SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems
by: Jia, Pengyue, et al.
Published: (2024)

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
by: Zhang, Yingyi, et al.
Published: (2025)

LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations
by: Zhang, Wenlin, et al.
Published: (2024)

A Unified Framework for Multi-Domain CTR Prediction via Large Language Models
by: Fu, Zichuan, et al.
Published: (2023)

MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
by: Zhang, Sheng, et al.
Published: (2026)

Prompt Tuning as User Inherent Profile Inference Machine
by: Lu, Yusheng, et al.
Published: (2024)

ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems
by: Jia, Pengyue, et al.
Published: (2024)

Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
by: Zhang, Yingyi, et al.
Published: (2026)

Joint Modeling in Recommendations: A Survey
by: Zhao, Xiangyu, et al.
Published: (2025)

Scenario-Wise Rec: A Multi-Scenario Recommendation Benchmark
by: Li, Xiaopeng, et al.
Published: (2024)

HAMUR: Hyper Adapter for Multi-Domain Recommendation
by: Li, Xiaopeng, et al.
Published: (2023)

LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation
by: Wang, Yuhao, et al.
Published: (2024)

LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations
by: Gao, Jingtong, et al.
Published: (2024)

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation
by: Jia, Pengyue, et al.
Published: (2024)

RAGR: Review-Augmented Generative Recommendation
by: Zhang, Yingyi, et al.
Published: (2026)

No One Left Behind: How to Exploit the Incomplete and Skewed Multi-Label Data for Conversion Rate Prediction
by: Jia, Qinglin, et al.
Published: (2025)

CoIR: A Comprehensive Benchmark for Code Information Retrieval Models
by: Li, Xiangyang, et al.
Published: (2024)

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework
by: Zhang, Chao, et al.
Published: (2025)

GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization
by: Jia, Pengyue, et al.
Published: (2026)

Reinforced Preference Optimization for Reasoning-Augmented Recommendations
by: Gao, Jingtong, et al.
Published: (2026)

From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
by: Wu, Yaxiong, et al.
Published: (2025)

Retrievable Domain-Sensitive Feature Memory for Multi-Domain Recommendation
by: Zhao, Yuang, et al.
Published: (2024)

Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
by: Xu, Derong, et al.
Published: (2025)

Embedding Compression in Recommender Systems: A Survey
by: Li, Shiwei, et al.
Published: (2024)

Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
by: Liang, Jintao, et al.
Published: (2025)

Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation
by: Liu, Ziwei, et al.
Published: (2024)

MTRec: Learning to Align with User Preferences via Mental Reward Models
by: Zhao, Mengchen, et al.
Published: (2025)

Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models
by: Wu, Yichao, et al.
Published: (2026)

PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations
by: Guo, Chengcheng, et al.
Published: (2026)

Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
by: Li, Shiwei, et al.
Published: (2022)

FollowTable: A Benchmark for Instruction-Following Table Retrieval
by: Jin, Rihui, et al.
Published: (2026)

From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space
by: Jia, Pengyue, et al.
Published: (2026)